Compare commits

...

1937 Commits

Author SHA1 Message Date
Aiden Cline 57a8c746e5 [opencode/minimax] Add reasoning options 2026-06-13 16:00:55 -05:00
Aiden Cline 1ddcd9bc32 Merge pull request #2286 from anomalyco/fix/remove-glm-5.2-standard-apis
fix: remove GLM-5.2 from standard Z.AI APIs
2026-06-13 15:41:30 -05:00
Aiden Cline 7a9b4a167c Merge pull request #2206 from anomalyco/feat/berget-reasoning-options-wave3
[berget] Add reasoning options
2026-06-13 15:40:33 -05:00
Aiden Cline 33d88e41df Merge pull request #2203 from anomalyco/feat/the-grid-ai-reasoning-options-wave3
[the-grid-ai] Add reasoning options
2026-06-13 15:40:11 -05:00
Aiden Cline 300a46cfdc Merge pull request #2201 from anomalyco/feat/neuralwatt-reasoning-options-wave3
[neuralwatt] Add reasoning options
2026-06-13 15:36:53 -05:00
Aiden Cline 0e3c00595b [neuralwatt] Correct reasoning controls 2026-06-13 15:35:31 -05:00
Aiden Cline 1c9b748976 fix: remove GLM-5.2 from standard Z.AI APIs 2026-06-13 15:33:40 -05:00
Aiden Cline cf4ccf92ae Merge pull request #2285 from niushuai1991/add-glm-5.2-config
Add GLM-5.2 model config to zai and zhipuai providers
2026-06-13 15:31:44 -05:00
Aiden Cline a4a9d29c99 [berget] Correct remaining reasoning efforts 2026-06-13 15:30:02 -05:00
Aiden Cline 4670f99aac Merge pull request #2283 from anomalyco/fix/venice-sync-last-updated
fix(venice): preserve model update dates
2026-06-13 15:28:40 -05:00
Aiden Cline 3839c610a6 [berget] Remove unsupported GLM efforts 2026-06-13 15:28:06 -05:00
Aiden Cline b1095231a5 Merge pull request #2215 from anomalyco/feat/dinference-reasoning-options-wave3
[dinference] Mark reasoning controls fixed
2026-06-13 15:27:56 -05:00
Aiden Cline e8333b63a1 Merge pull request #2202 from anomalyco/feat/regolo-ai-reasoning-options-wave3
[regolo-ai] Add reasoning options
2026-06-13 15:27:32 -05:00
Aiden Cline 704ffc7371 Merge pull request #2229 from anomalyco/feat/anyapi-reasoning-options-wave4
[anyapi] Add reasoning options
2026-06-13 15:26:41 -05:00
Aiden Cline 4fdda4f262 [anyapi] Correct Claude reasoning options 2026-06-13 15:20:11 -05:00
Aiden Cline 41c243713f [berget] Correct Kimi reasoning option 2026-06-13 15:16:12 -05:00
Aiden Cline 36024f1bd2 Merge pull request #2218 from anomalyco/feat/gmicloud-reasoning-options-wave3
[gmicloud] Add reasoning options
2026-06-13 15:14:50 -05:00
Aiden Cline bfb0d3722a [gmicloud] Correct Claude reasoning options 2026-06-13 15:12:38 -05:00
Niu Shuai 3877dcf8b6 feat: add GLM-5.2 model config to zai and zhipuai providers 2026-06-14 04:10:00 +08:00
Aiden Cline d171755a90 Merge pull request #2220 from anomalyco/feat/azure-reasoning-options-wave3
[azure] Backfill DeepSeek V4 reasoning options
2026-06-13 14:39:42 -05:00
Aiden Cline 5394af4d63 Merge pull request #2189 from anomalyco/feat/upstage-reasoning-options-wave3
[upstage] Add reasoning options
2026-06-13 14:39:01 -05:00
Aiden Cline b78f6fb53e Merge pull request #2191 from anomalyco/feat/tencent-coding-plan-reasoning-options-wave3
[tencent-coding-plan] Add reasoning options
2026-06-13 14:36:46 -05:00
Aiden Cline 9e3c7d41ff Merge pull request #2200 from anomalyco/feat/modelscope-reasoning-options-wave3
[modelscope] Add reasoning options
2026-06-13 14:36:35 -05:00
Aiden Cline e8b1862dc2 Merge pull request #2195 from anomalyco/feat/minimax-cn-coding-plan-reasoning-options-wave3
[minimax-cn-coding-plan] Complete reasoning options
2026-06-13 14:36:20 -05:00
Aiden Cline 63da7583b5 Merge pull request #2188 from anomalyco/feat/moonshotai-reasoning-options-wave3
[moonshotai] Complete reasoning options
2026-06-13 14:36:03 -05:00
Aiden Cline e5b1221baa fix(venice): preserve model update dates 2026-06-13 14:31:04 -05:00
Aiden Cline 43e502a0bc Merge pull request #2282 from anomalyco/fix/mimo-reasoning-options-audit
fix MiMo reasoning options across providers
2026-06-13 14:16:58 -05:00
Aiden Cline b19a423f31 fix MiMo reasoning options across providers 2026-06-13 14:13:33 -05:00
Aiden Cline 77e04a5f1a Merge pull request #2184 from anomalyco/feat/nova-reasoning-options-wave3
[nova] Add reasoning options
2026-06-13 13:32:23 -05:00
Aiden Cline 2e1a8245c6 Merge pull request #2181 from anomalyco/feat/cloudferro-sherlock-reasoning-options-wave3
[cloudferro-sherlock] Add reasoning options
2026-06-13 13:32:14 -05:00
Aiden Cline b197346558 Merge pull request #2183 from anomalyco/feat/drun-reasoning-options-wave3
[drun] Add reasoning options
2026-06-13 13:32:03 -05:00
Aiden Cline a04024bd21 Merge pull request #2185 from anomalyco/feat/moark-reasoning-options-wave3
[moark] Add reasoning options
2026-06-13 13:31:53 -05:00
Aiden Cline 0186f9e638 Merge pull request #2187 from anomalyco/feat/poolside-reasoning-options-wave3
[poolside] Add reasoning options
2026-06-13 13:31:35 -05:00
Aiden Cline deb664d9c6 Merge pull request #2186 from anomalyco/feat/lucidquery-reasoning-options-wave3
[lucidquery] Add reasoning options
2026-06-13 13:31:26 -05:00
Aiden Cline 8ade756d9b Merge pull request #2182 from anomalyco/feat/inception-reasoning-options-wave3
[inception] Add reasoning options
2026-06-13 13:31:14 -05:00
Aiden Cline fc109cc2c2 Merge pull request #2221 from anomalyco/feat/xiaomi-token-plan-cn-reasoning-options-wave3
[xiaomi-token-plan] Add reasoning toggles
2026-06-13 13:30:47 -05:00
Aiden Cline 0427b955c6 Merge pull request #2222 from anomalyco/feat/ambient-reasoning-options-wave3
[ambient] Add reasoning options
2026-06-13 13:23:26 -05:00
Aiden Cline e1c887294a Merge pull request #2225 from anomalyco/feat/abacus-reasoning-options-wave4
[abacus] Add reasoning options
2026-06-13 13:23:10 -05:00
Aiden Cline 67cbb6e5f4 Merge pull request #2226 from anomalyco/feat/cloudflare-ai-gateway-reasoning-options-wave4
[cloudflare-ai-gateway] Add reasoning options
2026-06-13 13:18:42 -05:00
Aiden Cline 3f183e2962 Merge pull request #2227 from anomalyco/feat/chutes-reasoning-options-wave4
[chutes] Add reasoning options
2026-06-13 13:18:23 -05:00
Aiden Cline b2ada02538 Merge pull request #2238 from anomalyco/feat/digitalocean-reasoning-options-wave4
[digitalocean] Add reasoning options
2026-06-13 13:16:48 -05:00
Aiden Cline 6dcd5d65a0 Merge pull request #2244 from anomalyco/feat/huggingface-reasoning-options-wave4
[huggingface] Add reasoning options
2026-06-13 13:14:23 -05:00
Aiden Cline 9f2265f81f Merge pull request #2281 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-06-13 13:13:02 -05:00
Aiden Cline b0e4f07b73 Merge pull request #2224 from anomalyco/feat/auriko-reasoning-options-wave4
[auriko] Add reasoning options
2026-06-13 13:12:39 -05:00
Aiden Cline 503b07ddfa Merge pull request #2219 from anomalyco/feat/mistral-reasoning-options-wave3
[mistral] Mark Magistral reasoning controls fixed
2026-06-13 13:11:11 -05:00
Aiden Cline d13507ee94 Merge pull request #2217 from anomalyco/feat/lilac-reasoning-options-wave3
[lilac] Add reasoning options
2026-06-13 13:10:58 -05:00
github-actions[bot] 1f391a1908 chore(sync): update OpenRouter model catalog 2026-06-13 17:46:55 +00:00
Aiden Cline f31519bf52 Merge pull request #2280 from CodeAnimal/az-deepseek-v4
Correct Azure DeepSeek V4 model prices
2026-06-13 11:25:26 -05:00
Aiden Cline d56e8387ba Merge pull request #2274 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-06-13 11:25:15 -05:00
CodeAnimal 0132340a2c Correct Azure DeepSeek V4 model prices 2026-06-13 17:23:18 +01:00
Aiden Cline ead650e6b0 Merge pull request #2277 from ririnto/feat/zai-coding-plan-glm-5-2-anthropic
Add ZAI Coding Plan GLM-5.2 with Anthropic provider model
2026-06-13 11:19:37 -05:00
Aiden Cline c3beda0405 fix(zai-coding-plan): use default GLM-5.2 provider 2026-06-13 11:17:47 -05:00
Aiden Cline 814770c1c7 Merge dev and reuse Kimi K2.7 metadata 2026-06-13 11:09:49 -05:00
Aiden Cline e3d49ae6e2 Merge pull request #2279 from mathiasloh/feat_add_ollama_cloud_kimi_k27_code
feat(ollama-cloud): add kimi-k2.7-code
2026-06-13 11:07:44 -05:00
Aiden Cline fdabca87a0 Merge pull request #2275 from jubalm/add-zai-glm-5-2
Add ZAI Coding Plan GLM-5.2
2026-06-13 11:07:27 -05:00
github-actions[bot] acd9fa80ad chore(sync): update OpenRouter model catalog 2026-06-13 15:49:42 +00:00
mathias.loh 00c5b75ed9 feat(ollama-cloud): add kimi-k2.7-code 2026-06-13 22:42:54 +08:00
ririnto d210e45dd5 refactor(zai-coding-plan): split GLM-5.2 metadata into model + base_model reference
Move provider-agnostic facts (name, family, dates, capability flags,
limit, modalities) into models/zhipuai/glm-5.2.toml and reference it
via base_model in the provider TOML, which now keeps only provider-
specific fields (reasoning_options, interleaved, cost, per-model
anthropic [provider] override). Per README wrapper-provider guidance.
2026-06-13 22:39:29 +09:00
ririnto c9e026b5de feat(zai-coding-plan): add GLM-5.2 model metadata 2026-06-13 18:04:46 +09:00
Jubal Mabaquiao 3be537dad4 Add ZAI Coding Plan GLM-5.2 2026-06-13 16:45:57 +08:00
Aiden Cline 63a7bc11a9 Merge pull request #2216 from anomalyco/feat/inceptron-reasoning-options-wave3
[inceptron] Add reasoning options
2026-06-13 00:30:24 -05:00
Aiden Cline 0d2db5359d Merge pull request #2258 from anomalyco/feat/alibaba-coding-plan-cn-reasoning-options-final
[alibaba-coding-plan-cn] Add reasoning options
2026-06-13 00:27:45 -05:00
Aiden Cline a2d9f79f7e Merge pull request #2255 from anomalyco/feat/alibaba-coding-plan-reasoning-options-final
[alibaba-coding-plan] Add reasoning options
2026-06-13 00:27:30 -05:00
Aiden Cline e4d366cf4f Merge pull request #2256 from anomalyco/feat/evroc-reasoning-options-final
[evroc] Add reasoning options
2026-06-13 00:27:15 -05:00
Aiden Cline 9631b93843 Merge pull request #2260 from anomalyco/feat/alibaba-token-plan-cn-reasoning-options-final
feat(alibaba-token-plan-cn): add reasoning options
2026-06-13 00:27:01 -05:00
Aiden Cline 5424fbd2de Merge pull request #2270 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-06-13 00:26:42 -05:00
Aiden Cline 73cbf85a43 Merge pull request #2272 from anomalyco/automation/sync-models-vercel
chore(sync): update Vercel AI Gateway model catalog
2026-06-13 00:26:27 -05:00
Aiden Cline 097afb7e31 Merge pull request #2273 from zainhas/dev
[Together AI] add minimax m3
2026-06-13 00:26:12 -05:00
Zain Hasan 2c5ebe8219 [Together AI] add minimax m3 2026-06-12 22:12:45 -07:00
Frank 3a7b0ba2dc update zen models 2026-06-13 01:00:30 -04:00
github-actions[bot] e6c0abd6a9 chore(sync): update Vercel AI Gateway model catalog 2026-06-13 03:26:15 +00:00
github-actions[bot] 5288464365 chore(sync): update OpenRouter model catalog 2026-06-13 03:26:13 +00:00
Aiden Cline 7900fcd5a6 Merge pull request #2271 from shzdehmd/dev
feat(fireworks-ai): adding Kimi K2.7 Code, Qwen 3.7 Plus, and Minimax M3; removing deprecated models
2026-06-12 21:51:13 -05:00
Ahmad Shahzad 2df2c13060 feat(fireworks-ai): add K2.7 Code variants, Qwen 3.7 Plus, Minimax M3; remove deprecated models
- Add Kimi K2.7 Code (accounts/fireworks/models/kimi-k2p7-code)

- Add Kimi K2.7 Code Fast (accounts/fireworks/routers/kimi-k2p7-code-fast)

- Add Qwen 3.7 Plus (accounts/fireworks/models/qwen3p7-plus)

- Add Minimax M3 (accounts/fireworks/models/minimax-m3)

- Remove deprecated Kimi K2.5, Minimax M2.5, and Qwen 3.6 Plus
2026-06-13 07:48:41 +05:00
Aiden Cline f846124b1f Merge pull request #2257 from anomalyco/feat/google-reasoning-options-final
[google] Complete reasoning options
2026-06-12 17:47:42 -05:00
Aiden Cline cc81c1843f Merge pull request #2259 from anomalyco/feat/freemodel-reasoning-options-final
[freemodel] Add reasoning options
2026-06-12 17:47:16 -05:00
Aiden Cline c7823958d4 [freemodel] Add Anthropic reasoning controls 2026-06-12 17:42:25 -05:00
Aiden Cline 0178741953 [freemodel] Add OpenAI reasoning efforts 2026-06-12 17:34:32 -05:00
Aiden Cline 75db7752f5 Merge pull request #2156 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-06-12 17:31:09 -05:00
Aiden Cline 48d1bc2ee6 Merge pull request #2265 from jcraftsman/update-umans-ai-provider
Update Umans AI Coding Plan + add Umans AI (pay-per-token) provider
2026-06-12 17:30:09 -05:00
Aiden Cline d147b31d97 Merge pull request #2266 from anomalyco/automation/sync-models-vercel
chore(sync): update Vercel AI Gateway model catalog
2026-06-12 17:29:37 -05:00
github-actions[bot] b6fea3d470 chore(sync): update Vercel AI Gateway model catalog 2026-06-12 21:54:31 +00:00
github-actions[bot] d3fe5e3f4e chore(sync): update OpenRouter model catalog 2026-06-12 21:54:30 +00:00
Frank 1280fc51bc update go models 2026-06-12 16:24:50 -04:00
Aiden Cline 0e6590cc7a Merge pull request #2269 from anomalyco/fix/kimi-family-sync
fix(sync): normalize Kimi model families
2026-06-12 14:13:38 -05:00
Aiden Cline 78cb28fe8e fix(sync): normalize Kimi model families 2026-06-12 13:50:14 -05:00
Aiden Cline fcd71901fc Merge pull request #2267 from anomalyco/automation/sync-models-cloudflare-workers-ai
chore(sync): update Cloudflare Workers AI model catalog
2026-06-12 13:40:14 -05:00
github-actions[bot] 5ffe02911a chore(sync): update Cloudflare Workers AI model catalog 2026-06-12 18:04:11 +00:00
Aiden Cline add04f88a2 Merge pull request #2268 from leszek3737/zenmux/k2.7
Add Kimi K2.7 Code and version free model configuration
2026-06-12 12:32:38 -05:00
wassel alazhar 9fdad9f497 Add temperature = false for Kimi and Flash models (locked by Umans) 2026-06-12 19:28:31 +02:00
Leszek 1545b64010 [zenmux] Add Kimi K2.7 Code (Free) model configuration 2026-06-12 19:26:12 +02:00
Adrian Rogala 0382da663b Merge branch 'anomalyco:dev' into zenmux/k2.7 2026-06-12 19:22:21 +02:00
Leszek 0a933025aa [zenmux] Add kimi-k2.7-code model configuration 2026-06-12 19:20:59 +02:00
wassel alazhar 735e5f7f08 Remove umans-flash-beta from Coding Plan (deprecated, sunset 2026-06-07) 2026-06-12 19:16:05 +02:00
wassel alazhar a414765865 Update Umans AI Coding Plan and add Umans AI (pay-per-token) provider
Umans AI Coding Plan (subscription):
- Add umans-kimi-k2.7 (Kimi K2.7 Code) model
- Add umans-flash-beta (deprecated alias for umans-flash)
- Fix umans-glm-5.1: add vision modality (via handoff) and interleaved reasoning
- Fix umans-flash: add interleaved reasoning field
- Fix umans-qwen3.6-35b-a3b: add interleaved reasoning field
- Add reasoning_options to all models
- Add explicit name field to models using base_model

Umans AI (new provider - pay-per-token for orgs):
- New provider for organization service-account usage
- Per-token pricing from the org billing page:
  - Kimi K2.6: /bin/bash.95/.00 (input/output), /bin/bash.20 cache read
  - Kimi K2.7 Code: /bin/bash.95/.00, /bin/bash.19 cache read
  - GLM 5.1: .40/.40, /bin/bash.29 cache read
  - Umans Flash (Qwen3.6-35B-A3B): /bin/bash.15/.00, /bin/bash.05 cache read
  - Umans Coder: routes to Kimi K2.6 rates
- Same endpoint (api.code.umans.ai), different billing model
2026-06-12 19:08:15 +02:00
Aiden Cline 32f2c6de2a Merge pull request #2263 from anomalyco/feat/kimi-k2.7-code
feat(models): add Kimi K2.7 Code
2026-06-12 11:36:40 -05:00
Aiden Cline bd6fc4b145 feat(models): add Kimi K2.7 Code 2026-06-12 11:35:17 -05:00
Aiden Cline a0957ebea8 Merge pull request #2237 from anomalyco/feat/crof-reasoning-options-wave4
[crof] Add reasoning options
2026-06-12 11:17:12 -05:00
Aiden Cline 8b50fa5029 [crof] Add DeepSeek V4 reasoning efforts 2026-06-12 11:01:44 -05:00
Aiden Cline d6f87b6e64 Merge pull request #2233 from anomalyco/feat/gitlab-reasoning-options-wave4
[gitlab] Add reasoning options
2026-06-12 10:51:47 -05:00
Aiden Cline a66ef9ca19 Merge pull request #2209 from anomalyco/feat/meganova-reasoning-options-wave3
[meganova] Add reasoning options
2026-06-12 10:30:41 -05:00
Aiden Cline a48f0722e8 Merge pull request #2240 from anomalyco/feat/fastrouter-reasoning-options-wave4
[fastrouter] Add reasoning options
2026-06-12 10:28:15 -05:00
Aiden Cline aed6a48d73 Merge pull request #2241 from anomalyco/feat/neon-reasoning-options-wave4
[neon] Add reasoning options
2026-06-12 10:27:49 -05:00
Aiden Cline 1b24a035da Merge pull request #2245 from anomalyco/feat/helicone-reasoning-options-wave4
[helicone] Add reasoning options
2026-06-12 10:27:20 -05:00
Aiden Cline 560dceadf3 Merge pull request #2261 from anomalyco/feat/alibaba-token-plan-reasoning-options-final
[alibaba-token-plan] Add reasoning options
2026-06-12 10:26:40 -05:00
Aiden Cline f3607ba954 Merge pull request #2262 from anomalyco/feat/lmstudio-reasoning-options-final
[lmstudio] Add GPT-OSS reasoning options
2026-06-12 10:26:18 -05:00
Aiden Cline 6b90987895 Merge pull request #2248 from anomalyco/automation/sync-models-xai
chore(sync): update xAI model catalog
2026-06-12 10:26:05 -05:00
github-actions[bot] ec6b7af421 chore(sync): update xAI model catalog 2026-06-12 15:25:05 +00:00
Aiden Cline 25c2cf9224 [lmstudio] Add GPT-OSS reasoning options 2026-06-12 10:22:51 -05:00
Aiden Cline a4cdec5316 [alibaba-token-plan] Add reasoning options 2026-06-12 10:21:30 -05:00
Aiden Cline 90f36e0550 [freemodel] Add reasoning options 2026-06-12 10:21:27 -05:00
Aiden Cline f15aad08ef feat(alibaba-token-plan-cn): add reasoning options 2026-06-12 10:21:26 -05:00
Aiden Cline 063429a4ae [digitalocean] Cover remaining reasoning options 2026-06-12 10:20:56 -05:00
Aiden Cline b21c08dc44 [alibaba-coding-plan-cn] Add reasoning options 2026-06-12 10:20:42 -05:00
Aiden Cline 592da7f45c [google] Complete reasoning options 2026-06-12 10:20:36 -05:00
Aiden Cline 717892fd72 [evroc] Add reasoning options 2026-06-12 10:20:26 -05:00
Aiden Cline deef87451d [alibaba-coding-plan] Add reasoning options 2026-06-12 10:20:23 -05:00
Aiden Cline cd3c1f22f7 Merge remote-tracking branch 'origin/dev' into feat/digitalocean-reasoning-options-wave4 2026-06-12 10:19:56 -05:00
Aiden Cline 3f9980168e Merge pull request #2251 from houtanb/dev
Fix release dates
2026-06-12 09:51:58 -05:00
Jack 6f900fa761 Merge pull request #2180 from anomalyco/fix/opencode-go-minimax-m3-pricing
fix(opencode-go): update MiniMax M3 pricing
2026-06-12 21:09:49 +08:00
Houtan Bastani 61a153e6bb Update Mistral Large 2411 release date
Set mistral-large-2411 release_date and last_updated  metadata to 2024-11-18.

Evidence:

https://github.com/mistralai/platform-docs-public/blob/main/src/schema/models/models/mistral-large-2-1-24-11.ts#L9
2026-06-12 11:35:43 +02:00
Houtan Bastani 5a8f9d44d5 Update Gemini 2.5 Flash and Gemini 2.5 Pro release dates
Set Gemini 2.5 Flash and Gemini 2.5 Pro release_date and last_updated metadata to 2025-06-17.

Evidence:

https://ai.google.dev/gemini-api/docs/deprecations#gemini-2.5-flash-models

https://ai.google.dev/gemini-api/docs/deprecations#gemini-2.5-pro-models
2026-06-12 11:35:33 +02:00
Aiden Cline 629ce9b9f7 Merge pull request #2243 from anomalyco/feat/opencode-go-reasoning-options-wave4
[opencode-go] Add reasoning options
2026-06-12 00:07:39 -05:00
Aiden Cline 074022b5ad [huggingface] Correct fixed reasoning controls 2026-06-11 23:58:31 -05:00
Aiden Cline c562522e4f [opencode-go] Normalize DeepSeek V4 efforts 2026-06-11 23:57:47 -05:00
Aiden Cline dd051fd682 [helicone] Add reasoning options 2026-06-11 23:56:41 -05:00
Aiden Cline 074a288d15 [huggingface] Add reasoning options 2026-06-11 23:56:40 -05:00
Aiden Cline 2d0173d177 [opencode-go] Add reasoning options 2026-06-11 23:56:33 -05:00
Aiden Cline df75f7c438 [neon] Add reasoning options 2026-06-11 23:56:10 -05:00
Aiden Cline ffe754d81c [fastrouter] Add reasoning options 2026-06-11 23:56:04 -05:00
Aiden Cline c67d3e84ff [digitalocean] Add reasoning options 2026-06-11 23:55:32 -05:00
Aiden Cline 2f5d53cdf3 [crof] Add reasoning options 2026-06-11 23:54:59 -05:00
Aiden Cline 08b5fd9061 [gitlab] Add reasoning options 2026-06-11 23:54:10 -05:00
Aiden Cline 5aeaaa8d47 [anyapi] Add reasoning options 2026-06-11 23:52:40 -05:00
Aiden Cline 12280f413b [chutes] Add reasoning options 2026-06-11 23:52:31 -05:00
Aiden Cline 1a772fd297 Merge pull request #2223 from anomalyco/feat/google-vertex-reasoning-options-wave3
[google-vertex] Add MaaS reasoning options
2026-06-11 23:52:15 -05:00
Aiden Cline 38c708714f [cloudflare-ai-gateway] Add reasoning options 2026-06-11 23:52:04 -05:00
Aiden Cline 13abc41ac9 [abacus] Add reasoning options 2026-06-11 23:51:42 -05:00
Aiden Cline cf6a5e104d [auriko] Add reasoning options 2026-06-11 23:51:41 -05:00
Aiden Cline 128e0fbd8a [ambient] Add reasoning options 2026-06-11 23:50:16 -05:00
Aiden Cline c63920050a [google-vertex] Add MaaS reasoning options 2026-06-11 23:50:13 -05:00
Aiden Cline 24d2a74f4d [xiaomi-token-plan] Add reasoning toggles 2026-06-11 23:50:05 -05:00
Aiden Cline e62b47a005 [azure] Backfill DeepSeek V4 reasoning options 2026-06-11 23:49:52 -05:00
Aiden Cline eac6d1aaed [mistral] Mark Magistral reasoning controls fixed 2026-06-11 23:49:47 -05:00
Aiden Cline a914876008 [gmicloud] Add reasoning options 2026-06-11 23:49:46 -05:00
Aiden Cline 794203e12c [lilac] Add reasoning options 2026-06-11 23:49:45 -05:00
Aiden Cline 2624678dbe [dinference] Mark reasoning controls fixed 2026-06-11 23:49:42 -05:00
Aiden Cline 2d18ebb301 [inceptron] Mark reasoning controls fixed 2026-06-11 23:49:40 -05:00
Aiden Cline df45483742 Merge pull request #2211 from anomalyco/feat/wafer.ai-reasoning-options-wave3
[wafer.ai] Add reasoning options
2026-06-11 23:49:22 -05:00
Aiden Cline 4ecdcb8f2b Merge pull request #2196 from anomalyco/feat/hpc-ai-reasoning-options-wave3
[hpc-ai] Add reasoning options
2026-06-11 23:48:29 -05:00
Aiden Cline 4644def1ae [hpc-ai] Remove unsupported reasoning efforts 2026-06-11 23:45:03 -05:00
Aiden Cline f9091af5ee Merge pull request #2198 from anomalyco/feat/mixlayer-reasoning-options-wave3
[mixlayer] Add reasoning options
2026-06-11 23:41:20 -05:00
Aiden Cline 7022a48bfc Merge pull request #2205 from anomalyco/feat/vultr-reasoning-options-wave3
[vultr] Add reasoning options
2026-06-11 23:40:45 -05:00
Aiden Cline dda69225d8 Merge pull request #2190 from anomalyco/feat/perplexity-reasoning-options-wave3
[perplexity] Add reasoning options
2026-06-11 23:38:49 -05:00
Aiden Cline 2e020b1dd2 Merge pull request #2194 from anomalyco/feat/minimax-coding-plan-reasoning-options-wave3
[minimax-coding-plan] Complete reasoning options
2026-06-11 23:38:32 -05:00
Aiden Cline 67252bda30 Merge pull request #2197 from anomalyco/feat/submodel-reasoning-options-wave3
[submodel] Add reasoning options
2026-06-11 23:38:20 -05:00
Aiden Cline ac1566f622 Merge pull request #2193 from anomalyco/feat/minimax-reasoning-options-wave3
[minimax] Complete reasoning options
2026-06-11 23:38:02 -05:00
Aiden Cline 48837609aa Merge pull request #2199 from anomalyco/feat/v0-reasoning-options-wave3
[v0] Add reasoning options
2026-06-11 23:37:49 -05:00
Aiden Cline c2a0ff023a Merge pull request #2138 from martinmose/add-zeldoc-provider
feat(provider): add zeldoc provider
2026-06-11 23:28:07 -05:00
Aiden Cline 282821e7b6 Merge pull request #2208 from anomalyco/feat/qihang-ai-reasoning-options-wave3
[qihang-ai] Add reasoning options
2026-06-11 23:25:07 -05:00
Aiden Cline 1b8e53bcbd Merge pull request #2192 from anomalyco/feat/minimax-cn-reasoning-options-wave3
[minimax-cn] Complete reasoning options
2026-06-11 23:14:09 -05:00
Aiden Cline f671147f71 Merge pull request #2207 from anomalyco/feat/scaleway-reasoning-options-wave3
[scaleway] Add reasoning options
2026-06-11 23:13:54 -05:00
Aiden Cline e23e759601 Merge pull request #2204 from anomalyco/feat/clarifai-reasoning-options-wave3
[clarifai] Add reasoning options
2026-06-11 23:13:40 -05:00
Aiden Cline 4b4546f3e3 Merge pull request #2213 from anomalyco/feat/friendli-reasoning-options-wave3
[friendli] Add reasoning options
2026-06-11 23:13:24 -05:00
Aiden Cline 040f0ca995 [wafer.ai] Add DeepSeek V4 effort controls 2026-06-11 23:12:29 -05:00
Aiden Cline 9acac34889 [friendli] Remove unsupported reasoning efforts 2026-06-11 23:11:37 -05:00
Aiden Cline 78ad91f773 Merge pull request #2212 from anomalyco/feat/iflowcn-reasoning-options-wave3
[iflowcn] Add reasoning options
2026-06-11 23:10:34 -05:00
Aiden Cline 4b0aeef538 Merge pull request #2214 from anomalyco/feat/io-net-reasoning-options-wave3
[io-net] Add reasoning options
2026-06-11 23:09:58 -05:00
Aiden Cline 856787cb84 [friendli] Add reasoning options 2026-06-11 23:08:36 -05:00
Aiden Cline 084f0bb4ba [iflowcn] Add reasoning options 2026-06-11 23:08:36 -05:00
Aiden Cline ee1301fb63 [io-net] Add reasoning options 2026-06-11 23:08:36 -05:00
Aiden Cline 502957b778 [wafer.ai] Add reasoning options 2026-06-11 23:08:29 -05:00
Aiden Cline 3fba77ee56 [the-grid-ai] Add reasoning options 2026-06-11 23:07:50 -05:00
Aiden Cline 0a6286e468 [regolo-ai] Add reasoning options 2026-06-11 23:07:50 -05:00
Aiden Cline 8af96ce933 [berget] Add reasoning options 2026-06-11 23:07:50 -05:00
Aiden Cline 4a056bd1ef [meganova] Add reasoning options 2026-06-11 23:07:50 -05:00
Aiden Cline 9f11a93d06 [vultr] Add reasoning options 2026-06-11 23:07:50 -05:00
Aiden Cline be8d8a2ec2 [qihang-ai] Add reasoning options 2026-06-11 23:07:50 -05:00
Aiden Cline d4193dbad6 [scaleway] Add reasoning options 2026-06-11 23:07:50 -05:00
Aiden Cline fb6b0985ce [clarifai] Add reasoning options 2026-06-11 23:07:50 -05:00
Aiden Cline 506ca0f7c3 [neuralwatt] Add reasoning options 2026-06-11 23:07:49 -05:00
Aiden Cline 4cafdb31ff [tencent-coding-plan] Add reasoning options 2026-06-11 23:07:20 -05:00
Aiden Cline d97aedf7a1 [modelscope] Add reasoning options 2026-06-11 23:07:20 -05:00
Aiden Cline 404bba4d1f [minimax-cn-coding-plan] Add reasoning options 2026-06-11 23:07:20 -05:00
Aiden Cline 2bb4fe287e [hpc-ai] Add reasoning options 2026-06-11 23:07:20 -05:00
Aiden Cline b58c396106 [mixlayer] Add reasoning options 2026-06-11 23:07:20 -05:00
Aiden Cline 575f078887 [minimax-coding-plan] Add reasoning options 2026-06-11 23:07:20 -05:00
Aiden Cline acf194ec01 [submodel] Add reasoning options 2026-06-11 23:07:20 -05:00
Aiden Cline c80ff1ad2c [minimax] Add reasoning options 2026-06-11 23:07:20 -05:00
Aiden Cline a41f6f5913 [v0] Add reasoning options 2026-06-11 23:07:20 -05:00
Aiden Cline 8dffe03a9c [minimax-cn] Add reasoning options 2026-06-11 23:07:20 -05:00
Aiden Cline 9ea761af1a [perplexity] Add reasoning options 2026-06-11 23:07:07 -05:00
Aiden Cline c10ba76860 [upstage] Add reasoning options 2026-06-11 23:06:33 -05:00
Aiden Cline 30a019056f [moonshotai] Add reasoning options 2026-06-11 23:06:33 -05:00
Aiden Cline d7c4b11163 [nova] Add reasoning options 2026-06-11 23:06:33 -05:00
Aiden Cline 1018ddf139 [cloudferro-sherlock] Add reasoning options 2026-06-11 23:06:33 -05:00
Aiden Cline a5e572bcf6 [drun] Add reasoning options 2026-06-11 23:06:33 -05:00
Aiden Cline 2d52062693 [moark] Add reasoning options 2026-06-11 23:06:33 -05:00
Aiden Cline 6f3b739418 [poolside] Add reasoning options 2026-06-11 23:06:33 -05:00
Aiden Cline f52cc7e895 [lucidquery] Add reasoning options 2026-06-11 23:06:33 -05:00
Aiden Cline 473d12c44b [inception] Add reasoning options 2026-06-11 23:06:33 -05:00
Jack 9401952857 chore(opencode-go): preserve MiniMax M3 file ending 2026-06-12 12:01:40 +08:00
Jack 623f5e8ea4 fix(opencode-go): update MiniMax M3 pricing 2026-06-12 11:59:03 +08:00
Aiden Cline 526b4cd543 Merge pull request #2179 from anomalyco/feat/deepseek-reasoning-options-wave2
[deepseek] Complete reasoning options
2026-06-11 22:55:29 -05:00
Aiden Cline b7d165296c Merge pull request #2172 from anomalyco/feat/privatemode-ai-reasoning-options
[privatemode-ai] Add reasoning options
2026-06-11 22:55:21 -05:00
Aiden Cline 655f757925 Merge pull request #2177 from anomalyco/feat/llmtr-reasoning-options
[llmtr] Complete reasoning options
2026-06-11 22:55:07 -05:00
Aiden Cline cce129dfd9 Merge pull request #2173 from anomalyco/feat/zai-coding-plan-reasoning-options
[zai-coding-plan] Complete reasoning options
2026-06-11 22:54:57 -05:00
Aiden Cline 548f3b5869 Merge pull request #2175 from anomalyco/feat/zhipuai-coding-plan-reasoning-options
[zhipuai-coding-plan] Complete reasoning options
2026-06-11 22:54:51 -05:00
Aiden Cline f349a9dde6 Merge pull request #2176 from anomalyco/feat/kuae-cloud-reasoning-options
[kuae-cloud-coding-plan] Add reasoning options
2026-06-11 22:54:34 -05:00
Aiden Cline 05c1041160 [deepseek] Mark reasoner controls fixed 2026-06-11 22:54:19 -05:00
Aiden Cline 215c3dfbc8 Merge pull request #2174 from anomalyco/feat/kimi-for-coding-reasoning-options
[kimi-for-coding] Complete reasoning options
2026-06-11 22:54:16 -05:00
Aiden Cline ddc6ad75a2 Merge pull request #2178 from anomalyco/feat/firepass-reasoning-options
[firepass] Add reasoning options
2026-06-11 22:54:05 -05:00
Aiden Cline 757bee7de8 Merge pull request #2167 from anomalyco/feat/claudinio-reasoning-options
[claudinio] Add reasoning options
2026-06-11 22:53:39 -05:00
Aiden Cline 5ee32a47ae Merge pull request #2170 from anomalyco/feat/bailing-reasoning-options
[bailing] Add reasoning options
2026-06-11 22:53:30 -05:00
Aiden Cline 2c22f4b488 [privatemode-ai] Add reasoning options 2026-06-11 22:51:42 -05:00
Aiden Cline 097296f6c6 [llmtr] Add reasoning options 2026-06-11 22:51:42 -05:00
Aiden Cline 2559ed64c5 [zai-coding-plan] Add reasoning options 2026-06-11 22:51:42 -05:00
Aiden Cline c56ac404d3 [zhipuai-coding-plan] Add reasoning options 2026-06-11 22:51:42 -05:00
Aiden Cline 4681e30afb [kuae-cloud-coding-plan] Add reasoning options 2026-06-11 22:51:42 -05:00
Aiden Cline 94cd023a88 [kimi-for-coding] Add reasoning options 2026-06-11 22:51:42 -05:00
Aiden Cline b5c33b6347 [deepseek] Add reasoning options 2026-06-11 22:51:41 -05:00
Aiden Cline 2014d883e4 [firepass] Add reasoning options 2026-06-11 22:51:41 -05:00
Aiden Cline 2f749b7cf9 [claudinio] Add reasoning options 2026-06-11 22:51:31 -05:00
Aiden Cline d7ab976e3c [bailing] Add reasoning options 2026-06-11 22:51:31 -05:00
Aiden Cline 32066b7856 Merge pull request #2131 from anomalyco/feat/ovhcloud-reasoning-audit
feat(ovhcloud): add reasoning options
2026-06-11 22:42:30 -05:00
Aiden Cline 3ded2fae72 Merge pull request #2130 from anomalyco/audit/nebius-models
[nebius] Audit reasoning controls
2026-06-11 22:38:33 -05:00
Aiden Cline 9771180f83 [nebius] Correct reasoning controls 2026-06-11 22:31:54 -05:00
Aiden Cline fa65113f37 Merge pull request #2162 from mikeyp/chore/update-digitalocean-models
Add anthropic-claude-fable-5 and nemotron-3-ultra-550b to DigitalOcean
2026-06-11 22:19:22 -05:00
Aiden Cline 1ab5784118 Merge pull request #2161 from andrelandgraf/feat/add-neon-provider
Add Neon provider
2026-06-11 22:17:07 -05:00
Mike Prasuhn 411bc157e6 Add anthropic-claude-fable-5 and nemotron-3-ultra-550b to DigitalOcean 2026-06-11 23:09:08 -04:00
Andre Landgraf 58ab76b8f3 Add Neon provider
Neon serves the same Databricks-backed model catalog through its
branch-scoped AI Gateway via an OpenAI-compatible endpoint, so this mirrors
the `databricks` provider's models.

- `api` uses the branch-scoped `NEON_AI_GATEWAY_BASE_URL` + the unified MLflow
  OpenAI-compatible route; `NEON_AI_GATEWAY_TOKEN` is the bearer key. Both are
  emitted by `neonctl env pull`.
- Model ids drop the `databricks-` prefix (the gateway accepts the bare ids),
  so models resolve as `neon/claude-haiku-4-5`, `neon/gpt-5-nano`, etc.
2026-06-11 19:52:37 -07:00
Martin Mose Facondini 8f2607fcdb fix(zeldoc): make logo black 2026-06-12 00:12:49 +02:00
Martin Mose Facondini 23e07a27d2 fix(zeldoc): correct z-code model fields 2026-06-12 00:12:44 +02:00
Aiden Cline 37e8e0cf95 Merge pull request #2086 from anomalyco/feat/openrouter-reasoning-options
feat(openrouter): add reasoning options
2026-06-11 16:21:15 -05:00
Aiden Cline 0e0fe311ab Merge dev into feat/openrouter-reasoning-options 2026-06-11 16:14:33 -05:00
Aiden Cline 3d763d081e fix(openrouter): document Claude effort mapping 2026-06-11 16:14:03 -05:00
Aiden Cline ebbd3416e2 Merge pull request #2154 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-06-11 16:07:40 -05:00
Aiden Cline a3509f9a3d Merge pull request #2155 from anomalyco/automation/sync-models-vercel
chore(sync): update Vercel AI Gateway model catalog
2026-06-11 16:07:24 -05:00
github-actions[bot] 71d00e7dfc chore(sync): update Vercel AI Gateway model catalog 2026-06-11 21:06:24 +00:00
github-actions[bot] 26f7b6f6b6 chore(sync): update OpenRouter model catalog 2026-06-11 21:06:21 +00:00
Aiden Cline 270009bd93 fix(openrouter): correct reasoning controls 2026-06-11 15:03:25 -05:00
Aiden Cline 91cc389af3 fix(openrouter): correct Claude reasoning controls 2026-06-11 14:57:34 -05:00
Aiden Cline 1c7b7e8247 Merge dev into feat/openrouter-reasoning-options 2026-06-11 14:27:05 -05:00
Aiden Cline a382026ce9 Merge pull request #2153 from anomalyco/automation/sync-models-vercel
chore(sync): update Vercel AI Gateway model catalog
2026-06-11 14:21:25 -05:00
github-actions[bot] 1fc7261c14 chore(sync): update Vercel AI Gateway model catalog 2026-06-11 19:15:03 +00:00
Aiden Cline 765dae9f61 Merge pull request #2134 from anomalyco/audit/deepinfra-reasoning
fix(deepinfra): reconcile reasoning controls
2026-06-11 13:02:22 -05:00
Aiden Cline 02cd80a2ab Merge pull request #2032 from anthraxx/alibaba-qwen3.7-plus
add Qwen3.7 Plus model configuration to Alibana coding plan
2026-06-11 12:57:58 -05:00
Aiden Cline fcbd02fa84 Merge pull request #2148 from anomalyco/automation/sync-models-venice
chore(sync): update Venice model catalog
2026-06-11 12:56:57 -05:00
Aiden Cline e07a0bab97 Merge pull request #2132 from anomalyco/chore/fireworks-reasoning
fix(fireworks-ai): reconcile reasoning controls
2026-06-11 12:55:12 -05:00
Aiden Cline ad166f7448 fix(fireworks-ai): verify reasoning toggles 2026-06-11 12:33:12 -05:00
github-actions[bot] 660350c5fa chore(sync): update Venice model catalog 2026-06-11 17:29:06 +00:00
Aiden Cline 54d94bdc79 fix(deepinfra): restore Kimi K2.5 toggle 2026-06-11 12:28:40 -05:00
Aiden Cline 912ee1fe86 fix(deepinfra): restore V4 effort enum 2026-06-11 12:23:47 -05:00
Aiden Cline 9379be8911 Merge pull request #2151 from anomalyco/fix/togetherai-required-reasoning-options
[togetherai] Require reasoning options metadata
2026-06-11 12:21:18 -05:00
Aiden Cline 1ccb247f7f [togetherai] Require reasoning options metadata 2026-06-11 12:05:22 -05:00
Aiden Cline 7d5469898d [nebius] Complete reasoning option coverage 2026-06-11 12:04:48 -05:00
Aiden Cline ec3c4ed8ea fix(fireworks-ai): mark unresolved reasoning controls 2026-06-11 12:04:47 -05:00
Aiden Cline 2b42408582 fix(deepinfra): mark unresolved reasoning controls 2026-06-11 12:04:46 -05:00
Aiden Cline 8521822a96 Merge pull request #2135 from anomalyco/audit/togetherai-reasoning-20260610
Audit Together AI models and reasoning controls
2026-06-11 12:01:15 -05:00
Aiden Cline 6b62d03ac0 chore(deepinfra): remove provider test 2026-06-11 12:00:46 -05:00
Aiden Cline 9df50e0ccc chore(ovhcloud): remove test changes 2026-06-11 12:00:37 -05:00
Aiden Cline 9b3d25aae8 [nebius] Remove provider matrix test 2026-06-11 12:00:36 -05:00
Aiden Cline ea4d10b219 chore(fireworks-ai): remove catalog test 2026-06-11 12:00:36 -05:00
Aiden Cline d3d163dd95 Remove Together provider matrix test 2026-06-11 12:00:35 -05:00
Aiden Cline 78f8fb92fc Merge pull request #2129 from anomalyco/audit/cerebras-models-20260610
[cerebras] Refresh public model catalog
2026-06-11 12:00:23 -05:00
Aiden Cline 62b4296b3d Delete packages/core/test/cerebras.test.ts 2026-06-11 12:00:10 -05:00
Aiden Cline 12057804f5 Merge pull request #2143 from Nindaleth/feature/ghcp-fable
feat(github-copilot): add Claude Fable 5 model
2026-06-11 11:48:42 -05:00
Aiden Cline 127290ebec Merge pull request #2142 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-06-11 11:45:55 -05:00
Aiden Cline 5abbfce7d6 Merge pull request #2120 from davidfierro/feat/snowflake-cortex-models
feat(snowflake-cortex): add missing but officially supported models
2026-06-11 11:45:36 -05:00
Aiden Cline 6ff6ab4028 Merge pull request #2145 from Omee11/feat/token-plan-cn
feat(alibaba-token-plan-cn): add Alibaba Token Plan (China) provider
2026-06-11 11:36:16 -05:00
Aiden Cline 0f3e0d7337 Merge pull request #2146 from Omee11/feat/token-plan-qwen3.7-plus
feat(alibaba-token-plan): add qwen3.7-plus
2026-06-11 10:51:52 -05:00
github-actions[bot] 8381089b11 chore(sync): update OpenRouter model catalog 2026-06-11 15:28:27 +00:00
Oliver Mee 98bed4baf6 feat(alibaba-token-plan-cn): add Alibaba Token Plan (China) provider 2026-06-11 18:14:20 +08:00
Oliver Mee e55ab2daf8 feat(alibaba-token-plan): add qwen3.7-plus 2026-06-11 18:14:20 +08:00
Radek Liska c60784fab5 feat(github-copilot): add Claude Fable 5 model 2026-06-11 09:15:02 +02:00
Aiden Cline 21581d8f4c test(sync): cover factored reasoning overrides 2026-06-10 23:20:55 -05:00
Aiden Cline 20bfe37a53 fix(sync): resolve changed canonical base 2026-06-10 23:19:32 -05:00
Aiden Cline fc4a781c2f fix(ovhcloud): complete reasoning controls 2026-06-10 23:16:08 -05:00
Aiden Cline 28674e1af4 [cerebras] Assert complete resolved models 2026-06-10 23:16:01 -05:00
Aiden Cline 1e76995f8e Test resolved Together provider matrix 2026-06-10 23:15:34 -05:00
Aiden Cline 0e371b761d fix(sync): resolve reasoning before preservation 2026-06-10 23:14:13 -05:00
Aiden Cline 7a5bf4f56e [cerebras] Test resolved model matrix 2026-06-10 23:13:39 -05:00
Aiden Cline 4c5b17b1db [nebius] Test generated provider matrix 2026-06-10 23:13:35 -05:00
Aiden Cline c4650219c3 fix(sync): drop stale reasoning options 2026-06-10 23:13:06 -05:00
Aiden Cline 9fb0474d1c feat(ovhcloud): add reasoning options 2026-06-10 23:13:06 -05:00
Aiden Cline 8807bb0069 Correct Together reasoning and pricing metadata 2026-06-10 23:12:12 -05:00
Aiden Cline 56426cc834 fix(deepinfra): preserve cache pricing 2026-06-10 23:11:28 -05:00
Aiden Cline 18c35709c5 Merge pull request #2139 from anomalyco/fix/venice-sync-models
Venice: fix synced model metadata
2026-06-10 20:14:38 -05:00
Aiden Cline b618a32341 fix(deepinfra): verify R1 reasoning controls 2026-06-10 20:13:26 -05:00
Aiden Cline f8229eba2e fix(deepinfra): narrow reasoning controls 2026-06-10 20:07:25 -05:00
Aiden Cline 6799ff1078 [nebius] Correct verified reasoning controls 2026-06-10 20:02:58 -05:00
Aiden Cline 236ff0e39b fix(fireworks-ai): add Qwen reasoning budget 2026-06-10 20:02:44 -05:00
Aiden Cline cb4fd81c59 Correct Together Qwen reasoning metadata 2026-06-10 19:51:01 -05:00
Aiden Cline 79e47be952 fix(deepinfra): use model-specific reasoning controls 2026-06-10 19:50:58 -05:00
Aiden Cline 03c161f038 [cerebras] Correct GLM reasoning option 2026-06-10 19:50:19 -05:00
Aiden Cline 38a2f09999 [nebius] Reconcile model lifecycle evidence 2026-06-10 19:49:42 -05:00
Aiden Cline 1f77766834 fix(fireworks-ai): remove unverified toggles 2026-06-10 19:48:27 -05:00
Aiden Cline da1032a1cb [venice] Fix synced model metadata 2026-06-10 19:46:52 -05:00
Aiden Cline 55848d41c6 Merge pull request #2123 from BlockListed/cortecs-add-claude-opus-4-8
add claude opus 4.8 to cortecs
2026-06-10 19:36:26 -05:00
BlockListed e8304a0b0f add claude opus 4.8 to cortecs 2026-06-10 23:48:02 +02:00
Martin Mose Facondini 23b4754d23 rename agentic-coding model to z-code 2026-06-10 23:06:51 +02:00
Martin Mose Facondini 20ffc3909f add zeldoc provider with agentic-coding model 2026-06-10 23:06:21 +02:00
Aiden Cline 09c7f864f2 Audit Together AI model catalog and reasoning 2026-06-10 16:05:11 -05:00
Aiden Cline c71d0c8065 fix(deepinfra): reconcile reasoning controls 2026-06-10 16:05:01 -05:00
Aiden Cline 5a3e0cacea test(fireworks-ai): lock reasoning controls 2026-06-10 16:04:34 -05:00
Aiden Cline f8ccb57731 [nebius] Audit reasoning controls 2026-06-10 16:04:09 -05:00
Aiden Cline c0b03ed655 [cerebras] Refresh public model catalog 2026-06-10 16:03:52 -05:00
Aiden Cline 63feee7eca Merge pull request #2128 from anomalyco/chore/close-stale-pull-requests
Automate stale pull request cleanup
2026-06-10 15:55:45 -05:00
Aiden Cline 233d636579 Merge pull request #2118 from dpuyosa/feat/venice-base-model
Venice: Update generation script to use base_model and reasoning_options
2026-06-10 15:55:01 -05:00
Aiden Cline 337d50d90f Automate stale pull request cleanup 2026-06-10 15:54:40 -05:00
Aiden Cline dfb3f2a421 Merge pull request #2062 from knowhycodata/add-llmtr-provider
feat: add LLMTR provider
2026-06-10 15:53:35 -05:00
Aiden Cline a87f44dc06 [venice] Remove stale generated metadata 2026-06-10 14:59:51 -05:00
Aiden Cline 19cb771778 [venice] Generate metadata for new models 2026-06-10 14:40:06 -05:00
Aiden Cline 1f1a82c280 [venice] Reconcile synced model overrides 2026-06-10 14:24:32 -05:00
Aiden Cline d9b2cd9076 Merge remote-tracking branch 'refs/remotes/contributor/feat/venice-base-model' into feat/venice-base-model 2026-06-10 14:24:21 -05:00
Aiden Cline 0ce7da24b6 [venice] Factor all models through metadata 2026-06-10 14:23:52 -05:00
Aiden Cline 44dabca8de Merge pull request #2093 from jatingomnet/fastrouter_model_update
feat(sync): sync FastRouter model catalog
2026-06-10 14:22:20 -05:00
Aiden Cline 62c62ec36f Merge pull request #2113 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-06-10 14:21:33 -05:00
Aiden Cline c3dcc2730f Merge pull request #2114 from anomalyco/automation/sync-models-vercel
chore(sync): update Vercel AI Gateway model catalog
2026-06-10 14:21:16 -05:00
Aiden Cline 4d90460f96 Merge pull request #2127 from leszek3737/zenmux/step-free
feat(zenmux): remove of Step 3.5 Flash (Free) model and add Step 3.7 Flash (Free)
2026-06-10 14:16:59 -05:00
github-actions[bot] 87b37096fc chore(sync): update OpenRouter model catalog 2026-06-10 19:10:45 +00:00
github-actions[bot] 1ea8f58f13 chore(sync): update Vercel AI Gateway model catalog 2026-06-10 19:10:44 +00:00
Aiden Cline 9a13c66393 Merge pull request #2126 from vglafirov/feat/gitlab-claude-fable-5
feat(gitlab): add Claude Fable 5 model
2026-06-10 11:57:34 -05:00
Leszek f8a551f850 Remove of Step 3.5 Flash (Free) model and add Step 3.7 Flash (Free) 2026-06-10 18:55:15 +02:00
Vladimir Glafirov 1751dc2671 feat(gitlab): add Claude Fable 5 model 2026-06-10 18:50:26 +02:00
Aiden Cline d333702d19 Merge pull request #2115 from pawelsierant/dev
Add Claude Fable 5 support for Azure
2026-06-10 11:40:16 -05:00
Aiden Cline 8f323c3a78 Merge pull request #2125 from Nichokas/add-freemodel-provider
feat(providers): add Claude Fable 5 to FreeModel
2026-06-10 11:40:03 -05:00
dpuyosa 8d3c8cfe21 Merge branch 'dev' into feat/venice-base-model 2026-06-10 18:39:23 +02:00
Aiden Cline 1f8adf44e7 Merge pull request #2091 from dpuyosa/feat/venice-models
Venice: Add tencent-hy3-preview and update minimax-m27
2026-06-10 11:13:10 -05:00
Aiden Cline 4201586665 [venice] Remove models missing from API 2026-06-10 11:08:15 -05:00
Nichokas 28d6a54256 feat: add Claude Fable 5 to FreeModel 2026-06-10 18:06:54 +02:00
Aiden Cline 33bceb35a5 Merge remote-tracking branch 'origin/dev' into feat/venice-base-model
# Conflicts:
#	providers/venice/models/claude-fable-5.toml
2026-06-10 11:00:48 -05:00
Aiden Cline 25c3d6cd23 [venice] Migrate generator to sync runner 2026-06-10 10:58:12 -05:00
David Fierro Iglesias 5dcd077370 feat(snowflake-cortex): add officially supported models 2026-06-10 16:29:41 +02:00
Aiden Cline 987ca2d2f8 Merge pull request #2117 from dpuyosa/feat/venice-claude-fable-5
Venice: Add claude-fable-5 model
2026-06-10 09:28:58 -05:00
dpuyosa 07d2e3e23f [venice] Update models with the new generation script version
- Use new `base_model` and `reasoning_options`
2026-06-10 13:37:13 +02:00
dpuyosa 5d5a421b35 [venice] Add claude-fable-5 model
- Add new provider model configuration inheriting from anthropic base
- Enable structured_output and define cost/modalities
- New file: providers/venice/models/claude-fable-5.toml
2026-06-10 13:15:23 +02:00
dpuyosa 63f56867b9 [venice] Add tencent-hy3-preview and update minimax-m27
- Inherit base_model metadata for both models
- Add reasoning_options with effort levels
- Remove redundant fields now provided by base
2026-06-10 13:06:17 +02:00
dpuyosa d4bf232f91 [venice] Add base_model + reasoning_options to generator
- Derive open_weights from base model metadata when present
- Remove open_weights from baseModelOverrides and formatBaseModelToml
- Add temperature comparison in detectChanges for provider models
2026-06-10 12:59:38 +02:00
dpuyosa 0b27d6034d [venice] Add base_model + reasoning_options to generator
- Add base_model lookup via models/ metadata directory
- Support new reasoning field (reasoning_options effort), audio pricing, and full TOML formatting
- Preserve existing fields and emit minimal override TOMLs when base_model present
- Update change detection and formatting for base_model mode
2026-06-10 12:42:39 +02:00
Frank 57caaf88a2 update zen models 2026-06-10 03:55:32 -04:00
Pawel Sierant 3b3d7ac3aa Add Claude Fable 5 support for Azure 2026-06-10 08:37:24 +02:00
jatin.go 015679c420 chore(fastrouter): use base_model for grok-build-0.1 and sarvam models
Addresses PR #2093 review feedback to use base_model inheritance where a
canonical models/ entry exists or can be added.

- providers/fastrouter/models/x-ai/grok-build-0.1.toml: switch to
  base_model = "xai/grok-build-0.1" (canonical already existed); drop
  duplicated/conflicting facts.
- models/sarvam/sarvam-30b.toml, models/sarvam/sarvam-105b.toml: add new
  canonical metadata so multiple sarvam-hosting providers can share it.
- providers/fastrouter/models/sarvam/sarvam-30b.toml,
  providers/fastrouter/models/sarvam/sarvam-105b.toml: switch to
  base_model with only [cost] override.

bun validate exits 0.
2026-06-10 11:22:29 +05:30
Aiden Cline de6034494d Merge pull request #2112 from anomalyco/feat/groq-reasoning-options
fix(groq): reconcile model catalog and reasoning options
2026-06-10 00:29:38 -05:00
Aiden Cline feb387982b fix(groq): reconcile active model catalog 2026-06-10 00:14:39 -05:00
Aiden Cline 3beb135e23 feat(groq): add reasoning options 2026-06-10 00:08:17 -05:00
Aiden Cline eb2dc1750e Merge pull request #2111 from anomalyco/feat/nvidia-reasoning-options
feat(nvidia): add reasoning options
2026-06-09 23:44:39 -05:00
Aiden Cline 0fa6f6a983 feat(schema): support unbounded reasoning budgets 2026-06-09 23:20:21 -05:00
Aiden Cline aba6cae853 fix(nvidia): narrow reasoning controls 2026-06-09 23:16:13 -05:00
Aiden Cline 83e2a3437f feat(nvidia): add reasoning options 2026-06-09 20:48:07 -05:00
Aiden Cline f3d8034335 Merge pull request #2109 from anomalyco/fix/cloudflare-sync-reasoning-options
fix(sync): preserve reasoning options
2026-06-09 19:54:25 -05:00
Aiden Cline 42fbb1d9ca Merge pull request #2067 from CodeAnimal/az-deepseek-v4
Azure DeepSeek-V4-Pro and DeepSeek-V4-Flash
2026-06-09 19:53:46 -05:00
Aiden Cline 431df4b758 fix(sync): preserve authored reasoning options 2026-06-09 19:51:11 -05:00
Aiden Cline e9f798225c Merge pull request #2090 from coder-wangbin/fix/qwen3.7-plus-params
fix(alibaba/qwen3.7-plus): correct max output to 64K and tier size to 256K
2026-06-09 19:47:27 -05:00
Aiden Cline c2a85735d3 fix(cloudflare): preserve reasoning options during sync 2026-06-09 19:47:13 -05:00
Aiden Cline 8bc3d0b602 Merge pull request #2095 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-06-09 19:45:58 -05:00
Aiden Cline bcfcaccbd3 Merge pull request #2077 from anomalyco/feat/novita-reasoning-options
feat(novita-ai): add reasoning options
2026-06-09 19:45:42 -05:00
github-actions[bot] e0f2b8a542 chore(sync): update OpenRouter model catalog 2026-06-09 23:45:17 +00:00
Aiden Cline e0c0f0202d fix(novita-ai): omit unusable V4 none effort 2026-06-09 17:32:35 -05:00
Aiden Cline 3bc08e0991 Merge pull request #2100 from kites262/feat/add-mimo-v25-pro-ultraspeed
feat(xiaomi): add mimo-v2.5-pro-ultraspeed
2026-06-09 17:28:51 -05:00
Aiden Cline f63d764e53 Merge pull request #2108 from leszek3737/zenmux/claude-fable-5
Fead(zenmux): Add Claude Fable 5 support for Zenmux
2026-06-09 17:28:24 -05:00
Leszek 8a24eecc9a Add Claude Fable 5 for Zenmux 2026-06-09 23:13:00 +02:00
Frank fb13347f59 update zen model 2026-06-09 15:40:00 -04:00
Aiden Cline d06fc9dfc8 fix(novita-ai): add DeepSeek V4 reasoning efforts 2026-06-09 13:47:34 -05:00
Aiden Cline b1867ba865 Merge pull request #2104 from helloimalastair/cloudflare-aig-fable-5
Add Claude Fable 5 for Cloudflare AI Gateway
2026-06-09 13:46:31 -05:00
Aiden Cline e5a8bf7e59 Merge pull request #2105 from anomalyco/automation/sync-models-vercel
chore(sync): update Vercel AI Gateway model catalog
2026-06-09 13:46:21 -05:00
Aiden Cline a93d3b37f4 Merge pull request #2106 from unexge/push-tkvuvvvrvmlq
Add Claude Fable 5 for Amazon Bedrock
2026-06-09 13:46:06 -05:00
Aiden Cline c08584c555 Merge pull request #2107 from vercel/fix-fable-5-reasoning-options
fix(vercel): declare claude-fable-5 reasoning as effort-only
2026-06-09 13:45:50 -05:00
R-Taneja 62fb2b4437 fix(vercel): declare claude-fable-5 reasoning as effort-only
claude-fable-5 rejects thinking.type=enabled (budget_tokens) and requires
thinking.type=adaptive + output_config.effort. Without reasoning_options,
consumers like OpenCode fall back to the legacy budget_tokens control and
the API errors. Mirror claude-opus-4-8, which is also effort-only.
2026-06-09 11:40:16 -07:00
Burak Varli ab1b725656 Add Claude Fable 5 for Amazon Bedrock
Add us/eu/global cross-region inference profiles and set the knowledge
cutoff on the shared base model.
2026-06-09 18:39:45 +00:00
github-actions[bot] 6c710128ef chore(sync): update Vercel AI Gateway model catalog 2026-06-09 17:56:48 +00:00
helloimalastair ef15783481 add claude fable 5 for cloudflare ai gateway 2026-06-09 10:32:45 -07:00
Rohan Taneja ea3976505e Merge pull request #2103 from vercel/update-vercel-models-claude-fable-5
Add Claude Fable 5 (Vercel AI Gateway)
2026-06-09 10:32:16 -07:00
Aiden Cline b2780222da Merge pull request #2102 from anomalyco/add-anthropic-claude-fable-5
Add Claude Fable 5
2026-06-09 12:30:18 -05:00
R-Taneja 303758f170 chore(vercel): add claude-fable-5 model definition
Generated from the Vercel AI Gateway API (bun run vercel:generate --new-only).
2026-06-09 10:30:10 -07:00
Aiden Cline 259aff58eb Add Claude Fable 5 2026-06-09 12:15:45 -05:00
Frank 22f6dd1b9d update zen models 2026-06-09 12:08:10 -04:00
Aiden Cline 7c6727ffc9 Merge pull request #2094 from tomscohere/cohere-north-mini-code-1.0
[cohere] Add Cohere North-Mini-Code-1.0 and Cohere Command A+
2026-06-09 10:55:42 -05:00
kites262 7a25c3fe9c feat(xiaomi): add mimo-v2.5-pro-ultraspeed 2026-06-09 23:52:25 +08:00
Aiden Cline 57e0020109 Merge pull request #2089 from RISHIKREDDYL/dev
fix(azure-cognitive-services): remove broken symlinks for retired xAI models
2026-06-09 10:48:29 -05:00
Aiden Cline 9b7dbfea77 refactor(cohere): use base models 2026-06-09 09:53:44 -05:00
Aiden Cline 8648cb4778 Merge pull request #2084 from anomalyco/feat/cloudflare-workers-ai-reasoning-options
feat(cloudflare-workers-ai): add reasoning options
2026-06-09 09:52:13 -05:00
tomscohere ca1d731028 Update name 2026-06-09 14:21:49 +00:00
tomscohere f0928f55be Update North mini code to Cohere provider 2026-06-09 14:10:39 +00:00
tomscohere 8fbda849d7 Fix A+ last_updated 2026-06-09 11:55:42 +00:00
tomscohere 938ef111c4 Restore package lock 2026-06-09 11:50:56 +00:00
tomscohere 7b65a7c6de Add North-Mini-Code and Cohere CMDA+ 2026-06-09 11:50:07 +00:00
jatin.go eaffc05654 chore(fastrouter): drop unrequested models from prior sync
Removes ~117 model TOMLs introduced by the merged-in big sync commit and
keeps only the 32 explicitly-requested new models. Also reverts the two
pricing changes (deepseek-r1-distill-llama-70b, z-ai/glm-5) and restores
the two previously-deleted files (moonshotai/kimi-k2.toml, z-ai/glm-4.5)
to their original pre-sync state.

bun validate exits 0.
2026-06-09 16:28:15 +05:30
jatin.go c8adf1e849 Merge branch 'fastrouter_model_update' of https://github.com/jatingomnet/models.dev into fastrouter_model_update 2026-06-09 16:25:01 +05:30
jatin.go 8a8912c39d feat(sync): add new FastRouter models
Adds 32 new model TOMLs matching the latest fastrouter.ai/models listing.

- Anthropic: claude-opus-4.8, claude-sonnet-4.6
- xAI: grok-4.3, grok-build-0.1
- OpenAI: gpt-5.5, gpt-5.5-pro, gpt-5.4-mini, gpt-5.4-nano,
  gpt-5.3-codex, gpt-image-2, gpt-realtime-1.5
- Google: gemini-3.5-flash, gemini-3.1-pro-preview, gemma-4-31b-it,
  gemini-3.1-flash-image-preview, gemini-3-pro-image-preview,
  imagen-4.0-fast, imagen-4.0-ultra, veo3.1, veo3.1-fast, veo3.1-lite
- DeepSeek: deepseek-v4-pro
- MoonshotAI: kimi-k2.6
- Z.AI: glm-5.1
- MiniMax: minimax-m2.7, minimax-m2.7-highspeed
- Sarvam: sarvam-105b, sarvam-30b
- ByteDance: seedance-2
- Alibaba: wanx/wan-v2-6
- Leonardo.AI: lucid-origin, lucid-realism

Uses base_model inheritance where canonical models/ entries exist;
self-contained TOMLs otherwise. bun validate exits 0.
2026-06-09 16:20:29 +05:30
jatin.go c6641ba93d feat(sync): sync FastRouter model catalog
Adds ~117 new model TOMLs, removes 1 stale entry, and updates 2 pricing
files to match the current fastrouter.ai/models listing.

- Remove moonshotai/kimi-k2 (replaced by kimi-k2.5 and kimi-k2.6)
- Fix z-ai/glm-4.5 (missing .toml extension); convert to base_model ref
- Update pricing: deepseek-r1-distill-llama-70b, z-ai/glm-5
- Add Anthropic claude-opus-4.5 through claude-3-5-haiku-20241022
- Add OpenAI gpt-5.x/4.x/3.5, o-series, realtime, image, sora, embeddings
- Add Google gemini-3.x/gemma-4, imagen-4, veo2/veo3/veo3.1 families
- Add xAI grok-4.x/3.x/2, DeepSeek v3.x/v4-pro/R1 variants
- Add Qwen, MoonshotAI, MiniMax, Perplexity, Meta, Mistral, Z.AI, Sarvam
- Add FLUX, ByteDance seedream/seedance, Leonardo AI, Kling, Runway,
  Pika, Pollo, Vidu, Wanx video/image models and ace-step audio

Uses base_model inheritance where canonical models/ entries exist;
self-contained TOMLs otherwise. bun validate exits 0.
2026-06-09 15:40:27 +05:30
dpuyosa fc7493b27b [venice] Add tencent-hy3-preview and update minimax-m27
- Add new tencent-hy3-preview model with cost/limit/modality config
- Update minimax-m27 last_updated and cache_read pricing
2026-06-09 11:56:16 +02:00
wangbin d4d0b483b5 fix(alibaba/qwen3.7-plus): correct output to 64K and tier size to 256K
- output: 16,384 → 65,536 (official max output is 64K)
- tier.size: 128,000 → 256,000 (matches qwen3.6-plus tier threshold)

Verified against official spec:
https://bailian.console.aliyun.com/cn-beijing/?tab=model#/model-market/detail/qwen3.7-plus
Context: 1M | Max Output: 64K | Modalities: text + image + video
2026-06-09 16:57:14 +08:00
CodeAnimal f83b8ea4a1 Introduce base_model and other corrections based on feedback 2026-06-09 09:53:54 +01:00
Ubuntu b66908a347 fix(azure-cognitive-services): remove broken symlinks for retired xAI models 2026-06-09 11:54:19 +05:30
Aiden Cline 37b1d0ac95 fix(cloudflare-workers-ai): preserve schema compatibility 2026-06-08 23:19:03 -05:00
Aiden Cline f674b240c3 Merge pull request #2087 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-06-08 23:03:09 -05:00
Aiden Cline b233bbdb81 Merge pull request #2075 from anomalyco/feat/azure-reasoning-options
feat(azure): add reasoning options
2026-06-08 23:02:50 -05:00
Aiden Cline 2817f22c8a fix(azure): expose Kimi reasoning toggles 2026-06-08 23:02:12 -05:00
Aiden Cline ec05c9d5f1 Merge pull request #2088 from anomalyco/feat/baseten-model-sync
feat(sync): add Baseten model sync
2026-06-08 22:53:56 -05:00
Aiden Cline f96381a34d feat(sync): add Baseten model sync 2026-06-08 22:51:22 -05:00
Aiden Cline aeecf3b66f fix(novita-ai): add GPT OSS reasoning efforts 2026-06-08 22:41:16 -05:00
Aiden Cline a963e6ae00 Merge pull request #2078 from anomalyco/feat/baseten-reasoning-options
feat(baseten): add reasoning options
2026-06-08 22:28:13 -05:00
github-actions[bot] 075fd9263e chore(sync): update OpenRouter model catalog 2026-06-09 03:25:49 +00:00
Aiden Cline f4bea4e831 Merge pull request #2081 from anomalyco/feat/vertex-reasoning-options
feat(google-vertex): add reasoning options
2026-06-08 22:13:28 -05:00
Aiden Cline dcae17ea26 fix(google-vertex): retain latest Gemini aliases 2026-06-08 22:12:00 -05:00
Aiden Cline ffedd884f7 fix(google-vertex): remove retired models 2026-06-08 22:06:17 -05:00
Aiden Cline e885955e2f Merge pull request #2079 from anomalyco/feat/ollama-cloud-reasoning-options
feat(ollama-cloud): add reasoning options
2026-06-08 21:57:41 -05:00
Aiden Cline bddf7e070c Merge pull request #2083 from anomalyco/feat/deepinfra-reasoning-options
feat(deepinfra): add reasoning options
2026-06-08 21:56:56 -05:00
Aiden Cline 80c55103dd fix(deepinfra): restore DeepSeek V4 effort controls 2026-06-08 21:13:16 -05:00
Aiden Cline 9a8efd2f2f fix(ollama-cloud): expose MiniMax M3 reasoning controls 2026-06-08 21:00:49 -05:00
Aiden Cline 919ee8da23 fix(ollama-cloud): expose DeepSeek max reasoning 2026-06-08 20:49:29 -05:00
Aiden Cline 71f76d7a1b Merge pull request #2080 from anomalyco/feat/fireworks-reasoning-options
feat(fireworks-ai): add reasoning options
2026-06-08 20:46:48 -05:00
Aiden Cline b6e8a23d76 Merge pull request #2085 from anomalyco/feat/xai-reasoning-options
feat(xai): add reasoning options
2026-06-08 20:36:44 -05:00
Aiden Cline f1fb54c7ba test(xai): reflect language model sync fields 2026-06-08 20:34:29 -05:00
Aiden Cline 9d6cfa4c3f fix(xai): preserve reasoning options during sync 2026-06-08 20:30:35 -05:00
Aiden Cline 5e7769cb71 fix(openrouter): expose Claude Opus effort 2026-06-08 20:22:10 -05:00
Aiden Cline add3daacea feat(openrouter): add reasoning options 2026-06-08 20:17:16 -05:00
Aiden Cline 83faa5efe4 feat(xai): add reasoning options 2026-06-08 20:17:02 -05:00
Aiden Cline bf9b74e973 feat(cloudflare-workers-ai): add reasoning options 2026-06-08 20:16:58 -05:00
Aiden Cline 077a047eb0 feat(deepinfra): add reasoning options 2026-06-08 20:16:49 -05:00
Aiden Cline e696b33e0f feat(google-vertex): add reasoning options 2026-06-08 20:16:48 -05:00
Aiden Cline d1f12dd63a feat(fireworks-ai): add reasoning options 2026-06-08 20:16:45 -05:00
Aiden Cline 30406be8f4 feat(ollama-cloud): add reasoning options 2026-06-08 20:16:42 -05:00
Aiden Cline e4768a2d76 feat(baseten): add reasoning options 2026-06-08 20:16:41 -05:00
Aiden Cline c347e8b438 feat(novita-ai): add reasoning options 2026-06-08 20:16:40 -05:00
Aiden Cline 5bb6b2aaf8 Merge pull request #2076 from anomalyco/feat/bedrock-reasoning-options
feat(amazon-bedrock): add reasoning options
2026-06-08 19:36:54 -05:00
Aiden Cline 468e2ad4ca feat(amazon-bedrock): add reasoning options 2026-06-08 19:28:00 -05:00
Aiden Cline 04ba6ca94e feat(azure): add reasoning options 2026-06-08 17:53:46 -05:00
Aiden Cline 0d7d13bb38 Merge pull request #2074 from anomalyco/feat/openai-reasoning-options
feat(openai): add reasoning options
2026-06-08 17:28:22 -05:00
Aiden Cline 6cc99b6a97 feat(openai): add reasoning options 2026-06-08 17:17:21 -05:00
Aiden Cline fe7927f2dd Merge pull request #2061 from Astro-Han/add-qwen3.7-plus-coding-plan-cn
feat: add qwen3.7-plus to alibaba-coding-plan-cn provider
2026-06-08 16:43:46 -05:00
Aiden Cline cef703a91b Merge pull request #2072 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-06-08 16:43:09 -05:00
Aiden Cline 3cdf2181f5 Merge pull request #2073 from anomalyco/fix/vercel-sync-all-model-types
fix(vercel): sync all gateway model types
2026-06-08 16:42:45 -05:00
Aiden Cline b0e1ed9338 fix(vercel): sync all gateway model types 2026-06-08 16:32:25 -05:00
github-actions[bot] d061339e5d chore(sync): update OpenRouter model catalog 2026-06-08 21:05:13 +00:00
Aiden Cline 26362a4ce3 Merge pull request #2068 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-06-08 15:55:27 -05:00
Aiden Cline 2b0e0b7c95 Merge pull request #2047 from leszek3737/zenmux-7.06
feat(zenmux): add 11 new model definitions
2026-06-08 15:53:19 -05:00
github-actions[bot] 6a1ef22dcd chore(sync): update OpenRouter model catalog 2026-06-08 19:58:10 +00:00
Leszek 9a576170d4 fix(zenmux): correct Claude Opus 4.8 base model ID 2026-06-08 21:40:32 +02:00
CodeAnimal b821602bbd Add DeepSeek-V4-Flash to Azure provider 2026-06-08 17:21:48 +01:00
CodeAnimal 74bf471580 Add DeepSeek-V4-Pro to Azure provider 2026-06-08 17:21:36 +01:00
knowhy e043cc6da1 refactor(llmtr): use base_model for qwen3-6-35b 2026-06-08 18:19:40 +03:00
knowhy 6c523206aa feat(llmtr): add logo 2026-06-08 18:19:39 +03:00
Aiden Cline bccfdc7b87 Merge pull request #2050 from hgraca/nvidia
Add NVIDIA/NVIDIA Nemotron 3 Ultra
2026-06-08 09:55:16 -05:00
Aiden Cline 7217d11f79 fix(nvidia): use base model for nemotron ultra 2026-06-08 09:41:07 -05:00
Aiden Cline ca035f8d4c Merge pull request #2060 from nathannli/dev
fix(cerebras): deprecate llama3.1-8b
2026-06-08 09:21:54 -05:00
Aiden Cline 047af97a74 Merge pull request #2063 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-06-08 09:18:59 -05:00
Aiden Cline 3b05a8e199 Merge pull request #2066 from dpuyosa/feat/venice-nemotron
Venice: Update gemma pricing and add nemotron model
2026-06-08 09:18:46 -05:00
github-actions[bot] 67880dc681 chore(sync): update OpenRouter model catalog 2026-06-08 13:46:24 +00:00
dpuyosa dcf7f6d0a3 [venice] Update gemma pricing and add nemotron model
- Update google-gemma-4-31b-it cost/last_updated
- Add nvidia-nemotron-3-ultra-550b-a55b.toml with pricing/limits
2026-06-08 13:30:36 +02:00
Jack 209ce771e9 update minimax-m3 price in go 2026-06-08 19:11:47 +08:00
knowhy 5ccbf972a5 feat(llmtr): add models/sincap.toml 2026-06-08 08:30:28 +03:00
knowhy c178001cca feat(llmtr): add models/magibu-11b-v8.toml 2026-06-08 08:30:27 +03:00
knowhy 69a833ef58 feat(llmtr): add models/trendyol-7b.toml 2026-06-08 08:30:26 +03:00
knowhy 33c79f65b1 feat(llmtr): add models/medgemma-4b.toml 2026-06-08 08:30:25 +03:00
knowhy c4fba0747f feat(llmtr): add models/qwen3-6-35b.toml 2026-06-08 08:30:24 +03:00
knowhy daf5f684b8 feat(llmtr): add models/gemma-4.toml 2026-06-08 08:30:23 +03:00
knowhy fa17e02dc2 feat(llmtr): add provider.toml 2026-06-08 08:30:22 +03:00
Yuhan Lei 4dbd6b6b13 fix: use base_model format instead of full definition 2026-06-08 10:56:26 +08:00
Yuhan Lei ff9199d68c feat: add qwen3.7-plus to alibaba-coding-plan-cn provider
Qwen3.7 Plus is now available on Alibaba Cloud Coding Plan (China).
2026-06-08 10:52:50 +08:00
Nathan Li e46f128b3a fix(cerebras): deprecate llama3.1-8b 2026-06-07 21:28:51 -04:00
Aiden Cline b5a8387a39 Merge pull request #2053 from smakosh/add-llmgateway-minimax-m3-qwen37-plus
feat(llmgateway): add MiniMax M3 and Qwen3.7 Plus
2026-06-07 20:12:32 -05:00
Aiden Cline f55137b165 Merge pull request #2056 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-06-07 20:12:15 -05:00
Aiden Cline 08607a1ea0 Merge pull request #2057 from anomalyco/automation/sync-models-vercel
chore(sync): update Vercel AI Gateway model catalog
2026-06-07 20:12:07 -05:00
Aiden Cline 4cabf9f282 Merge pull request #2055 from anomalyco/automation/sync-models-cloudflare-workers-ai
chore(sync): update Cloudflare Workers AI model catalog
2026-06-07 20:11:55 -05:00
github-actions[bot] d603abe1d9 chore(sync): update Cloudflare Workers AI model catalog 2026-06-07 23:38:41 +00:00
github-actions[bot] aedf097709 chore(sync): update OpenRouter model catalog 2026-06-07 23:38:39 +00:00
github-actions[bot] dafb6a02a2 chore(sync): update Vercel AI Gateway model catalog 2026-06-07 23:38:37 +00:00
Levente Polyak 15f015fd4a add Qwen3.7 Plus model configuration to Alibana coding plan
Coding-plan models are at a fixed monthly fee.

Link: https://modelstudio.console.alibabacloud.com/eu-central-1?tab=doc#/doc/?type=model&url=3005961
2026-06-07 21:54:13 +02:00
Leszek c02cf9ee89 refactor(zenmux): centralize model definitions and simplify provider configs
This refactors Zenmux model configurations by:
- Moving comprehensive model properties (e.g., limits, modalities) from `providers/zenmux/models/` to the shared `models/` directory.
- Introducing `base_model` references in `providers/zenmux/models/` files, which now primarily specify provider-specific attributes like `cost`.
- Updating parameters for `qwen3.7-plus`, `gpt-5.5-instant`, and `step-3.7-flash` during this reorganization.
2026-06-07 20:22:01 +02:00
Aiden Cline f112360043 Merge pull request #2052 from anomalyco/fix/google-sync-preserve-base-models
fix(google): compact sync and add Vertex TTS
2026-06-07 12:49:43 -05:00
Aiden Cline e6aca83545 feat(google-vertex): add Gemini 2.5 TTS models 2026-06-07 12:38:21 -05:00
smakosh 257a4fd79c fix(llmgateway): use base_model inheritance for MiniMax M3 and Qwen3.7 Plus
Upstream renamed the inheritance keyword from [extends].from to
base_model. Switch both new llmgateway entries to base_model so they
inherit the shared canonical metadata and only override llmgateway cost.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-07 18:29:09 +01:00
Aiden Cline 7feb291963 fix(google): remove unsupported TTS model ID 2026-06-07 12:28:33 -05:00
smakosh 3e8bec11b5 Merge remote-tracking branch 'upstream/dev' into add-llmgateway-minimax-m3-qwen37-plus
# Conflicts:
#	providers/alibaba/models/qwen3.7-plus.toml
#	providers/minimax/models/MiniMax-M3.toml
2026-06-07 18:21:42 +01:00
smakosh d322c49fc5 feat(llmgateway): add MiniMax M3 and Qwen3.7 Plus
Add two new text models from the LLM Gateway catalog
(https://api.llmgateway.io/v1/models), each as an llmgateway entry
extending a canonical provider model:

- minimax-m3 -> minimax/MiniMax-M3
- qwen3.7-plus -> alibaba/qwen3.7-plus

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-07 18:20:10 +01:00
Aiden Cline a067d458a9 Merge pull request #2030 from Nichokas/add-freemodel-provider
feat(freemodel): add FreeModel.dev provider (Anthropic + OpenAI formats)
2026-06-07 12:17:29 -05:00
Aiden Cline 9c0aaa8482 chore(google): sync image context limit 2026-06-07 12:17:23 -05:00
Aiden Cline 317334dc33 fix(google): preserve synced base models 2026-06-07 12:16:58 -05:00
Aiden Cline 134906e37c Merge pull request #2051 from anomalyco/refactor/vercel-shared-sync
chore(sync): update Vercel model catalog
2026-06-07 12:06:18 -05:00
Aiden Cline f473f985d9 Merge pull request #2049 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-06-07 12:05:21 -05:00
Frank b8f06211b0 update zen models 2026-06-07 12:48:22 -04:00
github-actions[bot] 8b742acb8b chore(sync): update OpenRouter model catalog 2026-06-07 16:46:19 +00:00
Aiden Cline 33be44552c Merge pull request #2042 from anomalyco/chore/sync-vercel-catalog
chore(sync): update Vercel model catalog
2026-06-07 11:45:03 -05:00
Herberto Graca 0645480326 Add NVIDIA/NVIDIA Nemotron 3 Ultra 2026-06-07 16:47:31 +02:00
Leszek 8d2f754dd6 feat(zenmux): add 11 new model definitions
New models: claude-opus-4.8, gemini-3.1-flash-lite, gemini-3.5-flash, ring-2.6-1t, minimax-m3, gpt-5.5-instant, qwen3.7-max, qwen3.7-plus, step-3.7-flash, grok-4.3, grok-build-0.1
2026-06-07 13:56:12 +02:00
Nichokas 72bba2a4a3 fix: Update logo to comply with the guidelines 2026-06-07 10:36:11 +02:00
Aiden Cline 3cfa5e6583 Merge pull request #2041 from anomalyco/refactor/vercel-shared-sync
refactor(sync): migrate Vercel to shared runner
2026-06-07 00:22:31 -05:00
Aiden Cline 4a01190179 Merge pull request #2043 from anomalyco/automation/sync-models-cloudflare-workers-ai
chore(sync): update Cloudflare Workers AI model catalog
2026-06-07 00:04:35 -05:00
Aiden Cline a00c4b4feb Merge pull request #2044 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-06-07 00:04:04 -05:00
github-actions[bot] b32b126540 chore(sync): update Cloudflare Workers AI model catalog 2026-06-07 03:26:37 +00:00
github-actions[bot] 4f296dcf55 chore(sync): update OpenRouter model catalog 2026-06-07 03:26:36 +00:00
Aiden Cline 285ca1a865 chore(sync): update Vercel model catalog 2026-06-06 19:49:46 -05:00
Aiden Cline 55b630c1f6 fix(vercel): inherit model update dates 2026-06-06 19:49:09 -05:00
Aiden Cline 20756bbba8 fix(vercel): resolve Alibaba metadata links 2026-06-06 18:56:46 -05:00
Aiden Cline 9260d4d112 fix(sync): match canonical metadata casing 2026-06-06 18:56:10 -05:00
Aiden Cline 022e6350c7 fix(vercel): factor canonical model metadata 2026-06-06 18:55:48 -05:00
Aiden Cline 2fc28466e8 fix(sync): report retained Vercel models 2026-06-06 18:51:55 -05:00
Aiden Cline a700d92235 refactor(sync): migrate Vercel to shared runner 2026-06-06 18:49:36 -05:00
Aiden Cline 95cfda05be Merge pull request #2028 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-06-06 18:44:57 -05:00
Aiden Cline 0f1783dad9 Merge pull request #2040 from anomalyco/fix/sync-retain-curated-base-models
fix(sync): retain curated base model links
2026-06-06 18:42:53 -05:00
Aiden Cline 7dfc7867f1 fix(sync): retain curated base model links 2026-06-06 18:41:11 -05:00
Aiden Cline 62ac8db1b8 Merge pull request #2039 from anomalyco/automation/sync-models-cloudflare-workers-ai
chore(sync): update Cloudflare Workers AI model catalog
2026-06-06 18:40:34 -05:00
github-actions[bot] 877da3f734 chore(sync): update OpenRouter model catalog 2026-06-06 23:38:33 +00:00
github-actions[bot] 62e9bdadb6 chore(sync): update Cloudflare Workers AI model catalog 2026-06-06 23:38:33 +00:00
Nichokas 14709d66d7 feat(freemodel): add provider logo
Addresses review feedback on #2030 — provider was missing a logo.svg.
2026-06-07 01:36:32 +02:00
Aiden Cline 1dd2250d1e Merge pull request #2038 from anomalyco/fix/cloudflare-sync-base-models
fix(sync): preserve Cloudflare base models
2026-06-06 18:20:59 -05:00
Aiden Cline 5bb15e680d fix(sync): preserve Cloudflare base models 2026-06-06 18:15:48 -05:00
Aiden Cline caa3521f13 update logos 2026-06-06 18:00:19 -05:00
Aiden Cline d996411611 Merge pull request #2037 from licat2023/fix/deepseek-cache-pricing
fix(models.dev): correct deepseek-chat/reasoner cache_read pricing
2026-06-06 17:51:44 -05:00
licat2023 68b75c7e5f fix(models.dev): correct deepseek-reasoner cache_read pricing (0.028 to 0.0028)
Matches DeepSeek V4 Flash pricing as deepseek-reasoner is a deprecated alias.
Ref: https://api-docs.deepseek.com/quick_start/pricing
2026-06-07 05:01:20 +08:00
licat2023 b780073b8d fix(models.dev): correct deepseek-chat cache_read pricing (0.028 to 0.0028)
Matches DeepSeek V4 Flash pricing as deepseek-chat is a deprecated alias.
Ref: https://api-docs.deepseek.com/quick_start/pricing
2026-06-07 05:01:18 +08:00
Nichokas 88abd70b24 refactor(freemodel): merge into one provider with per-model hosts
opencode exposes freemodel as a single provider behind one login. Move the
four GPT models out of the separate `freemodel-codex` provider and into
`freemodel`, giving each a per-model `[provider]` override
(`@ai-sdk/openai-compatible`, https://api.freemodel.dev/v1) so the Claude
models keep the provider default (`@ai-sdk/anthropic`, cc.freemodel.dev)
and the GPT models route to the OpenAI host. Removes `freemodel-codex`.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-06 15:32:29 +02:00
Adam e524b01b9a fix(models): add nvidia nemotron bases 2026-06-06 06:38:27 -05:00
Adam f753ddacdb fix(web): search provider models 2026-06-06 05:04:20 -05:00
Nichokas 84ed973170 feat(freemodel): add FreeModel.dev provider (Anthropic + OpenAI formats)
Adds two provider entries for freemodel.dev, a gateway exposing two model
sets depending on the API format:

- freemodel: Anthropic-format endpoint (cc.freemodel.dev) serving Claude
  models, via @ai-sdk/anthropic
- freemodel-codex: OpenAI-compatible endpoint (api.freemodel.dev) serving
  GPT/Codex models, via @ai-sdk/openai-compatible

Models inherit metadata via base_model and are priced at the providers'
standard rates; freemodel additionally charges cache_write at the input
rate for the OpenAI models.
2026-06-05 20:55:11 +02:00
Aiden Cline a6538b3644 Merge pull request #2012 from mvanhorn/fix/1848-evroc-qwen3-embedding-output-limit
fix: correct evroc Qwen3-Embedding-8B limit.output to 4096
2026-06-05 11:07:54 -05:00
Adam d70426e098 feat(web): improve search palette 2026-06-05 10:49:32 -05:00
Aiden Cline a4895edaac Merge pull request #2011 from Suat-B/dev
Add GPT 5.5 model to Xpersona provider
2026-06-05 09:34:10 -05:00
Adam 724ee7c132 feat(web): add search palette 2026-06-05 09:31:32 -05:00
Aiden Cline b9684cc0e8 Merge pull request #2027 from shzdehmd/dev
feat(fireworks-ai): add kimi-k2p6-fast model
2026-06-05 09:02:26 -05:00
Aiden Cline c22a18f293 Merge pull request #2017 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-06-05 08:55:58 -05:00
Ahmad Shahzad 173d5c6add feat(fireworks-ai): add kimi-k2p6-fast model
Fireworks AI is standardizing their naming convention to just "Fast"
for Fast/Turbo offerings (e.g., GLM 5.1 Fast). Adding kimi-k2p6-fast
to match this pattern while retaining kimi-k2p6-turbo for backward
compatibility with existing user workflows.
2026-06-05 18:52:13 +05:00
Aiden Cline d50aa210b7 fix: copilot modes 2026-06-05 08:34:41 -05:00
github-actions[bot] 7447979e06 chore(sync): update OpenRouter model catalog 2026-06-05 13:23:27 +00:00
Jack 189bd4139b Merge pull request #2023 from anomalyco/fix/opencode-go-qwen-plus-pricing-limits
feat(opencode-go): update Qwen Plus pricing and limits
2026-06-05 18:51:59 +08:00
Jack 350704d762 feat(opencode-go): update Qwen Plus pricing and limits 2026-06-05 18:32:20 +08:00
Aiden Cline 75c0d2cad3 Merge pull request #2020 from anomalyco/fix/google-missing-gemini-models
fix(google): add missing Gemini models
2026-06-05 00:48:27 -05:00
Aiden Cline c525d2a0fe fix(google): add missing Gemini models 2026-06-05 00:46:54 -05:00
Aiden Cline 0dc4a5f947 Merge pull request #2019 from anomalyco/fix/openrouter-inherit-input-limits
fix(openrouter): inherit input limits when context matches
2026-06-05 00:40:16 -05:00
Aiden Cline ad3e1e7d02 fix(openrouter): inherit input limits when context matches 2026-06-05 00:30:17 -05:00
Aiden Cline efc8827451 fix(bedrock): remove legacy model extends 2026-06-04 22:19:06 -05:00
Aiden Cline 947990c838 Merge pull request #1978 from anomalyco/feat/amazon-bedrock-openai-mantle-models
feat(amazon-bedrock): add OpenAI Mantle models
2026-06-04 22:15:31 -05:00
Aiden Cline 90a383e04e Merge pull request #2013 from Sawyerb/dev
Removed mercury-coder-small
2026-06-04 21:29:10 -05:00
Adam 9342481774 feat(web): redesign model-centric navigation (#2014) 2026-06-04 19:17:05 -05:00
Adam c7e827b320 fix(sync): use zhipuai metadata (#2010) 2026-06-04 18:30:39 -05:00
Sawyer 74dc5f8b46 removed mercury-coder-small 2026-06-04 16:19:20 -07:00
Matt Van Horn dd74f0c51c fix: correct evroc Qwen3-Embedding-8B output limit to 4096 2026-06-04 16:05:07 -07:00
Suat-B a7ab4866a2 Add trailing newline to Xpersona GPT-5.5 model 2026-06-04 17:31:20 -05:00
Suat-B 3f0137ae71 Use base model metadata for Xpersona GPT-5.5 2026-06-04 17:29:54 -05:00
Suat-B b3ba5f7727 Add GPT 5.5 model listed as official Xpersona offering 2026-06-04 17:17:55 -05:00
Aiden Cline 4bbb2c486f Merge pull request #1986 from anomalyco/feat/mistral-reasoning-options
feat(mistral): add reasoning effort options
2026-06-04 14:24:57 -05:00
Aiden Cline 5fe04aee59 fix(mistral): correct medium latest alias 2026-06-04 14:13:20 -05:00
Aiden Cline 3e5716e147 fix(mistral): add verified reasoning effort models 2026-06-04 13:48:44 -05:00
Aiden Cline c4aac4aea7 Merge pull request #2006 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-06-04 13:08:50 -05:00
Adam 69d1cb7773 feat(web): remove benchmarks column 2026-06-04 13:03:45 -05:00
Adam 32d509dd3b Normalize base-model inheritance (#2007) 2026-06-04 12:53:42 -05:00
github-actions[bot] 6c89d5fef7 chore(sync): update OpenRouter model catalog 2026-06-04 17:20:46 +00:00
Aiden Cline 8e6d393c01 Merge pull request #1984 from anomalyco/feat/sarvam-reasoning-options
feat(sarvam): add reasoning options
2026-06-04 11:59:21 -05:00
Aiden Cline ee8104f0a1 Merge pull request #2005 from zainhas/dev
[Together AI] add nemotron 3 ultra
2026-06-04 11:51:16 -05:00
Aiden Cline 10155a62eb Merge pull request #2004 from anomalyco/fix/sync-reasoning-options
fix(sync): preserve reasoning options
2026-06-04 11:51:03 -05:00
Zain Hasan afa81334ce [Together AI] add nemotron 3 ultra 2026-06-04 09:49:59 -07:00
Aiden Cline cc956258d6 fix(sync): preserve reasoning options 2026-06-04 11:49:16 -05:00
Aiden Cline dfcf5ba1cf Merge pull request #1999 from houtanb/fix-together-deepseek-models
fix(together): DeepSeek-R1, DeepSeek-V3 name & release date
2026-06-04 11:40:33 -05:00
Aiden Cline 637f7e3eec Merge pull request #1997 from dpuyosa/update-models
Venice: Add Qwen 3.7 Plus and update models
2026-06-04 11:40:20 -05:00
Aiden Cline a4b39711da Merge pull request #1996 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-06-04 11:39:34 -05:00
Aiden Cline 8f5d9e7b82 Merge pull request #1998 from chenkuilinckl-ai/fix/qwen3.7-plus-vision-1m-context
fix(alibaba): qwen3.7-plus GA adds vision (image+video) and 1M context
2026-06-04 11:39:04 -05:00
Aiden Cline 7beeab6cef Merge pull request #2003 from BlockListed/cortecs-gpt-5-4
add gpt 5.4 to cortecs
2026-06-04 11:37:46 -05:00
BlockListed 0a03c18424 add gpt 5.4 to cortecs 2026-06-04 18:13:57 +02:00
Adam c8a52d19c1 feat(models): add coding benchmarks and weights (#2000)
* feat(models): add coding benchmarks and weights

* feat(models): add more coding benchmarks

* feat(models): add agent benchmark scores

* feat(models): normalize benchmark metadata
2026-06-04 11:09:53 -05:00
Adam 859bb31ffa refactor(chutes): use base_model for tee wrappers (#2002) 2026-06-04 11:05:45 -05:00
Adam a672fe4b08 feat(web): surface model metadata links (#2001) 2026-06-04 11:03:53 -05:00
Frank 72fc81a4da update zen models 2026-06-04 11:31:06 -04:00
github-actions[bot] 2f77d0afac chore(sync): update OpenRouter model catalog 2026-06-04 15:25:27 +00:00
Houtan Bastani 03333d9aa4 fix(together): DeepSeek-R1, DeepSeek-V3 name & release date
See timestamps:
* "Release DeepSeek-R1": https://github.com/deepseek-ai/DeepSeek-R1/commit/23807ced51627276434655dd9f27725354818974
* "Release DeepSeek-V3": https://github.com/deepseek-ai/DeepSeek-V3/commit/4c2fdb8f55e049553b9f4f1a3241f86d739c8cf8
2026-06-04 13:16:14 +02:00
chenkuilinckl-ai 977e2f0155 fix(alibaba): qwen3.7-plus GA adds vision (image+video) and 1M context 2026-06-04 17:29:42 +08:00
dpuyosa 963e9a6bab [venice] Add Qwen 3.7 Plus and update models
- Added qwen-3-7-plus
- Update google-gemma-4-31b-it cache_read
- Update minimax-m3 output limit, modalities
2026-06-04 10:01:57 +02:00
Aiden Cline 9e8cad9ac9 Merge pull request #1988 from anomalyco/feat/stepfun-reasoning-options
feat(stepfun): add reasoning effort options
2026-06-04 00:38:32 -05:00
Aiden Cline f6c1036a86 Merge pull request #1985 from anomalyco/feat/xiaomi-reasoning-options
feat(xiaomi): add reasoning toggles
2026-06-04 00:37:58 -05:00
Aiden Cline 1926832a9d fix(sarvam): expose null reasoning effort 2026-06-04 00:17:23 -05:00
Aiden Cline cb22ad5625 Merge pull request #1992 from anomalyco/fix/sync-base-model-output
fix(sync): preserve base model output
2026-06-04 00:02:46 -05:00
Aiden Cline 909db75087 fix(sync): preserve base model output 2026-06-04 00:00:46 -05:00
Aiden Cline b551552f14 Merge pull request #1983 from anomalyco/feat/cohere-reasoning-options
feat(cohere): add reasoning options
2026-06-03 23:34:36 -05:00
Aiden Cline 0919062b40 Merge pull request #1989 from anomalyco/feat/google-gemini-reasoning-options
feat(google): add Gemini reasoning options
2026-06-03 23:05:44 -05:00
Aiden Cline 8662c63313 fix(google): retain deprecated Gemini reasoning metadata 2026-06-03 23:03:08 -05:00
Aiden Cline 36b808691a Merge pull request #1991 from shzdehmd/dev
chore(fireworks): update qwen3p6-plus limits to 262K context / 65K output
2026-06-03 22:21:52 -05:00
Ahmad Shahzad c8feebb7cd chore(fireworks): update qwen3p6-plus limits to 262K context / 65K output 2026-06-04 07:05:29 +05:00
Aiden Cline 259801fba5 fix(google): exclude unavailable Gemini 3 Pro preview 2026-06-03 18:28:25 -05:00
Aiden Cline ce35e18561 feat(stepfun): add reasoning effort options 2026-06-03 17:49:21 -05:00
Aiden Cline 133a0b0126 feat(google): add Gemini reasoning options 2026-06-03 17:49:09 -05:00
Aiden Cline 19d26ba611 feat(mistral): add reasoning effort options 2026-06-03 17:48:39 -05:00
Aiden Cline 99406ae7df feat(xiaomi): add reasoning toggles 2026-06-03 17:48:22 -05:00
Aiden Cline 4f25170be2 feat(cohere): add reasoning options 2026-06-03 17:48:05 -05:00
Aiden Cline 6ddf935238 feat(sarvam): add reasoning options 2026-06-03 17:48:00 -05:00
Aiden Cline 6ae56b00a8 Merge pull request #1981 from anomalyco/feat/glm-coding-plan-reasoning-toggle
feat(glm): add Zhipu and coding plan reasoning toggles
2026-06-03 17:31:39 -05:00
Aiden Cline 2cb0d28e17 feat(zhipuai): add reasoning toggles 2026-06-03 17:27:57 -05:00
Aiden Cline 03d90aeacc Merge pull request #1982 from anomalyco/fix/sync-model-catalog-matrix
fix(sync): restore model catalog workflow
2026-06-03 17:26:22 -05:00
Aiden Cline eb7dbead75 fix(sync): restore model catalog workflow 2026-06-03 17:20:01 -05:00
Aiden Cline 36cbbfc577 feat(glm): add coding plan reasoning toggles 2026-06-03 16:56:42 -05:00
Aiden Cline d84e883ede Merge pull request #1980 from anomalyco/feat/deepseek-reasoning-options
feat(deepseek): add reasoning options
2026-06-03 16:09:22 -05:00
Aiden Cline dd9d6ff54e feat(deepseek): add reasoning options 2026-06-03 16:08:09 -05:00
Aiden Cline d7e19c7627 Merge pull request #1979 from anomalyco/feat/moonshot-reasoning-toggle
feat(moonshot): add reasoning toggle options
2026-06-03 15:46:39 -05:00
Aiden Cline ca3eb39fbd feat(moonshot): add reasoning toggle options 2026-06-03 15:45:15 -05:00
Aiden Cline d136e7b036 Merge pull request #1955 from eliasaronson/chore/mark-deprecated-models
chore: mark retired models as deprecated
2026-06-03 15:25:27 -05:00
Adam f6c6f04367 feat(models): add model metadata (#1974)
* feat(models): add model metadata

* feat(models): rename model metadata namespaces
2026-06-03 15:13:54 -05:00
Aiden Cline 1e9e4bbdab Merge pull request #1977 from Ardakilic/feat/nano-gpt-20260603
chore: sync nano-gpt models: 20260603
2026-06-03 15:02:42 -05:00
Aiden Cline fbaf50d323 feat(amazon-bedrock): add OpenAI Mantle models 2026-06-03 14:58:05 -05:00
Arda Kılıçdağı efb553d287 chore: sync nano-gpt models: 20260603 2026-06-03 21:31:28 +03:00
Jack d9b83ca9cd Merge pull request #1975 from anomalyco/update/opencode-go-qwen3.7-plus
feat(opencode-go): add Qwen3.7 Plus model
2026-06-04 01:30:11 +08:00
Aiden Cline 25592e361a Merge pull request #1976 from jerome-benoit/feat/sap-ai-core-gpt-5.5
feat(sap-ai-core): add GPT-5.5
2026-06-03 12:28:07 -05:00
Jérôme Benoit 012928800c fix(sap-ai-core): align GPT-5.4 release_date with upstream
SAP AI Core routes to OpenAI gpt-5.4; release_date should reflect
the actual model release (2026-03-05) rather than the SAP catalog
availability date (2026-04-27).
2026-06-03 19:09:54 +02:00
Jérôme Benoit ee60c2e4d4 feat(sap-ai-core): add GPT-5.5
SAP AI Core routes to OpenAI gpt-5.5; specs mirror the canonical
provider/openai/gpt-5.5 with the established sap-ai-core wrapper
adjustments (lowercase name, drop [[cost.tiers]], drop
[experimental.modes.fast]).
2026-06-03 19:06:07 +02:00
Jack 7e76cde0b1 fix(opencode-go): correct Qwen3.7 Plus dates 2026-06-04 00:59:42 +08:00
Jack bbd2479e12 feat(opencode-go): add Qwen3.7 Plus model 2026-06-04 00:57:42 +08:00
Aiden Cline eeb17ccab4 Merge pull request #1971 from coder-wangbin/feat/alibaba-cn-qwen3.7-plus
feat: add Qwen3.7 Plus model for alibaba-cn provider
2026-06-03 10:00:39 -05:00
Aiden Cline 46ffeee012 Merge pull request #1972 from Phosmachina/feature/update-deepinfra-deepseek-and-mimo
Feature/update deepinfra deepseek and mimo
2026-06-03 09:56:37 -05:00
Aiden Cline 8c1e45007d Merge pull request #1967 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-06-03 09:54:14 -05:00
Frank 364628cb93 update zen models 2026-06-03 10:32:41 -04:00
github-actions[bot] 50f5d40b4e chore(sync): update OpenRouter model catalog 2026-06-03 14:02:08 +00:00
Michel Paronnaud 707be517c6 chore(deepinfra): adjust prices and limit for DeepSeek models 2026-06-03 12:40:49 +02:00
Michel Paronnaud 657598e609 fix(deepinfra): path for mimo models 2026-06-03 12:28:08 +02:00
wangbin 0999a475ba feat: add Qwen3.7 Plus model for alibaba-cn provider
- Add base definition in providers/alibaba/models/qwen3.7-plus.toml
- Add extends reference in providers/alibaba-cn/models/qwen3.7-plus.toml
- Release date: 2026-06-02
- Context: 131K tokens, Output: 16K tokens
- Pricing: $0.50/$3.00 per 1M tokens (input/output)
- Supports reasoning and tool calling
2026-06-03 17:40:12 +08:00
Frank e1ea0254ed update zen models 2026-06-02 22:51:19 -04:00
Aiden Cline 7fad18b054 fix 2026-06-02 16:36:29 -05:00
Aiden Cline 710bbc5375 Merge pull request #1961 from anomalyco/feat/minimax-m3-reasoning-toggle
feat(minimax): add M3 reasoning toggle
2026-06-02 16:34:19 -05:00
Aiden Cline 0b9fa62153 Merge pull request #1963 from nicholasgriffintn/open-mistral-nemo
fix: update mistral nemo
2026-06-02 14:34:54 -05:00
Aiden Cline 126a481a70 Merge pull request #1965 from nicholasgriffintn/update-devstral-models
chore: update devstral models
2026-06-02 14:34:38 -05:00
Aiden Cline b080cf1fe4 Merge pull request #1952 from anomalyco/automation/sync-models-xai
chore(sync): update xAI model catalog
2026-06-02 14:03:02 -05:00
Nicholas Griffin 042002d3a3 chore: update devstral models 2026-06-02 19:47:17 +01:00
Nicholas Griffin a192b51e84 chore: undo 2026-06-02 19:46:13 +01:00
Nicholas Griffin b870c796ef chore: undo 2026-06-02 19:45:25 +01:00
Nicholas Griffin 35e4981aa9 chore: update 2026-06-02 19:40:02 +01:00
Frank 970b660070 sync 2026-06-02 14:24:55 -04:00
Nicholas Griffin bb03a8c207 fix: update mistral nemo 2026-06-02 19:22:36 +01:00
github-actions[bot] b6dbb68c32 chore(sync): update xAI model catalog 2026-06-02 18:21:19 +00:00
Aiden Cline b34a7c21f3 feat(minimax): add M3 reasoning toggle 2026-06-02 12:43:17 -05:00
Aiden Cline 4b169b8cb6 Merge pull request #1960 from anomalyco/feat/zai-reasoning-toggle
feat(zai): add reasoning toggle options
2026-06-02 12:38:15 -05:00
Aiden Cline f8ecf4daec feat(zai): add reasoning toggle options 2026-06-02 12:02:54 -05:00
Frank eb68be3fbc stats 2026-06-02 12:38:49 -04:00
Aiden Cline 55fb058cc5 tweak: update available options 2026-06-02 11:35:26 -05:00
Aiden Cline 5545a98866 tweak: handle missing omits gracefully 2026-06-02 11:25:55 -05:00
Aiden Cline 1a7b103bba fix: omit 2026-06-02 11:22:52 -05:00
Aiden Cline f341858398 Merge pull request #1896 from stevenyeung/add/alibaba-token-plan
feat: add Alibaba Token Plan provider with 15 models
2026-06-02 11:20:42 -05:00
Aiden Cline f2d1e42582 Merge pull request #1951 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-06-02 11:03:27 -05:00
Aiden Cline 2f9d2d8d78 Merge pull request #1957 from kapelame/fix/minimax-m3-prune
fix(minimax): correct MiniMax-M3 pricing and max output
2026-06-02 10:53:58 -05:00
Aiden Cline bf6b0e32d7 Merge pull request #1959 from Tavernari/feat/claudinio-add-audio-video
feat(claudinio): add audio and video input modalities
2026-06-02 10:53:25 -05:00
github-actions[bot] 5b4d2ea2e4 chore(sync): update OpenRouter model catalog 2026-06-02 15:41:53 +00:00
Victor Carvalho Tavernari ee4badab7b fix(claudinio): update cache_read price to 0.150 per 1M tokens 2026-06-02 16:34:05 +01:00
Victor Carvalho Tavernari 6c05a6b519 Merge branch 'dev' into feat/claudinio-add-audio-video 2026-06-02 16:32:12 +01:00
Victor Carvalho Tavernari 91ae9a48e3 feat(claudinio): add audio and video input modalities 2026-06-02 16:24:06 +01:00
kapelame 85d02711bd fix(minimax): correct MiniMax-M3 pricing and max output
The M3 entries added in #1940 copied M2.7's cost values. Correct them to
the official M3 pricing and limits:

- minimax / minimax-cn (pay-as-you-go): input 0.30 -> 0.60,
  output 1.20 -> 2.40, cache_read 0.06 -> 0.12, and remove cache_write
  (M3 has no active prompt-cache-write tier).
- max output 131072 -> 128000 across all four providers.
- coding-plan variants keep their subscription-plan zero pricing; only
  max output is corrected.

Context (512K), modalities, and the other flags are unchanged.
2026-06-02 21:03:45 +08:00
Elias H Aronsson 1ba404612d chore: mark retired models as deprecated
Add status = "deprecated" to models that are past their provider's
shutdown/retirement date (no longer served by the public API).

Google Gemini (4):
  gemini-2.0-flash, gemini-2.0-flash-lite, gemini-3-pro-preview,
  gemini-3.1-flash-lite-preview

Anthropic Claude (7):
  claude-3-sonnet-20240229, claude-3-5-sonnet-20240620,
  claude-3-5-sonnet-20241022, claude-3-opus-20240229,
  claude-3-7-sonnet-20250219, claude-3-5-haiku-20241022,
  claude-3-haiku-20240307

OpenAI (2):
  o1-preview, o1-mini

Sources:
  https://ai.google.dev/gemini-api/docs/deprecations
  https://platform.claude.com/docs/en/about-claude/model-deprecations
  https://developers.openai.com/api/docs/deprecations
2026-06-02 10:06:18 +02:00
Aiden Cline f91dd4ad0b Merge pull request #1950 from anomalyco/fix/reasoning-options-inheritance
fix: do not inherit reasoning options
2026-06-01 23:24:13 -05:00
Aiden Cline 449b926f40 fix: do not inherit reasoning options 2026-06-01 23:22:04 -05:00
Aiden Cline 2546ffe570 Merge pull request #1940 from matstrange/add-minimax-m3
Add MiniMax-M3 model (#1933)
2026-06-01 22:57:45 -05:00
Hex Agent f33ff9ba78 Add MiniMax-M3 model to 5 providers
MiniMax-M3 is MiniMax's new frontier multimodal coding model: 1M context
window (512K minimum on ollama-cloud), native text/image/video input,
tool calling, reasoning, and open weights.

Adds the model to all five providers where it should be available:

  - minimax (pay-as-you-go)
  - minimax-cn (pay-as-you-go, China)
  - minimax-coding-plan (token plan subscription)
  - minimax-cn-coding-plan (token plan subscription, China)
  - ollama-cloud

Closes #1933.

Notes for reviewers:
  - Cost fields on minimax/minimax-cn match M2.7; M3 docs state the
    pricing is unchanged from M2.7.
  - The 1M/512K context divergence on ollama-cloud is intentional —
    ollama advertises 1M with a 512K minimum, so 512K is the safe floor
    that won't surprise opencode users with mid-request rejections.
  - output = 131072 is inherited from the existing M2.7 files; MiniMax's
    published M3 docs only advertise the 1M input context, not a separate
    output cap.
  - The minimax-coding-plan variant has been verified end-to-end in
    opencode against the MiniMax token plan API.
2026-06-01 22:54:17 -05:00
Aiden Cline 98bf80cd77 Merge pull request #1949 from anomalyco/fix/github-copilot-context-limits-complete
fix(github-copilot): preserve model-specific limits
2026-06-01 22:49:00 -05:00
Aiden Cline 68660cad83 Merge pull request #1938 from anyapi-ai/dev
Add AnyAPI provider
2026-06-01 22:47:26 -05:00
Aiden Cline 78e6c1a2dd fix(github-copilot): preserve model-specific limits 2026-06-01 22:46:56 -05:00
Aiden Cline 062ba1fbb7 Merge pull request #1939 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-06-01 22:46:18 -05:00
Aiden Cline 477ccffee8 Merge pull request #1948 from anomalyco/feat/anthropic-reasoning-options
feat(anthropic): add reasoning options
2026-06-01 22:41:23 -05:00
github-actions[bot] 6ce2f88eac chore(sync): update OpenRouter model catalog 2026-06-02 03:26:49 +00:00
Aiden Cline 4501589a20 feat(anthropic): add reasoning options 2026-06-01 22:17:07 -05:00
Aiden Cline 0b643efd17 Merge pull request #1947 from LYY/fix/github-copilot-context-limits
fix(github-copilot): correct limits for 8 models with verified CAPI data (partial, refs #1946)
2026-06-01 22:16:07 -05:00
LYY 8a0ea15aca fix(github-copilot): correct limits for models with verified CAPI data
The github-copilot model stubs use [extends] and inherit the upstream
base model's context/input/output limits (~1M), which do not match the
limits GitHub Copilot actually enforces via api.githubcopilot.com/models.

Override the limit fields for the 8 models whose live CAPI values were
verified first-hand. Models that were not enabled on the test account
(no CAPI data available) are intentionally left unchanged.

Refs anomalyco/models.dev#1946
2026-06-02 11:08:51 +08:00
Aiden Cline b3676fd77d Merge pull request #1934 from yukoba/github-copilot-2026-06
June 2026 changes of GitHub Copilot
2026-06-01 16:10:45 -05:00
Aiden Cline f97a02078c Merge pull request #1932 from eliasto/ovhcloud/update-models-qwen
feat(ovhcloud): Add new Qwen models and sync mode
2026-06-01 14:27:58 -05:00
Aiden Cline 2a7153fcef Merge pull request #1943 from peculiarnewbie/fix/crof-models-update
fix: update crof.ai models to match current API
2026-06-01 13:41:23 -05:00
Aiden Cline 3396f15854 Merge pull request #1942 from anomalyco/feat/reasoning-options-schema
feat: add reasoning options schema
2026-06-01 13:41:10 -05:00
Aiden Cline ccfd99b5e9 Merge pull request #1941 from KTibow/fix-llmgateway-deepseek-v3-2-price
fix(llmgateway): update model pricing
2026-06-01 13:40:20 -05:00
bolt ef6eb88216 fix: update crof.ai models to match current API 2026-06-02 00:52:14 +07:00
Aiden Cline 94e128244a feat: add reasoning options schema 2026-06-01 12:48:11 -05:00
KTibow ec6d07d41c fix(llmgateway): use weighted pricing selection 2026-06-01 10:41:23 -07:00
KTibow 4efbe58af8 fix(llmgateway): update model pricing 2026-06-01 10:24:05 -07:00
Christina 3b55102a45 Add AnyAPI provider with 30 models
Adds AnyAPI (https://anyapi.ai) as a new provider. Models reuse existing
canonical entries through `extends`. Cost fields are omitted as AnyAPI uses
a credit-based pricing system. Validated locally with `bun validate`.

Models (30):
- openai: gpt-5.4, gpt-5.2, gpt-5.1, gpt-5, gpt-5-mini, gpt-4.1, gpt-4.1-mini, o4-mini, o3, o3-mini
- anthropic: claude-opus-4-7, claude-opus-4-6, claude-sonnet-4-6, claude-sonnet-4-5, claude-haiku-4-5
- google: gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-lite, gemini-3-pro-preview, gemini-3-flash-preview
- deepseek: deepseek-v4-pro, deepseek-v4-flash, deepseek-chat, deepseek-r1
- mistralai: mistral-large-2512, devstral-2512
- perplexity: sonar-pro, sonar-reasoning-pro
- cohere: command-r-plus-08-2024
- xai: grok-4.3
2026-06-01 17:14:24 +02:00
Aiden Cline a4fe8fc36b fmt 2026-06-01 09:53:16 -05:00
Aiden Cline b24b44ca0a Merge pull request #1920 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-06-01 09:39:43 -05:00
Aiden Cline 466d664bf9 Merge pull request #1930 from dpuyosa/dev
Venice: Add MiniMax M3 model
2026-06-01 09:39:27 -05:00
Aiden Cline 340ef131e9 Merge pull request #1936 from JoshuaDietz/dev
feat(ollama-cloud): add minimax m3
2026-06-01 09:38:47 -05:00
Aiden Cline 6ce69a706a Merge pull request #1937 from KTibow/fix/hpc-ai-pricing
fix: update HPC-AI model pricing
2026-06-01 09:38:34 -05:00
KTibow 3505674a1b fix: update HPC-AI model pricing 2026-06-01 07:29:43 -07:00
github-actions[bot] cfeaef8f77 chore(sync): update OpenRouter model catalog 2026-06-01 14:25:41 +00:00
Joshua Dietz f73a5d571b feat(ollama-cloud): add minimax m3 2026-06-01 16:14:49 +02:00
Yu Kobayashi 62d31abff8 June 2026 changes of GitHub Copilot 2026-06-01 22:03:44 +09:00
Elias TOURNEUX ee71ea7181 feat(ovhcloud): Add qwen 3.6 27b 2026-06-01 11:57:58 +02:00
Elias TOURNEUX b038f40b64 feat(ovhcloud): Add OVHcloud sync mode 2026-06-01 10:28:46 +02:00
Elias TOURNEUX 4b7bdd9692 feat(ovhcloud): Add new Qwen models 2026-06-01 10:16:54 +02:00
dpuyosa b73ef1a634 [venice] Add MiniMax M3 model
- Add minimax-m3.toml with cost, limits, modalities
- Enable text/image input and text output support
- Set 500k context, 32k output, cache pricing
2026-06-01 09:38:12 +02:00
Aiden Cline c11b5bb00b Merge pull request #1927 from Jercik/codex/update-wafer-price-cuts
fix: update Wafer.ai pricing
2026-06-01 00:01:03 -05:00
Łukasz Jerciński 01bc1785b4 fix: update Wafer price cuts 2026-06-01 06:25:20 +02:00
Aiden Cline 36b5847fa4 Merge pull request #1925 from anomalyco/fix/vercel-claude-opus-4-1-symlink
fix vercel claude opus 4.1 symlink
2026-05-31 22:12:27 -05:00
Aiden Cline 040beaf818 fix vercel claude opus 4.1 symlink 2026-05-31 22:11:05 -05:00
Frank 9f8e1a3858 update zen models 2026-05-31 22:07:52 -04:00
Jack ce7a1c0218 update context limit of M3 in Go 2026-06-01 09:45:46 +08:00
Jack 55e6c7a2ee add image,video modalities to M3 2026-06-01 08:58:02 +08:00
Frank 8bacf496fe update zen models 2026-05-31 19:49:41 -04:00
Frank ac12cf1f43 update zen models 2026-05-31 19:47:33 -04:00
Frank 06c7ea2303 update zen models 2026-05-31 19:47:04 -04:00
Frank 92b6e9da53 update zen models 2026-05-31 19:43:09 -04:00
Frank 660ff026a0 update zen models 2026-05-31 19:40:57 -04:00
Aiden Cline 9a910a1fb3 Merge pull request #1917 from markgibaud/fix/eu-opus-bedrock-pricing
fix(bedrock): correct EU cross-region pricing for Claude Opus and Sonnet models
2026-05-31 17:37:45 -05:00
Aiden Cline 7dc5f787b0 Merge pull request #1915 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-05-31 17:10:10 -05:00
Aiden Cline c25ddce07c Merge pull request #1916 from anomalyco/automation/sync-models-cloudflare-workers-ai
chore(sync): update Cloudflare Workers AI model catalog
2026-05-31 17:05:57 -05:00
github-actions[bot] e73a82e44e chore(sync): update OpenRouter model catalog 2026-05-31 21:36:49 +00:00
github-actions[bot] 7de9710b5a chore(sync): update Cloudflare Workers AI model catalog 2026-05-31 21:36:49 +00:00
Frank d1a8dbcdde update zen models 2026-05-31 14:19:49 -04:00
markgibaud 556ef84d11 fix(bedrock): correct EU cross-region pricing for Claude Opus and Sonnet models
AWS Bedrock EU (Europe/London) cross-region inference has a 10% premium
over the base Anthropic pricing. The EU models were incorrectly using
the same pricing as the US/base models.

Affected models:
- eu.anthropic.claude-opus-4-6-v1
- eu.anthropic.claude-opus-4-7
- eu.anthropic.claude-opus-4-8
- eu.anthropic.claude-sonnet-4-5-20250929-v1:0
- eu.anthropic.claude-sonnet-4-6

Corrected Opus per 1M token prices:
- Input: $5.00 -> $5.50
- Output: $25.00 -> $27.50
- Cache read: $0.50 -> $0.55
- Cache write: $6.25 -> $6.875

Corrected Sonnet per 1M token prices:
- Input: $3.00 -> $3.30
- Output: $15.00 -> $16.50
- Cache read: $0.30 -> $0.33
- Cache write: $3.75 -> $4.125

Source: AWS Bedrock pricing page, Europe (London) region
2026-05-31 11:07:18 +01:00
Aiden Cline f2020553ea Merge pull request #1898 from Suat-B/codex/xpersona-frieren-1
Rename Xpersona Frieren display name
2026-05-30 16:44:39 -05:00
Aiden Cline ca0a7e17cb Merge pull request #1910 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-05-30 16:44:22 -05:00
github-actions[bot] d2468eafb2 chore(sync): update OpenRouter model catalog 2026-05-30 21:37:16 +00:00
Aiden Cline 96d0f9beff Merge pull request #1913 from orangeclk/add-glm-4.6v-zhipuai-coding-plan
feat(zhipuai-coding-plan): add glm-4.6v symlink from zai
2026-05-30 11:52:50 -05:00
Aiden Cline 7989be9f34 Merge pull request #1912 from Jercik/codex/update-wafer-provider-models
feat: update Wafer provider models
2026-05-30 11:52:41 -05:00
Łukasz Jerciński f30e44f4b5 feat: update Wafer provider models 2026-05-30 14:53:02 +02:00
OrangeCLK 1383177893 feat(zhipuai-coding-plan): add glm-4.6v symlink from zai 2026-05-30 18:42:09 +08:00
Aiden Cline 2e58165af9 Merge pull request #1902 from kameshsampath/feat/provider/snowflake-cortex
feat(snowflake-cortex): add Snowflake Cortex provider
2026-05-29 23:55:55 -05:00
Kamesh Sampath f3466affc0 feat(snowflake-cortex): add Snowflake Cortex provider
Adds the snowflake-cortex provider which exposes Snowflake's Cortex
REST API (OpenAI Chat Completions-compatible endpoint) to opencode.

Provider details:
- npm: @ai-sdk/openai-compatible
- API: https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1
- Auth: SNOWFLAKE_ACCOUNT + SNOWFLAKE_CORTEX_PAT (Programmatic Access Token)

Models (11, all with tool_call support):
- Anthropic: claude-opus-4-7 (beta/preview), claude-sonnet-4-6,
  claude-sonnet-4-5, claude-haiku-4-5
- OpenAI: openai-gpt-5.4 (beta), openai-gpt-5.2, openai-gpt-5.1,
  openai-gpt-5 (beta), openai-gpt-5-mini (beta), openai-gpt-5-nano (beta),
  openai-gpt-4.1

Models without tool_call support (deepseek-r1, llama3.1-70b,
snowflake-llama-3.3-70b, mistral-large2) are excluded per Snowflake docs:
"Tool calling is supported for OpenAI and Claude models only."

Preview/not-GA models are marked with status = "beta".

Cost fields are intentionally omitted on all models. The Cortex REST API
is billed in USD (AI_INFERENCE service type) at rates defined in the
Snowflake Service Consumption Table.

Closes #1895
2026-05-30 09:04:43 +05:30
Aiden Cline 3697c99297 Merge pull request #1901 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-05-29 20:50:33 -05:00
Aiden Cline 796dda2fd1 Merge pull request #1904 from sdnts/dev
feat(cloudflare-ai-gateway): add opus 4.8
2026-05-29 20:50:11 -05:00
Aiden Cline 1d363cbd7f Merge pull request #1908 from anomalyco/fix/unique-provider-names
Ensure provider names are unique
2026-05-29 20:49:54 -05:00
Aiden Cline 3758725979 Ensure provider names are unique
Rename the China StepFun provider to "StepFun (China)" so it no longer
collides with the international "StepFun" provider, following the existing
Alibaba / Alibaba (China) naming convention.

Add a validation check in generate() that throws when two providers share
a (case-insensitive) name, preventing future duplicates.

Fixes #1906
2026-05-29 20:48:09 -05:00
github-actions[bot] c039e82f12 chore(sync): update OpenRouter model catalog 2026-05-30 01:16:42 +00:00
Siddhant 1e90242cdb feat(cloudflare-ai-gateway): add opus 4.8 2026-05-29 13:55:09 -04:00
Aiden Cline 277ac8577e Merge pull request #1897 from mikeyp/update-digitalocean-models
Add deepseek-4-flash and claude-opus-4.8 for DigitalOcean
2026-05-29 10:20:26 -05:00
Aiden Cline 6e5f35546d Merge pull request #1900 from ceyhanmolla/add-step-3.7-flash-v2
Add Step 3.7 Flash model to NVIDIA provider
2026-05-29 10:20:02 -05:00
ceyhanmolla aa69da14d6 Add Step 3.7 Flash model to NVIDIA provider
StepFun AI's Step 3.7 Flash - sparse MoE multimodal reasoning model:
- 198B total params, ~11B active per token
- 256K context window with sliding window attention
- Text + image input, text output
- Reasoning, tool calling, and attachment support
- Apache 2.0 license
2026-05-29 12:55:13 +02:00
Jack c7af5ba9be update model in Go 2026-05-29 16:20:16 +08:00
Suat-B d6e9e6735f Rename Xpersona Frieren model display name 2026-05-29 03:00:21 -05:00
Mike Prasuhn a987719410 Add deepseek-4-flash and claude-opus-4.8 2026-05-29 03:45:50 -04:00
Steven Yeung 3b792029c3 feat(alibaba-token-plan): add provider and 15 model TOMLs
Add Alibaba Cloud Model Studio Token Plan (Team Edition) provider with:
- Provider config (Singapore region, OpenAI-compatible endpoint)
- 10 models using extends pattern (zero-cost overrides from canonical providers)
- 5 models with full definitions (no canonical source available)
- Image generation models (qwen-image, wan2.7) with output=0 per convention
- deepseek-v3.2 with structured_output and corrected release date

Models: qwen3.7-max, qwen3.6-flash, qwen3.6-plus, kimi-k2.5, kimi-k2.6,
glm-5, glm-5.1, MiniMax-M2.5, deepseek-v4-pro, deepseek-v4-flash,
deepseek-v3.2, qwen-image-2.0, qwen-image-2.0-pro, wan2.7-image, wan2.7-image-pro
2026-05-29 15:12:27 +08:00
Aiden Cline 9528528f69 Merge pull request #1890 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-05-28 23:42:03 -05:00
github-actions[bot] fbad40d863 chore(sync): update OpenRouter model catalog 2026-05-29 03:26:05 +00:00
Aiden Cline 84559b598b Merge pull request #1894 from anomalyco/add-siliconflow-cn-deepseek-v4-pro
feat(siliconflow-cn): add deepseek-ai/DeepSeek-V4-Pro
2026-05-28 19:10:18 -05:00
Aiden Cline 9d45730db9 Merge pull request #1889 from fhennerkes/dev
poe: add Claude-Opus-4.8 model
2026-05-28 19:10:06 -05:00
Aiden Cline 791089e4aa Merge pull request #1891 from ticoombs/dev
feat(copilot): update all copilot models, add claude-opus-4.8
2026-05-28 19:09:52 -05:00
Aiden Cline fcc4387187 feat(siliconflow-cn): add deepseek-ai/DeepSeek-V4-Pro 2026-05-28 19:09:15 -05:00
Tim C 6aa32ba566 fix(copilot): update all context,input,output with correct limits 2026-05-29 08:56:19 +10:00
Tim C 459a563d2b feat(copilot): add claude-opus-4.8 2026-05-29 08:52:42 +10:00
Aiden Cline 739e5a7c8e Merge pull request #1877 from aakash-gupte/add-merge-gateway-provider
Add Merge Gateway provider
2026-05-28 16:55:40 -05:00
Aiden Cline efc87afa3a Merge pull request #1888 from smakosh/add-llmgateway-opus-4-8
feat(llmgateway): add Claude Opus 4.8
2026-05-28 16:54:46 -05:00
Aiden Cline f616aa6a0b Merge pull request #1887 from dpuyosa/dev
Venice: Add Claude Opus 4.8 models
2026-05-28 16:54:35 -05:00
fhennerkes f77e75a567 poe: add Claude-Opus-4.8 model
Add new Anthropic model from Poe API (released 2026-05-28).
Uses extends format inheriting from anthropic/claude-opus-4-8
with Poe-specific overrides (name format, markup pricing,
slightly different context limit).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-28 14:39:52 -07:00
smakosh 651bd4d91a feat(llmgateway): add Claude Opus 4.8
Extends anthropic/claude-opus-4-8, omitting the fast mode which LLM
Gateway does not expose, matching the existing 4.6/4.7 entries.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-05-28 22:07:40 +01:00
dpuyosa 30b9170106 [venice] Add Claude Opus 4.8 models
- Add claude-opus-4-8.toml (standard pricing)
- Add claude-opus-4-8-fast.toml (fast variant)
- Both: 1M context, image input, Opus 4.8 family
2026-05-28 22:54:39 +02:00
Aiden Cline 81e42c653c Merge pull request #1886 from vglafirov/add-gitlab-opus-4-8
feat: add GitLab Agentic Chat Opus 4.8
2026-05-28 15:25:06 -05:00
Vladimir Glafirov 11f2a38594 feat: add GitLab Agentic Chat Opus 4.8 2026-05-28 22:12:12 +02:00
Aiden Cline 6621be978f Merge pull request #1880 from bas3line/update-routing-run-base-url
Update routing.run API base URL
2026-05-28 14:46:09 -05:00
Aiden Cline c8d72661d6 Merge pull request #1885 from alaviss/bedrock-opus-4-8
feat: add cross-region inference entries for Bedrock for Opus 4.8
2026-05-28 14:45:43 -05:00
Hiếu Lê 21b7cacc33 feat: add cross-region inference entries for Bedrock for Opus 4.8 2026-05-28 12:38:19 -07:00
Aiden Cline ac1dc14439 Merge pull request #1884 from calebboyd/update-vercel-models-latest
feat: add vercel ai gateway opus 4.8
2026-05-28 14:31:03 -05:00
Aiden Cline 63acb799da Merge pull request #1883 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-05-28 14:30:56 -05:00
github-actions[bot] 2e6ebb6750 chore(sync): update OpenRouter model catalog 2026-05-28 19:11:47 +00:00
calebboyd d8c2e15632 feat: add vercel ai gateway opus 4.8 2026-05-28 13:33:37 -05:00
Frank 8a70160200 update zen model 2026-05-28 14:01:35 -04:00
Aiden Cline 7ea1d4e15c Merge pull request #1882 from anomalyco/add-opus-4.8
feat: add opus 4.8
2026-05-28 12:04:51 -05:00
Aiden Cline 1c71b1bf17 feat: add opus 4.8 2026-05-28 12:04:14 -05:00
Aiden Cline acc3126194 Merge pull request #1879 from Ardakilic/chore/ci-fork-ensurance
CI Scheduled fork upstream ensurance
2026-05-28 11:27:47 -05:00
Aiden Cline 1f67addc01 Merge pull request #1878 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-05-28 11:27:07 -05:00
github-actions[bot] bb011e71a7 chore(sync): update OpenRouter model catalog 2026-05-28 15:28:44 +00:00
bas3line 3df181411f fix(routing-run): update API base URL 2026-05-28 08:58:33 +05:30
Arda Kilicdagi a1f588463c chore: prevent forks to run cronjobbed sync commands 2026-05-28 06:25:45 +04:00
Arda Kilicdagi cb414c6886 chore: prevent forks to run cronjobbed sync commands 2026-05-28 05:31:19 +04:00
Arda Kilicdagi 4095e819c9 chore: prevent forks to run cronjobbed sync commands
chore: prevent forks to run cronjobbed sync commands
2026-05-28 05:26:15 +04:00
Aakash Gupte 9367cc1825 Add Merge Gateway logo
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-27 17:22:44 -04:00
Aakash Gupte 96b9a04c4b Add Merge Gateway provider
Merge Gateway (https://merge.dev) is an LLM gateway exposing an
OpenAI/Anthropic-compatible API across many providers, using the
published `merge-gateway-ai-sdk-provider` npm package. Models are
defined via `extends` from existing canonical entries.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-27 14:32:21 -04:00
Jack d9de217dc4 update zen models 2026-05-28 01:46:38 +08:00
Aiden Cline 64ea80d416 Merge pull request #1869 from anomalyco/fix/xiaomi-token-plan-models
fix Xiaomi Token Plan model catalog
2026-05-27 12:02:22 -05:00
Aiden Cline d3859517d1 Merge pull request #1870 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-05-27 12:01:59 -05:00
Aiden Cline 985a144c5f Merge pull request #1866 from tarikko/patch-1
Update Mistral Small model details in TOML file
2026-05-27 11:43:52 -05:00
Jack 5b05070eb4 Merge pull request #1875 from anomalyco/update/opencode-go-mimo-v2-5-pricing
update opencode go MiMo V2.5 pricing
2026-05-28 00:39:53 +08:00
Aiden Cline dad245c5e1 Merge pull request #1871 from oskarkocol/chore/update-groq-cache-prices
chore: update groq cache pricing
2026-05-27 11:39:22 -05:00
Aiden Cline bcff9bd6b2 Merge pull request #1874 from Alex-yang00/codex/sync-novita-models
Sync NovitaAI models
2026-05-27 11:39:03 -05:00
Aiden Cline 561bdaa546 Merge pull request #1876 from sebastiand-cerebras/deprecate-cerebras-qwen235b-llama8b-20260527
Remove deprecated Cerebras Qwen 3 235B model
2026-05-27 11:38:26 -05:00
Jack f4f210986c fix opencode go MiMo pricing conflict resolution 2026-05-28 00:36:48 +08:00
Jack f4206f4eaa Merge branch 'dev' into update/opencode-go-mimo-v2-5-pricing 2026-05-28 00:34:02 +08:00
Seb Duerr 52e5b67bc4 Remove deprecated Cerebras Qwen 3 235B model 2026-05-27 09:13:50 -07:00
Jack d11b0e448c update opencode go MiMo V2.5 pricing 2026-05-27 23:54:58 +08:00
github-actions[bot] 591745690e chore(sync): update OpenRouter model catalog 2026-05-27 15:28:06 +00:00
Codex 5a4bc9b383 Add selected NovitaAI models 2026-05-27 21:30:38 +08:00
Tarik a14171bcd4 Update mistral-small.toml
the only difference is the price so I removed the other fields
2026-05-27 14:00:33 +01:00
oskar 0741c5a53c chore: update kimi cache rate 2026-05-27 13:09:20 +07:00
oskar 7a1ec8737b chore: update groq cache pricing 2026-05-27 13:05:24 +07:00
Aiden Cline 7c37c92c2d fix Xiaomi Token Plan model catalog 2026-05-27 00:39:17 -05:00
Aiden Cline ec4ec6d441 Merge pull request #1867 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-05-27 00:00:17 -05:00
Aiden Cline d96da5ece6 Merge pull request #1868 from Ardakilic/chore/sync-kilo-models-20260527-1
Sync Kilo models with upstream gateway
2026-05-26 23:59:26 -05:00
github-actions[bot] 0342c79d03 chore(sync): update OpenRouter model catalog 2026-05-27 03:26:29 +00:00
Arda Kilicdagi 37136fc2f3 chore: sync upstream kilo api gateway models 2026-05-27 02:27:53 +04:00
Tarik 131eca9c5e Update Mistral Small model configuration
use [extends] syntax
2026-05-26 20:44:22 +01:00
Tarik 3e38d46c4c Update Mistral Small model details in TOML file
The details on helicone website are false,

accurate details are pulled from deepinfra website

https://www.helicone.ai/model/mistral-small

https://deepinfra.com/mistralai/Mistral-Small-3.2-24B-Instruct-2506
2026-05-26 19:34:07 +01:00
Aiden Cline 989939773b Merge pull request #1863 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-05-26 13:04:26 -05:00
Frank 4f1d5c511a update go models 2026-05-26 13:54:19 -04:00
github-actions[bot] 34a21e07f2 chore(sync): update OpenRouter model catalog 2026-05-26 17:26:26 +00:00
Aiden Cline 979f5da0ca Merge pull request #1864 from oskarkocol/update/openai-cache-rates
chore: update openai cache rates
2026-05-26 12:06:15 -05:00
oskar 73b357e2ab update cache rates 2026-05-26 23:28:11 +07:00
Aiden Cline 97c71f1663 Merge pull request #1862 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-05-26 09:11:54 -05:00
github-actions[bot] 59c270bc85 chore(sync): update OpenRouter model catalog 2026-05-26 13:23:20 +00:00
Aiden Cline a4c18f88ed Merge pull request #1860 from bas3line/sync-routing-run-models-2
Sync routing.run model catalog
2026-05-25 23:44:24 -05:00
bas3line 3343a585ac fix(routing-run): sync model catalog 2026-05-26 09:51:14 +05:30
Aiden Cline f23db95550 Merge pull request #1858 from smakosh/fix/llmgateway-qwen3.7-max-id
fix(llmgateway): correct Qwen3.7 Max model id to qwen3.7-max
2026-05-25 17:22:56 -05:00
Aiden Cline 556d9a9045 Merge pull request #1859 from Suat-B/update-xpersona-frieren-coder-limits
Update Xpersona Frieren Coder limits
2026-05-25 17:22:46 -05:00
Frank 49991c8f8f update zen models 2026-05-25 17:56:52 -04:00
Suat-B 20c1e810ce Update Xpersona Frieren Coder limits 2026-05-25 13:23:59 -05:00
smakosh 15d08b4540 fix(llmgateway): correct Qwen3.7 Max model id to qwen3.7-max
Rename qwen37-max.toml to qwen3.7-max.toml so the model id matches
the canonical alibaba/qwen3.7-max definition (name: Qwen3.7 Max).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-25 18:48:12 +01:00
Aiden Cline 14bbc303e5 Merge pull request #1852 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-05-25 09:49:26 -05:00
Aiden Cline 02da63ed48 Merge pull request #1853 from dpuyosa/chore/venice-pricing
Venice: Update pricing and limits for 4 models
2026-05-25 09:49:09 -05:00
github-actions[bot] 07daef8c54 chore(sync): update OpenRouter model catalog 2026-05-25 13:27:22 +00:00
dpuyosa b6ebe8696c [venice] Update pricing, limits, and last_updated for 4 models
- Reduce input/output/cache prices for gemini-3-5-flash, google-gemma-4-31b-it, and qwen-3-7-max
- Lower max output tokens from 65,536 to 16,384 for qwen3-5-35b-a3b
- Bump last_updated to 2026-05-25 for all 4 models
2026-05-25 10:07:32 +02:00
Aiden Cline ad654e71da Merge pull request #1850 from huxeon/dev
fix: modify the deepseek v4 flash/pro price
2026-05-25 00:18:18 -05:00
Aiden Cline 508f4d48e1 Merge pull request #1847 from ceyhanmolla/poolside/laguna-direct
Add Poolside provider with Laguna M.1 and XS.2 models
2026-05-24 23:26:34 -05:00
opencode-agent[bot] cd7c70b4fe revert: remove opencode-go deepseek-v4-pro price changes
Keep only the deepseek provider price updates as intended.
2026-05-25 04:26:14 +00:00
Aiden Cline 10e752ea84 Merge pull request #1845 from yukoba/vultr
Update Vultr models
2026-05-24 23:26:12 -05:00
huxeon 4cdb4c700b fix: modify the deepseek v4 flash/pro price in provider deepseek and opencode-go 2026-05-24 13:33:56 +08:00
Aiden Cline d497a446eb Merge pull request #1849 from technoabsurdist/add-wafer-ai-qwen3.6-35b-a3b-and-kimi-k2.6
providers/wafer.ai: add Qwen3.6-35B-A3B and Kimi-K2.6
2026-05-23 16:41:24 -05:00
Emilio Andere 745cf557b3 feat(wafer.ai): add Qwen3.6-35B-A3B and Kimi-K2.6
Both models are public serverless on pass.wafer.ai/v1/models but were
missing from the wafer.ai provider in models.dev, so OpenCode and other
tools that pull from the registry could not discover them.

- Qwen3.6 35B A3B: compact MoE, 32K context, vision-capable, $0.19/M in,
  $1.25/M out (NVFP4 on AMD MI355X — see wafer.ai/blog/qwen36-mi355x).
- Kimi K2.6: 1T sparse MoE, 262K context, vision-capable, $1.10/M in,
  $4.80/M out (NVFP4 on Blackwell — see wafer.ai/blog/kimi-k26-nvfp4).

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-23 13:26:18 -04:00
Yu Kobayashi db295d6842 Refactor to use the extends syntax 2026-05-24 01:20:31 +09:00
ceyhanmolla 47c0eed41e Add Poolside provider with Laguna M.1 and XS.2 models 2026-05-23 17:09:33 +02:00
Yu Kobayashi e690980857 Update Vultr models 2026-05-23 16:25:11 +09:00
Aiden Cline f5f7d1a167 Merge pull request #1840 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-05-22 16:58:23 -05:00
Aiden Cline cfbbb55c4d Merge pull request #1839 from anthraxx/alibaba-qwen3.7-plus
Alibaba: Add Qwen 3.7 Max and 3.6 Flash to all regions and plans
2026-05-22 16:58:08 -05:00
github-actions[bot] 1956762cdf chore(sync): update OpenRouter model catalog 2026-05-22 21:41:35 +00:00
Levente Polyak 28571433f7 feat(alibaba): add Qwen3.7 Max model configuration to all regions
Link: https://bailian.console.alibabacloud.com/cn-beijing?tab=model#/model-market/detail/qwen3.7-max?serviceSite=asia-pacific-china
2026-05-22 19:00:29 +02:00
Levente Polyak aef5e48bae feat(alibaba): add Qwen3.6 Flash model configuration to all regions
Link: https://bailian.console.alibabacloud.com/cn-beijing?tab=model#/model-market/detail/qwen3.6-flash?serviceSite=asia-pacific-china
2026-05-22 18:54:22 +02:00
Aiden Cline 8ba19639a7 Merge pull request #1825 from shzdehmd/dev
update(fireworks): sync models and pricing with current offerings
2026-05-22 11:45:45 -05:00
Aiden Cline 0f9b4c9edc Merge pull request #1834 from monotykamary/chore/update-neuralwatt-qwen3.6-pricing
fix(neuralwatt): update Qwen3.6 pricing to match API
2026-05-22 09:13:02 -05:00
Aiden Cline 2a9b6256dc Merge pull request #1836 from PierreLeGuen/nearai-provider
Add current NEAR AI Cloud models
2026-05-22 09:12:36 -05:00
Aiden Cline 51633fe106 Merge pull request #1838 from Quentinchampenois/fix/update-models-scaleway
fix: update Scaleway provider models list
2026-05-22 09:12:26 -05:00
Aiden Cline 169b5c4331 Merge pull request #1833 from NicoAvanzDev/add-copilot-gemini-3-5-flash
[GitHub Copilot] add Gemini 3.5 Flash
2026-05-22 09:09:25 -05:00
Aiden Cline 9d0f0d6d56 Merge pull request #1837 from fydrah/fix/google-vertex-gemini-3.5-flash
fix: missing google-vertex gemini 3.5 flash extend
2026-05-22 09:07:34 -05:00
Aiden Cline 1d2af0c97b Merge pull request #1835 from dpuyosa/feat/venice-models
Venice: Add Gemini 3.5 Flash and Qwen 3.7 Max, update Grok Build 0.1 pricing
2026-05-22 09:07:03 -05:00
Aiden Cline cc14ae4370 Merge pull request #1832 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-05-22 09:06:16 -05:00
github-actions[bot] ad9a3448d2 chore(sync): update OpenRouter model catalog 2026-05-22 14:03:32 +00:00
Quentin Champenois c6f9cf58e4 fix(scaleway): add new models gemma-4-26b-a4b-it and qwen3.6-35b-a3b 2026-05-22 15:43:11 +02:00
Quentin Champenois bba5809471 fix(scaleway): Extends existing models 2026-05-22 15:42:36 +02:00
Quentin Champenois c0852f1b4f fix(scaleway): Clear removed models from list 2026-05-22 15:11:44 +02:00
Flavien Hardy 0fc3a3f635 fix: missing google-vertex gemini 3.5 flash extend 2026-05-22 08:56:44 -04:00
Pierre LE GUEN 68936dc062 Add current NEAR AI Cloud models 2026-05-22 09:27:57 +00:00
dpuyosa ade9760060 [venice] Add Gemini 3.5 Flash and Qwen 3.7 Max, update Grok Build 0.1 pricing
- Add Gemini 3.5 Flash model (1M context, multimodal input)
- Add Qwen 3.7 Max model (1M context, text-only)
- Update Grok Build 0.1 cost tiers and pricing
2026-05-22 10:57:38 +02:00
Tom X Nguyen 2a8b90b197 fix(neuralwatt): update Qwen3.6 pricing to match API
Updates the per-token cost for Qwen3.6-35B-A3B and qwen3.6-35b-fast from /bin/bash.05//bin/bash.10 to /bin/bash.29/.15 (input/output per million tokens), matching the actual Neuralwatt API pricing as reflected in pi-neuralwatt-provider commit f634286.
2026-05-22 15:19:51 +07:00
NicoAvanzDev 8569f0dfef [GitHub Copilot] add Gemini 3.5 Flash 2026-05-22 07:57:10 +00:00
Aiden Cline fc98ceb72e fix sync workflow force lease 2026-05-21 23:52:34 -05:00
Aiden Cline be7c5afc94 Merge pull request #1831 from anomalyco/fix-vertex-sonnet-4-6-limits
Fix Vertex Sonnet 4.6 token limits
2026-05-21 23:38:18 -05:00
Aiden Cline 57e62c43b0 fix vertex sonnet 4.6 limits 2026-05-21 23:37:30 -05:00
Aiden Cline 0898c35c9f Merge pull request #1830 from zainhas/dev
[Together AI] add Qwen3.7 max
2026-05-21 21:00:51 -05:00
Zain Hasan 46b23fb313 Merge branch 'anomalyco:dev' into dev 2026-05-21 17:47:35 -07:00
Zain Hasan 05fedc76cc [Together AI] add Qwen3.7 2026-05-21 17:47:19 -07:00
Aiden Cline 2738f81d1a Merge pull request #1828 from anomalyco/refactor/sync-core-layout
refactor: move sync implementation into core src
2026-05-21 18:10:09 -05:00
Aiden Cline 89b834086a refactor: move sync implementation into core src 2026-05-21 18:06:25 -05:00
Aiden Cline 1ab2ff8163 Merge pull request #1826 from smakosh/add-llmgateway-models
feat: add new LLM Gateway text models
2026-05-21 17:58:29 -05:00
Frank 9468676683 update zen models 2026-05-21 18:42:36 -04:00
Claude 6cdd2f054b Merge upstream/dev into add-llmgateway-models; resolve gemini-3.5-flash conflict
# Conflicts:
#	providers/google/models/gemini-3.5-flash.toml
2026-05-21 21:48:48 +00:00
Aiden Cline b13abc9141 Merge pull request #1827 from anomalyco/update-xai-pricing
fix xAI long-context pricing
2026-05-21 16:45:43 -05:00
Aiden Cline e5ba264751 fix xAI long-context pricing 2026-05-21 16:41:36 -05:00
smakosh a7811fb522 refactor: use extends for gemini and qwen models
Add canonical google/gemini-3.5-flash and alibaba/qwen3.7-max defs and
have the llmgateway entries extend them, per PR review.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-21 23:38:57 +02:00
smakosh 605fae75d9 feat: add new LLM Gateway text models
Add Grok 4.20 (reasoning/non-reasoning), Gemini 3.5 Flash, and Qwen3.7 Max to the llmgateway provider.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-21 23:04:47 +02:00
Ahmad Shahzad bcab0885bc update(fireworks): sync models and pricing with current offerings
Removed — 11 deprecated models:
- deepseek-v3p1
- deepseek-v3p2
- glm-4p5
- glm-4p5-air
- glm-4p7
- glm-5
- kimi-k2-instruct
- kimi-k2-thinking
- minimax-m2p1
- routers/kimi-k2p5-turbo

Added — 2 new Turbo (routers) models:
- routers/glm-5p1-fast
- routers/kimi-k2p6-turbo

Modified — pricing fixes:
- deepseek-v4-pro: cache_read 0.15 → 0.145
- gpt-oss-120b: added cache_read = 0.015
- gpt-oss-20b: input 0.05 → 0.07, output 0.20 → 0.30, added cache_read = 0.035
- minimax-m2p7: cache_read 0.03 → 0.06
2026-05-22 01:55:31 +05:00
Aiden Cline 26b05268ae Merge pull request #1824 from anomalyco/fix/vercel-gemini-35-flash
Add new Vercel AI Gateway models
2026-05-21 15:30:35 -05:00
Aiden Cline 1aee13d2e5 Add new Vercel AI Gateway models 2026-05-21 13:21:25 -05:00
Aiden Cline 0a924e6bb2 Merge pull request #1822 from anomalyco/automation/sync-models-xai
chore(sync): update xAI model catalog
2026-05-21 13:05:20 -05:00
Aiden Cline 9769b2b11d Merge pull request #1823 from anomalyco/automation/sync-models-openrouter
chore(sync): update OpenRouter model catalog
2026-05-21 13:05:13 -05:00
github-actions[bot] 1b0db099cf chore(sync): update OpenRouter model catalog 2026-05-21 17:56:13 +00:00
github-actions[bot] 16ed78587c chore(sync): update xAI model catalog 2026-05-21 17:56:11 +00:00
Frank 0b88965165 update zen models 2026-05-21 13:41:55 -04:00
Aiden Cline acc704ce39 Merge pull request #1797 from arnavchachra/add-crof-provider
add crof.ai provider with 21 models
2026-05-21 11:43:02 -05:00
Aiden Cline 51ad3b264e Merge pull request #1821 from anomalyco/sync-provider-ci
chore: automate provider sync jobs
2026-05-21 11:23:49 -05:00
Aiden Cline 146b6c7084 Merge pull request #1819 from Inceptron-Software/add_inceptron_provider
Add Inceptron provider
2026-05-21 11:21:27 -05:00
Aiden Cline 0e3cbe3c64 chore: automate provider sync jobs 2026-05-21 11:21:12 -05:00
Aiden Cline 604d4d66a4 Merge pull request #1820 from Suat-B/codex/xpersona-image-input-20260521
Add image input modality to Xpersona model
2026-05-21 11:00:49 -05:00
SuatB f5090028b8 Add image input modality to Xpersona model 2026-05-21 09:46:28 -05:00
Frank 4bad8faf29 update zen models 2026-05-21 09:05:13 -04:00
Oskar Gustafsson 0df2ccf586 Add Inceptron provider 2026-05-21 09:24:43 +02:00
Aiden Cline bafdc00b45 Merge pull request #1812 from anomalyco/openrouter-extends-sync
Sync OpenRouter models with extends
2026-05-20 21:07:21 -05:00
Aiden Cline 49840c013b Merge pull request #1814 from neonn0d/feat/stepfun-ai
feat(stepfun-ai): add international StepFun platform
2026-05-20 20:58:37 -05:00
Aiden Cline eccae0b54e sync openrouter models with extends 2026-05-20 20:32:11 -05:00
Aiden Cline 4cca29405f Merge pull request #1817 from dpuyosa/dev
Venice: Remove Grok 4.1 Fast and add Grok Build 0.1
2026-05-20 20:26:45 -05:00
Aiden Cline e40d9dd338 Merge pull request #1818 from anomalyco/cloudflare-sync-env
chore(sync): isolate cloudflare credentials
2026-05-20 20:26:22 -05:00
Aiden Cline 6a74991397 chore(sync): isolate cloudflare credentials 2026-05-20 20:19:47 -05:00
dpuyosa 035999cb58 [venice] Replace Grok 4.1 Fast with Grok Build 0.1
- Remove deprecated grok-41-fast model entry
- Add grok-build-0-1 with 200K token tiered pricing
- Update context to 256K and output limit to 65,536
2026-05-21 02:36:19 +02:00
Frank cec56bf1bc update zen models 2026-05-20 19:43:25 -04:00
Aiden Cline 85f0cdcb2f Merge pull request #1816 from anomalyco/xai-sync
Add PDF input modality to Grok models
2026-05-20 18:12:47 -05:00
Aiden Cline ef80d4df4e Infer PDF modality for xAI image models 2026-05-20 18:12:11 -05:00
Aiden Cline af0ef00109 Update xAI Grok PDF modalities 2026-05-20 18:06:33 -05:00
Aiden Cline 5fdcea6b36 Merge pull request #1815 from anomalyco/cloudflare-ai-gateway
chore(sync): add cloudflare workers ai sync
2026-05-20 18:02:28 -05:00
Aiden Cline 31e56480b4 chore(sync): add cloudflare workers ai sync 2026-05-20 16:55:29 -05:00
Aiden Cline 92a621594e Merge pull request #1813 from anomalyco/sync-xai
chore(sync): add xai model sync
2026-05-20 16:02:38 -05:00
Aiden Cline d2db353ceb chore: ignore sync reports 2026-05-20 16:01:51 -05:00
Aiden Cline 900ae509d2 Merge pull request #1808 from ajussak/scaleway
Added Mistral Medium 3.5 128B from Scaleway
2026-05-20 15:58:00 -05:00
neo 9d60164243 feat(stepfun-ai): add international StepFun platform
StepFun runs two separate platforms with distinct accounts/keys:
platform.stepfun.com (China, already covered by providers/stepfun) and
platform.stepfun.ai (international). Keys are not interchangeable
across the two — .ai keys are rejected by api.stepfun.com as
invalid_api_key.

Stepfun's own opencode integration guide instructs users to point at
https://api.stepfun.ai/step_plan/v1. This adds providers/stepfun-ai
for that endpoint, symlinking the shared chat models. Follows the
moonshotai / moonshotai-cn pattern.
2026-05-20 20:43:47 +02:00
Adrien Jussak cd3e99025f Update Mistral Medium 3.5 128B model configuration to extend from mistral-medium-2604 and adjust context window size. 2026-05-20 20:43:45 +02:00
Aiden Cline 1098981eb6 chore(sync): add xai model sync 2026-05-20 13:23:02 -05:00
Aiden Cline 27a151cf53 Merge pull request #1811 from anomalyco/xai-grok-build-model
Add xAI Grok Build model
2026-05-20 13:05:06 -05:00
Aiden Cline 41ff42ab7f Merge pull request #1810 from fhennerkes/dev
poe: add Gemini-3.5-Flash model
2026-05-20 13:04:47 -05:00
Aiden Cline adf1cbdecd add xai grok build model 2026-05-20 13:04:13 -05:00
Frank 10ddc78ce0 update zen models 2026-05-20 14:02:01 -04:00
fhennerkes 7ae897e440 poe: add Gemini-3.5-Flash model
Add new Google model from Poe API (released 2026-05-19).
Uses extends format inheriting from google/gemini-3.5-flash with
Poe-specific overrides (name format, no temperature, markup pricing,
limited input modalities).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-20 10:52:15 -07:00
Aiden Cline 02e452c2e8 Merge pull request #1805 from anomalyco/sync-google
sync google models
2026-05-20 10:53:57 -05:00
Aiden Cline f05b63fff5 Merge pull request #1807 from anomalyco/automation/sync-models-aggregators
chore(sync): update aggregator model catalogs
2026-05-20 10:34:30 -05:00
Adrien Jussak e277d60236 Add Mistral Medium 3.5 128B to Scaleway 2026-05-20 16:14:37 +02:00
github-actions[bot] b01277a737 chore(sync): update aggregator model catalogs 2026-05-20 09:25:37 +00:00
Frank a5da5aa429 update zen models 2026-05-20 04:14:28 -04:00
Aiden Cline 5ceac8a58b updates 2026-05-19 23:43:01 -05:00
Aiden Cline 11e1d5623a Merge pull request #1806 from Cahl-Dee/grid-model-updates-2026-05
Grid model updates 2026-05
2026-05-19 23:42:26 -05:00
Aiden Cline f107afc57c sync 2026-05-19 22:56:50 -05:00
Carl DiClementi e789d7c1f2 Merge branch 'anomalyco:dev' into grid-model-updates-2026-05 2026-05-19 16:06:23 -05:00
Cahl-Dee 899668ad49 added new code and agent models and updated existing text models 2026-05-19 16:04:58 -05:00
Aiden Cline 8c677f0134 sync google models 2026-05-19 15:58:06 -05:00
Aiden Cline 462c7877d9 add gemini 3.5 flash 2026-05-19 15:43:38 -05:00
Aiden Cline 55871f9dca Merge pull request #1804 from Adanlink/dev
feat: add deepseek-v4-flash to the fireworks-ai provider
2026-05-19 15:29:33 -05:00
Aiden Cline 4f7194a3c8 test 2026-05-19 15:09:11 -05:00
Aiden Cline f65f0148da add sync guide 2026-05-19 15:08:44 -05:00
Adán 14952f8855 Rename deepseek-v4-flash to deepseek-v4-flash.toml 2026-05-19 18:56:43 +02:00
Adán d7c6d3ad12 Add deepseek-v4-flash model configuration 2026-05-19 18:53:48 +02:00
Aiden Cline 356bc79d08 Merge pull request #1637 from elvexai/fix/amazon-bedrock-kimi-token-limits
fix: Token limits for Amazon Bedrock Kimi K2 models
2026-05-19 09:42:30 -05:00
Aiden Cline a89b1ed726 Merge pull request #1801 from bas3line/sync-routing-run-models
Sync routing.run model catalog
2026-05-19 09:41:38 -05:00
bas3line a998576773 fix(routing-run): match live model metadata 2026-05-19 10:38:58 +05:30
bas3line fbe842bbea fix(routing-run): expose reasoning metadata 2026-05-19 08:39:51 +05:30
bas3line 6c0c3d1b10 fix(routing-run): sync model catalog 2026-05-19 07:37:53 +05:30
Aiden Cline db0a7cf611 Merge pull request #1798 from anomalyco/rework-sync-logic
sync: centralize aggregator model updates
2026-05-18 20:12:50 -05:00
Aiden Cline d775e37e3b Merge pull request #1800 from jerome-benoit/feat/sap-ai-core-gpt-5.4
feat(sap-ai-core): add GPT-5.4
2026-05-18 20:12:21 -05:00
Jérôme Benoit 36753063d9 feat(sap-ai-core): add GPT-5.4
Add gpt-5.4 with availability date from official SAP source.

Drop [[cost.tiers]] from gemini-2.5-pro pending SAP-side tiered
pricing confirmation; sap-ai-core now declares no per-model tiers
(SAP Note 3437766 is login-gated and authoritative for capacity
unit conversion rates).
2026-05-19 02:58:29 +02:00
Aiden Cline 5ee955297a sync: drop vercel catalog updates 2026-05-18 19:07:14 -05:00
Aiden Cline 1b77511903 Merge pull request #1799 from vglafirov/add-gitlab-gpt-5-5
feat(gitlab): add Agentic Chat (GPT-5.5) model
2026-05-18 15:24:18 -05:00
Aiden Cline 8896ead7bf sync: fix vercel pricing tiers 2026-05-18 14:52:40 -05:00
Vladimir Glafirov eb96594d47 feat(gitlab): add Agentic Chat (GPT-5.5) model
Adds duo-chat-gpt-5-5 to the GitLab provider. The GitLab AI Gateway
proxies this model to OpenAI's gpt-5.5-2026-04-23 backend with a
1.05M token context window (922k input + 128k output).

Source: gitlab-org/modelops/applied-ml/code-suggestions/ai-assist
models.yml (gpt_5_5 entry with proxy_provider: openai).

The gitlab-ai-provider npm package exposes this model id starting in
v6.7.0.
2026-05-18 20:44:34 +02:00
Aiden Cline 327332efe3 Merge pull request #1794 from bas3line/add-routing-run-provider
Add routing.run provider
2026-05-18 12:32:34 -05:00
Aiden Cline 5020951745 sync: refresh openrouter after dev merge 2026-05-18 12:30:29 -05:00
Aiden Cline cb6f97774e Merge remote-tracking branch 'origin/dev' into rework-sync-logic 2026-05-18 12:29:28 -05:00
Aiden Cline 7f8b493b0c Merge pull request #1795 from delafthi/delafthi/lxxqxzktnozv
fix(providers/novita-ai): use lowercase model names
2026-05-18 12:28:32 -05:00
Aiden Cline d65a862533 sync: centralize aggregator model updates 2026-05-18 12:12:15 -05:00
arnavchachra 9420048dfe fix crof model limits and reasoning flag to match Crof API 2026-05-18 21:51:19 +05:30
arnavchachra 8db6c27634 add crof provider with 21 models 2026-05-18 21:40:11 +05:30
Victor Navarro 8e710e19ea bring back old bick-pickle
Added interleaved section with reasoning_content field and removed provider section.
2026-05-18 11:44:14 +02:00
Frank 36c6896e97 update zen models 2026-05-17 22:58:06 -04:00
Aiden Cline a8be548a5d Merge pull request #1416 from Luew2/add-lilac-provider
Add Lilac provider
2026-05-17 19:23:07 -05:00
Luew2 8c2fae4ab0 Keep exact Lilac Gemma model name 2026-05-17 17:19:53 -07:00
Luew2 5e7fad350d Align Lilac Gemma display name 2026-05-17 17:19:04 -07:00
Luew2 feb85ef2c9 Align Lilac provider with registry conventions 2026-05-17 17:15:40 -07:00
Luew2 d4161ebf24 Follow models.dev conventions for Lilac provider 2026-05-17 17:11:03 -07:00
Luew2 b91ab02e2b Add Lilac MiniMax M2.7 model 2026-05-17 17:07:44 -07:00
Luew2 dd09d07f75 Update Lilac Kimi model to K2.6 2026-05-17 17:07:44 -07:00
Luew2 4515f85d47 Add Lilac cache pricing 2026-05-17 17:07:44 -07:00
Luew2 97572240e1 Add Gemma 4 31B IT model
Adds google/gemma-4-31b-it to the Lilac provider ($0.11/M input,
$0.35/M output, 262K context, native multimodal with image/video).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-17 17:07:44 -07:00
Luew2 80cc04e9e5 Fix Kimi K2.5 output limit to 262,144 tokens 2026-05-17 17:07:44 -07:00
Luew2 d532ebb89b Use purple gradient for Lilac logo (brand colors #6451dc → #b6a6f9) 2026-05-17 17:07:44 -07:00
Luew2 9bae3e887f Replace placeholder logo with Lilac icon mark (currentColor) 2026-05-17 17:07:44 -07:00
Luew2 0be69bf872 Add Lilac provider
Add Lilac as an OpenAI-compatible provider serving:
- z-ai/glm-5.1: Z.ai's flagship agentic model (754B MoE, 202.8K context)
- moonshotai/kimi-k2.5: Moonshot AI's multimodal reasoning model (1T MoE, 262K context)

API: https://api.getlilac.com/v1
Docs: https://docs.getlilac.com
2026-05-17 17:07:44 -07:00
Thierry Delafontaine 0ed38cbecf fix(providers/novita-ai): use lowercase model names
Mixed case naming causes conflicts on case-insensitive filesystems like macOS.
2026-05-17 21:17:46 +02:00
bas3line e65703382a feat: add routing.run provider 2026-05-17 20:27:56 +05:30
Aiden Cline 748754c99b Merge pull request #1792 from monotykamary/fix/neuralwatt-context-limits
fix(neuralwatt): sync context window and output limits with upstream API
2026-05-16 13:14:05 -05:00
Tom X Nguyen ec9c12d0fc fix(neuralwatt): sync context window and output limits with upstream API
Updates all 14 neuralwatt model TOML files with corrected context window
and max output token values as reported by the Neuralwatt API:

- Devstral-Small-2-24B-Instruct-2512: 262,144 -> 262,128
- GLM-5/GLM-5.1 variants: 200,000 -> 202,736
- GPT-OSS-20B: 16,384 -> 16,368
- Kimi-K2.5/K2.6 variants: 262,144 -> 262,128
- MiniMax-M2.5: 196,608 -> 196,592
- Qwen3.5-397B variants: 262,144 -> 262,128
- Qwen3.6-35B variants: 131,072 -> 131,056

Also fixes the README: moves kimi-k2.6-fast from 'Reasoning Models' to
'Fast Variants' and removes incorrect claim that fast variants support
reasoning.
2026-05-16 23:16:34 +07:00
Aiden Cline ac81822c89 Merge pull request #1777 from berget-ai/feat/berget-kimi-k2.6
feat: add Kimi K2.6 to berget.ai
2026-05-16 06:09:00 -05:00
Aiden Cline d32ed764bd Merge pull request #1791 from anomalyco/automation/sync-openrouter-models
Sync OpenRouter models
2026-05-16 06:08:09 -05:00
Christian Landgren 45fb951c42 feat: add Kimi K2.6 to berget.ai
Add Moonshot AI Kimi K2.6 model to berget.ai provider catalog.

- 262K context window
- 16K output tokens
- Text input/output
- Supports: reasoning, structured output, tool calling
- Pricing: /bin/zsh.83/M input, .85/M output (EUR-based)
- Open weights
2026-05-16 12:46:35 +02:00
github-actions[bot] 260d79b2d5 Sync OpenRouter models 2026-05-16 08:54:41 +00:00
Aiden Cline 746b9caf79 Merge pull request #1785 from jerome-benoit/feat/sap-ai-core-opus-4-7
feat(sap-ai-core): add Claude Opus 4.7 and sync model specs
2026-05-15 23:24:47 -05:00
Aiden Cline 8362b55503 Merge pull request #1786 from Ardakilic/chore/kilo-sync-20260516
providers(kilo): sync upstream
2026-05-15 23:24:34 -05:00
Aiden Cline dde3953a9f Merge pull request #1787 from Suat-B/codex/xpersona-www-api-url
Fix Xpersona API base URL
2026-05-15 23:24:06 -05:00
Aiden Cline 0a1695212c Merge pull request #1788 from Jaaneek/xai-may-15-2026-retirement
xai: drop models retired May 15, 2026 + add Grok Imagine models
2026-05-15 23:23:52 -05:00
Jaaneek 89fbb6bb69 xai: drop models retired May 15, 2026 + add Grok Imagine models 2026-05-16 01:57:15 +01:00
SuatB 005fe0fb5a Fix Xpersona provider API URL 2026-05-15 18:37:41 -05:00
Frank e283875ce7 update zen models 2026-05-15 17:24:53 -04:00
Arda Kilicdagi 3598019251 providers(kilo): sync upstream 2026-05-16 01:11:25 +04:00
Jérôme Benoit e9ad8b0a3f feat(sap-ai-core): add Claude Opus 4.7 and sync model specs 2026-05-15 22:16:07 +02:00
Aiden Cline 0ee78eeda5 sync: openrouter models 2026-05-15 10:20:36 -05:00
Aiden Cline 0a5b33e518 Merge pull request #1778 from zhenjunchen-png/add-orcarouter
feat: add OrcaRouter as a new provider
2026-05-15 10:16:29 -05:00
Aiden Cline 22416dda64 Merge pull request #1783 from anomalyco/sync-openrouter
add sync script for openrouter, sync openrouter models
2026-05-15 10:12:02 -05:00
Aiden Cline eba2702e3a fix: families 2026-05-15 10:03:39 -05:00
Aiden Cline c2c5cc8f21 add sync script for openrouter, sync openrouter models 2026-05-15 10:00:32 -05:00
zhenjun.chen 022b1b9946 feat(orcarouter): expand to 80 chat models and add brand logo
Adds 55 additional upstream-mirrored models alongside the existing 25,
covering the full OrcaRouter chat catalog as exposed by
https://www.orcarouter.ai/api/pricing (text-only chat — TTS, embeddings,
video, and image generation are filtered out).

Per-namespace upstream mappings used by [extends]:

  OrcaRouter ns  -> models.dev provider
  ---------------- + ---------------
  openai         -> openai
  anthropic      -> anthropic   (dot version -> dash, e.g. opus-4.7 -> opus-4-7)
  google         -> google
  deepseek       -> deepseek
  qwen           -> alibaba
  grok           -> xai
  kimi           -> moonshotai
  minimax        -> minimax     (minimax-m2.7 -> MiniMax-M2.7)
  z-ai           -> zai

OrcaRouter-specific aliases (dated snapshots like gpt-5-2025-08-07,
search-preview variants, qwen3-vl-* visual variants) are excluded from
v1 because their upstream canonical files do not yet exist in models.dev.

Also adds providers/orcarouter/logo.svg.
2026-05-15 14:48:31 +08:00
Aiden Cline 8269e04222 Merge pull request #1782 from Suat-B/codex/xpersona-limits-logo
Update Xpersona limits, cutoff, and logo
2026-05-15 00:29:32 -05:00
Aiden Cline a75cf2ed1c Merge pull request #1552 from aredridel/as/add-umans
feat(models): add umans.ai coding plan
2026-05-14 22:40:39 -05:00
Aria Stewart 7b00aafa79 feat(models): umans.ai definitions 2026-05-14 23:39:30 -04:00
Suat-B e54e0fc8b5 Update Xpersona limits, cutoff, and logo 2026-05-15 03:22:16 +00:00
Aiden Cline 38611e75fa Merge pull request #1781 from dpuyosa/feat/add-venice-claude-opus-4-7-fast-model
Venice: Add Claude Opus 4.7 Fast model
2026-05-14 22:08:14 -05:00
dpuyosa e62c1e973e [venice] Add Claude Opus 4.7 Fast model
- New pricing with 36/180 input/output per million tokens
- 1M context window with 128K output limit
- Text+image input, text-only output
2026-05-15 01:32:24 +02:00
Aiden Cline c2b3c601e4 Merge pull request #1724 from isaachuangGMICLOUD/feat/add-gmicloud-provider
providers(gmicloud): add GMI Cloud provider
2026-05-14 17:26:50 -05:00
Aiden Cline 9ff1d36a21 Merge pull request #1476 from Vect0rM/feat/add-atomic-chat-provider
feat: add Atomic Chat provider
2026-05-14 17:18:21 -05:00
Aiden Cline e0f4042ad1 Merge pull request #1776 from kapelame/docs/minimax-token-plan-rename
providers(minimax): rename Coding Plan → Token Plan in display labels
2026-05-14 17:16:28 -05:00
Frank 14736ba4b6 update zen models 2026-05-14 17:15:53 -04:00
Aiden Cline 9351d68731 Merge pull request #1772 from nearai/add-nearai
Add NEAR AI Cloud provider
2026-05-14 10:30:28 -05:00
Aiden Cline 7a5a1d2aff Merge pull request #1779 from NameIsHiki/siliconflow-deepseek-v4
feat(siliconflow): add DeepSeek v4 models
2026-05-14 10:29:52 -05:00
zhenjun.chen 699284ce91 chore(orcarouter): drop oversize logo, fall back to models.dev default
The previously committed logo is ~100KB; existing wrapper-provider logos
(openrouter, llmgateway, kilo, aihubmix, ambient) are all 0.3-6KB and use
`currentColor`. Falling back to the default logo per README:

  > If we don't have a provider's logo, a default logo is served instead.

A properly-sized currentColor logo will follow in a separate PR.
2026-05-14 21:37:48 +08:00
Hiki 21ce5c3ac8 Create deepseek-v4-flash.toml 2026-05-14 15:26:37 +02:00
Hiki 3485cf52d0 Create deepseek-v4-pro.toml 2026-05-14 15:22:53 +02:00
Frank 99e8f25c78 update zen models 2026-05-14 08:59:42 -04:00
zhenjun.chen 7102978cb4 feat: add OrcaRouter provider
OrcaRouter is an OpenAI-compatible meta-router aggregating 150+ LLMs
(OpenAI, Anthropic, Google, xAI, DeepSeek, Qwen, Kimi, MiniMax, ...)
behind a single API key, with a virtual orcarouter/auto smart-routing
entry that picks an upstream per request.

This initial scope covers 26 models (1 AUTO router + 25 upstream mirrors
using [extends]). Pricing computed from https://www.orcarouter.ai/api/pricing
on 2026-05-14: input = model_ratio * $2, output = model_ratio *
completion_ratio * $2 (USD per 1M tokens).

Disclosure: I'm an engineer on the OrcaRouter team.
2026-05-14 20:55:47 +08:00
kapelame 530f60c69c providers(minimax): rename Coding Plan → Token Plan in display labels
The product was renamed from "Coding Plan" to "Token Plan" when its
scope expanded beyond coding to cover all MiniMax modalities (text,
speech, video, music, image). Per
https://platform.minimax.io/docs/token-plan/intro:
"Token Plan extends upon our former Coding Plan."

Updates display name and doc URL for the two affected provider
catalog entries. Provider IDs (minimax-coding-plan,
minimax-cn-coding-plan) are intentionally unchanged for backward
compatibility — anyone with these IDs in opencode.json or
elsewhere keeps working. Old /coding-plan/* URLs still 307-redirect
to the new /token-plan/* paths upstream.

Region disambiguation stays as the URL in parens (matching the
existing minimax / minimax-cn naming convention) — no "China" word
added, since the URL already conveys the region cleanly in the
provider picker.
2026-05-14 19:18:03 +08:00
Misha Skvortsov 2415c5be21 fix(atomic-chat): update logo.svg with new design
Replaces the existing logo.svg file with an updated design for the Atomic Chat provider. This change enhances the visual branding of the application.
2026-05-14 10:58:36 +03:00
Aiden Cline 85aba468cd Merge pull request #1767 from Suat-B/codex/xpersona-provider-20260513
Add Xpersona provider
2026-05-13 23:20:20 -05:00
Aiden Cline d1ec1ba777 Merge pull request #1773 from ambient-gregory/dev
feat: add Ambient provider with GLM-5.1 and Kimi K2.6
2026-05-13 19:20:20 -05:00
Gregory 0f94bf16ec fix(ambient): shrink logo display size to match other providers 2026-05-13 19:33:26 -04:00
Aiden Cline 506e8f48a9 Merge pull request #1770 from EriDeLee/dev
chore(aihubmix): sync model catalog
2026-05-13 17:43:30 -05:00
Aiden Cline 3480bc5992 Merge pull request #1775 from michaelnchin/fix/amazon-bedrock-gpt-oss-tokens
fix: Output tokens for Bedrock GPT-OSS models
2026-05-13 17:36:42 -05:00
Michael Chin fde97814ef fix: Output tokens for Bedrock GPT-OSS models 2026-05-13 14:45:17 -07:00
Gregory ff7eddcb70 feat: add Ambient provider with GLM-5.1 and Kimi K2.6
Adds the Ambient inference provider (api.ambient.xyz) with an initial
catalog of GLM-5.1 and Kimi K2.6, plus a generator script that pulls
from /v1/models so pricing and limits stay in sync with the upstream API.

Run `bun run ambient:generate` to refresh model TOMLs.
2026-05-13 11:30:45 -04:00
Evrard-Nil Daillet 5cbab85b8d Add nearai logo.svg from cloud.near.ai favicon 2026-05-13 16:32:08 +02:00
Evrard-Nil Daillet 6f9820de9f Add NEAR AI Cloud provider
Adds nearai as an OpenAI-compatible provider at https://cloud-api.near.ai/v1
serving 33 models. First-party mirrors (anthropic/openai/google) use `extends`;
NEAR-hosted open-weight models (Qwen, GLM-5.1-FP8, gpt-oss, whisper, FLUX) have
full definitions.

Pricing and context limits sourced from cloud-api.near.ai/v1/models.
2026-05-13 16:32:08 +02:00
EriDeLee cdfb429098 chore(aihubmix): sync model catalog 2026-05-13 21:55:32 +08:00
Victor Navarro 1c2546af8a perf: virtualize models table and other improvements 2026-05-13 12:29:27 +02:00
vimtor 2288a1626b trim search index to essential fields and remove dead code 2026-05-13 12:21:52 +02:00
vimtor b3ecfc3d70 improve row scanning 2026-05-13 11:20:42 +02:00
Suat-B 30b3e677fd Add Xpersona provider 2026-05-13 00:39:09 -05:00
Suat-B 3b37eee86e Add Xpersona provider 2026-05-13 00:39:08 -05:00
Suat-B 71f069670e Add Xpersona provider 2026-05-13 00:39:07 -05:00
Aiden Cline f401672689 Merge pull request #1766 from michaelnchin/fix/amazon-bedrock-structured-output-05122026-2
fix: add structured_output=True for more supported Bedrock models
2026-05-12 23:24:39 -05:00
Michael Chin 2a0d86a034 update structured_output for more Bedrock models 2026-05-12 20:52:36 -07:00
Aiden Cline d9439cdf2f Merge pull request #1762 from zxyaction/feat/add-auriko-provider
feat: add Auriko provider with 15 models
2026-05-12 22:16:02 -05:00
Aiden Cline 3d443d568d Merge pull request #1765 from michaelnchin/fix/amazon-bedrock-structured-output-05122026
fix: update structured_output for Bedrock Claude 4.x models
2026-05-12 22:15:51 -05:00
Michael Chin a76c8fe9dd fix: update structured_output for Bedrock Claude 4.x models 2026-05-12 20:07:12 -07:00
Aiden Cline d08e8d6cc1 Merge pull request #1763 from Tavernari/feat/add-claudinio-provider
feat: add Claudinio provider
2026-05-12 19:13:54 -05:00
Victor Carvalho Tavernari 4c06e44047 fix: use currentColor in logo SVG per contributing guidelines 2026-05-12 23:59:03 +01:00
Aiden Cline 5e344ded49 Merge pull request #1755 from anomalyco/correct-context-tracking
feat: add new context pricing tiers
2026-05-12 17:40:48 -05:00
Aiden Cline 458b7f4d1a use Venice context tier thresholds 2026-05-12 17:39:40 -05:00
Aiden Cline baf4432140 Merge pull request #1759 from NameIsHiki/deepinfra-xiaomi-mimo-models
feat(deepinfra): add Xiaomi MiMo v2.5 and v2.5 Pro
2026-05-12 17:10:59 -05:00
Aiden Cline bbf72ea4e0 Merge pull request #1764 from anomalyco/add-anthropic-opus-4-7-fast-mode
Add fast mode for Anthropic Opus 4.7
2026-05-12 17:10:49 -05:00
Aiden Cline 8f9adc7567 fix generated tier change detection 2026-05-12 17:01:35 -05:00
Aiden Cline addaf1c036 add fast mode for anthropic opus 4.7 2026-05-12 17:01:05 -05:00
Victor Carvalho Tavernari 55d16a58b6 feat: add claudinio provider (OpenAI-compatible, 256K ctx, $0.50/$2.00 per MTok) 2026-05-12 22:33:45 +01:00
Hiki 72a4deab66 Update mimo-v2.5.toml 2026-05-12 23:23:53 +02:00
Hiki 8dd829a187 Update mimo-v2.5-pro.toml 2026-05-12 23:23:01 +02:00
Aiden Cline a671cc05d5 align cost tiers with model schema 2026-05-12 16:01:49 -05:00
Aiden Cline 656c6f08a7 Merge pull request #1761 from Sewer56/deprecate-wafer-models
providers/wafer.ai: Remove DeepSeek-V4-Pro and MiniMax-M2.7 models
2026-05-12 15:51:10 -05:00
Aiden Cline 8979741a32 Merge pull request #1760 from Ardakilic/fix/kilo/kimik26
Fix: Kimi k2.6 definition on Kilo Gateway
2026-05-12 15:50:53 -05:00
Frank 82851b9a3d update zen models 2026-05-12 16:44:41 -04:00
zxy_action ae511892d7 feat: add Auriko provider with 15 models
All models use [extends] to inherit from canonical definitions,
overriding only Auriko-specific pricing. Omits remove cost tiers
and features Auriko doesn't carry.

Models: claude-opus-4-{6,7}, claude-sonnet-4-6, deepseek-v4-{pro,flash},
gemini-{2.5-pro,2.5-flash,3.1-pro-preview}, grok-4.3, kimi-k2.{5,6},
minimax-m2-7{,-highspeed}, glm-5.1, qwen-3.6-plus
2026-05-12 13:34:34 -07:00
Sewer56 9312418242 Changed: Remove DSv4 Pro & MiniMax M2.7 from models.dev 2026-05-12 20:16:08 +01:00
vimtor 9828a0177d improve empty row 2026-05-12 19:49:03 +02:00
Arda Kılıçdağı 122627a852 fix: Kimi k2.6 definition on Kilo Gateway 2026-05-12 20:35:58 +03:00
vimtor 4dee8d0d34 minor improvements 2026-05-12 19:10:21 +02:00
Hiki 6883e793ce Create mimo-v2.5-pro.toml 2026-05-12 18:22:41 +02:00
Hiki e69064709b Update mimo-v2.5.toml 2026-05-12 18:19:52 +02:00
Hiki bd8e582b96 Create mimo-v2.5.toml 2026-05-12 18:03:09 +02:00
Shoubhit Dash 21945db90f Merge pull request #1662 from anomalyco/nxl/add-sarvam-provider
provider(sarvam): add chat models
2026-05-12 13:31:59 +05:30
Aiden Cline 1771e02be8 Merge pull request #1660 from Alex-wuhu/feat/novita-ai-sync-models
provider(novita-ai): sync latest models
2026-05-11 23:15:44 -05:00
Aiden Cline bb08fc26e9 Merge pull request #1706 from rohita5l/rohit/addDatabricks
Add Databricks as a provider
2026-05-11 19:28:34 -05:00
Aiden Cline 2e015de42d preserve generated tier thresholds 2026-05-11 17:07:19 -05:00
Rohit Agrawal 914a3d9d18 fix: restore bun.lock to use default registry instead of Databricks npm proxy
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-11 17:54:26 -04:00
Rohit Agrawal bab01dd9ab refactor: move databricks generate to packages/core/script following repo conventions
Addresses review feedback by removing AI SDK dependencies from package.json
and aligning with the Vercel/Helicone/Wandb pattern.

- Move generate-databricks.ts to packages/core/script/
- Add databricks:generate to root scripts
- Remove smoke test and runtime filtering (catalog should reflect what the
  upstream API exposes; AI SDK compatibility is a downstream concern)
- Add --dry-run and --new-only flags
- Merge with existing TOMLs instead of nuking them; warn about orphans
- Restore databricks-gemini-3-pro and databricks-gemini-3-1-pro
- Drop @ai-sdk/openai-compatible, ai, zod from root dependencies

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-11 17:54:04 -04:00
Rohit Agrawal bdaae956af feat: add AI SDK compatibility test to generate script, remove incompatible models
Generate script now smoke-tests each model with streamText after writing TOMLs
and removes any that return empty responses (incompatible with @ai-sdk/openai-compatible).
Removes databricks-gemini-3-pro and databricks-gemini-3-1-pro which return content
as array with thoughtSignature that the AI SDK cannot parse.

Also adds test-databricks.ts for standalone smoke testing.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-11 17:53:44 -04:00
Rohit Agrawal 6f118145c0 fix: inline gpt-oss model metadata instead of invalid extends path
openrouter models in subdirectories can't use extends (schema requires
provider/model format); resolve() now inlines the source TOML content directly.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-11 17:53:44 -04:00
Rohit Agrawal 386eaed119 add databricks 2026-05-11 17:53:44 -04:00
Aiden Cline 151e9c9071 fix tiered cost generation 2026-05-11 16:43:32 -05:00
Isaac ba99f1edce Add GMI Cloud GLM models 2026-05-11 14:40:03 -07:00
Aiden Cline b96b074a3b fix long-context cost tier omissions 2026-05-11 16:31:07 -05:00
Aiden Cline 2593e131a1 wip 2026-05-11 16:11:19 -05:00
Aiden Cline 4aebbe5ca3 Merge pull request #1754 from BruceMacD/brucemacd/fix-ollama-kimi-k2-6-model-id
fix ollama cloud kimi k2.6 model id
2026-05-11 14:57:03 -05:00
Bruce MacDonald b98495e9c8 fix ollama cloud kimi k2.6 model id 2026-05-11 12:40:17 -07:00
Frank bc95b42ccd update zen models 2026-05-11 11:26:08 -04:00
Aiden Cline 6139fb8c69 Merge pull request #1598 from mugnimaestra/feat/chutes-generate-script
feat(chutes): add API-driven model generator script
2026-05-11 09:30:38 -05:00
Aiden Cline 3070758007 Merge pull request #1678 from 5kahoisaac/chore/nvidia-models
Sync NVIDIA endpoint model catalog
2026-05-11 09:29:54 -05:00
Frank 5525e83de4 update zen models 2026-05-11 10:00:09 -04:00
Frank 359fd879b8 update zen models 2026-05-10 03:54:03 -04:00
Frank 01b5a1a656 update zen models 2026-05-10 02:52:44 -04:00
Frank b1958be099 update zen models 2026-05-10 02:42:44 -04:00
Aiden Cline 08aa068523 Temporarily remove kiro provider and models 2026-05-10 01:19:47 -05:00
Aiden Cline f31ad0b02f Merge pull request #1738 from mattiacerutti/chore/remove-gh-copilot-deprecated
chore(copilot): mark deprecated models
2026-05-09 15:42:19 -05:00
Aiden Cline 585aa7fa1b Merge pull request #1741 from EriDeLee/dev
Update aihubmix models
2026-05-09 15:42:03 -05:00
Aiden Cline c42a327b3e Merge pull request #1745 from mads-digitial-solutions/patch-1
Update Google provider docs url from pricing page to models page
2026-05-09 15:41:51 -05:00
mads-digitial-solutions 92ebbfb5c4 Update provider.toml
Update Google provider docs URL from the pricing page to the models page
2026-05-09 19:49:19 +01:00
Aiden Cline 535fe8c971 Merge pull request #1744 from OpeOginni/fix/bedrock-model-ids
chore(bedrock): Getting rid of legacy Amazon Bedrock model offerings
2026-05-09 13:48:52 -05:00
OpeOginni a3b4bfc16c fix(bedrock): remove uneeded model configurations 2026-05-09 20:35:34 +02:00
OpeOginni d0fcd6f11f fix(bedrock): align models with current docs 2026-05-09 20:29:11 +02:00
OpeOginni e55cd54218 fix(bedrock): remove legacy model entries 2026-05-09 20:21:33 +02:00
OpeOginni 0d73b82b9f fix(bedrock): restore regional model IDs 2026-05-09 20:18:59 +02:00
Aiden Cline 83c7e2b63f Merge pull request #1742 from Adam8234/add-firepass-provider
feat: add Fireworks (Firepass) provider
2026-05-09 12:45:09 -05:00
Adam 83ae4cf813 feat: add Fireworks (Firepass) provider
Adds the Fireworks AI Firepass subscription provider.
- Provider uses a dedicated FIREPASS_API_KEY
- Uses @ai-sdk/openai-compatible SDK
- Includes Kimi K2.6 Turbo (accounts/fireworks/routers/kimi-k2p6-turbo)
- Zero per-token cost since covered by subscription
2026-05-09 12:22:13 -05:00
EriDeLee 77eae6eef7 Update aihubmix models 2026-05-09 20:53:57 +08:00
Aiden Cline 8cbf6ed10e Merge pull request #1736 from vercel/update-vercel-models-1778258030
Update Vercel models
2026-05-08 21:58:40 -05:00
Mattia Cerutti 06d87e4411 chore(copilot): remove deprecated models 2026-05-09 00:19:50 +02:00
Frank 2cb3832618 update zen models 2026-05-08 17:11:05 -04:00
vimtor 950a0446d4 bring back svg loading 2026-05-08 20:18:12 +02:00
vimtor 41fbfb1a17 change sst mention 2026-05-08 20:13:09 +02:00
vimtor cf5045a90b move copy button next to name 2026-05-08 20:12:39 +02:00
vimtor ef739220de lock virtualized table column widths to prevent scroll jitter 2026-05-08 19:07:25 +02:00
github-actions[bot] df960d1a90 chore(vercel): update Vercel model definitions
Auto-generated by weekly workflow from Vercel AI Gateway API.

Co-Authored-By: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-05-08 16:33:52 +00:00
vimtor 7294efee15 move row-render.ts to shared.ts 2026-05-08 18:30:14 +02:00
vimtor 1e537147eb remove table row tuple optimization 2026-05-08 18:24:18 +02:00
Aiden Cline 8f2f83ef61 Merge pull request #1735 from slpdy/dev
Create DeepSeek-V4-Pro.toml
2026-05-08 10:59:33 -05:00
Aiden Cline b133426465 Merge pull request #1734 from oskarkocol/chore/update-novita-deepseek-prices
chore: update novita deepseek-v4-pro prices
2026-05-08 10:59:25 -05:00
Aiden Cline dafff5a770 Merge pull request #1730 from smakosh/add-llmgateway-models
Add new LLM Gateway text models (gpt-5.5, grok-4-3, gemini-3.1-flash-lite, qwen3.6, MiMo v2)
2026-05-08 10:58:20 -05:00
smakosh dd894f077f Merge remote-tracking branch 'upstream/dev' into add-llmgateway-models
# Conflicts:
#	providers/google/models/gemini-3.1-flash-lite.toml
2026-05-08 17:46:52 +02:00
smakosh 91590874e7 Revert "fix(models): use canonical entries for qwen3.6-max-preview and grok-4.3"
This reverts commit 70ac6fccda.
2026-05-08 17:43:07 +02:00
vimtor e9f4cecc54 extract shared row rendering module 2026-05-08 17:29:04 +02:00
vimtor fb1ac09883 virtualize model table 2026-05-08 17:07:28 +02:00
Jj a436236146 Create DeepSeek-V4-Pro.toml
Added DeepSeek-v4-Pro model to Nebius provider
2026-05-08 11:03:16 +01:00
oskar 1415b4be97 chore: update novita deepseek prices 2026-05-08 14:21:27 +07:00
Aiden Cline 1437da86e7 Merge pull request #1685 from 8023/dev
Add kimi-k2.6/deepseek-v4 model and EmpirioLabs AI integration for poe.com
2026-05-07 22:38:51 -05:00
Aiden Cline e7d57885d1 Merge pull request #1733 from chl-0537/feature/add-tencent
add model by openrouter
2026-05-07 22:21:07 -05:00
Aiden Cline 8157916515 fix: attachment 2026-05-07 22:12:11 -05:00
Aiden Cline 2e5b87a9c2 Merge pull request #1731 from mikeyp/chore/update-digitalocean-models
Add script to generate/update Digitalocean models
2026-05-07 16:42:09 -05:00
Aiden Cline 92e19432d3 add google gemini 3.1 flash lite 2026-05-07 15:44:25 -05:00
smakosh 70ac6fccda fix(models): use canonical entries for qwen3.6-max-preview and grok-4.3
Apply the canonical TOML provided by the LLM Gateway team for the
Qwen3.6 Max Preview and Grok 4.3 parent definitions, replacing the
upstream-merged variants whose dates and pricing did not match.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-07 22:34:01 +02:00
smakosh dc3283417d Merge remote-tracking branch 'upstream/dev' into add-llmgateway-models
# Conflicts:
#	providers/alibaba/models/qwen3.6-max-preview.toml
#	providers/llmgateway/models/qwen3.6-max-preview.toml
2026-05-07 22:28:23 +02:00
smakosh 34fd6673e5 chore(llmgateway): add new text models from llmgateway catalog
Add gemini-3.1-flash-lite, grok-4-3, gpt-5.5, gpt-5.5-pro, qwen3.6
and MiMo v2 models that exist in llmgateway.io but were missing
from models.dev. Adds parent definitions for grok-4-3,
gemini-3.1-flash-lite, and qwen3.6-max-preview where they did not
already exist.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-07 22:20:52 +02:00
Mike Prasuhn 5df9293314 Add script to generate/update Digitalocean models 2026-05-07 15:28:07 -04:00
Aiden Cline a81a9559d7 Merge pull request #1726 from Ardakilic/chore/sync-kilo-models
Chore: Sync Kilo models with upstream gateway
2026-05-07 13:04:51 -05:00
Aiden Cline 4197bf57a6 Merge pull request #1725 from dpuyosa/chore/venice-grok-costs
Venice: Update grok-4-20 pricing
2026-05-07 13:04:26 -05:00
Aiden Cline d0ac772507 Merge pull request #1717 from juls0730/refactor/mimo-extends/token-plan
refactor(xiaomi-token-plan): extends xiaomi base provider for xiaomi token plans
2026-05-07 13:04:05 -05:00
Aiden Cline 1afaa053e7 Merge pull request #1727 from sergeykonkin/update-nebius-models-2026-05
chore: update nebius provider models
2026-05-07 13:03:46 -05:00
Aiden Cline 9b77ce1c9e Merge pull request #1729 from Sewer56/add-minimax-m27-wafer
Added: MiniMax-M2.7 model for wafer.ai
2026-05-07 12:59:49 -05:00
Aiden Cline 68dc6d1820 Merge pull request #1728 from arafatkatze/codex/openrouter-qwen-cache-pricing
Add OpenRouter Qwen cache pricing
2026-05-07 12:59:29 -05:00
Arafatkatze a1eb5eece3 Add OpenRouter Qwen cache pricing 2026-05-07 10:29:48 -07:00
Sewer56 f7ec2c517f Added: wafer.ai/MiniMax-M2.7 model 2026-05-07 18:12:50 +01:00
Sergey Konkin f98e8ec793 chore: update nebius provider models 2026-05-07 15:37:18 +02:00
Arda Kilicdagi d210066793 chore: sync kilo gw models 2026-05-07 14:17:15 +03:00
Frank 06908cbf36 update zen models 2026-05-07 04:47:22 -04:00
dpuyosa b0614d2088 [venice] Update grok-4-20 pricing
- Lower grok-4-20 and multi-agent input/output costs to latest Venice pricing
2026-05-07 10:29:48 +02:00
mickalchen 32c1c45c52 add openrouter model 2026-05-07 11:22:11 +08:00
Frank 7c033f27e6 update zen models 2026-05-06 23:00:15 -04:00
mickalchen d648e63499 Merge remote-tracking branch 'origin/dev' into feature/add-tencent 2026-05-07 10:54:56 +08:00
Zoe 1353f965b9 refactor(xiaomi-token-plan): extends xiaomi base provider for xiaomi token plan 2026-05-06 18:53:49 -05:00
Isaac Huang 175082d43f Add GMI Cloud provider 2026-05-06 15:12:07 -07:00
Aiden Cline bba0a9c3f4 Merge pull request #1312 from NachoFLizaur/feat/kiro-provider
feat: add Kiro provider with 12 models
2026-05-06 12:16:47 -05:00
Frank 4bdb195178 update zen models 2026-05-06 12:56:58 -04:00
Aiden Cline 12706b7652 Merge pull request #1716 from juls0730/refactor/mimo-extends/zenmux
refactor(zenmux): extends mimo models from xiaomi provider
2026-05-06 10:45:01 -05:00
Aiden Cline d8c76d0c67 Merge pull request #1715 from juls0730/refactor/mimo-extends/qiniu-ai
refactor(qiniu-ai): extends mimo models from xiaomi provider
2026-05-06 10:30:46 -05:00
Aiden Cline 3963dd13d5 Merge pull request #1714 from juls0730/refactor/mimo-extends/openrouter
refactor(openrouter): extends mimo models from xiaomi provider
2026-05-06 10:30:32 -05:00
Aiden Cline 8749a56efa Merge pull request #1711 from juls0730/refactor/mimo-extends/kilo
refactor(kilo/xiaomi): extends mimo models from xiaomi provider
2026-05-06 10:29:31 -05:00
Aiden Cline 25de2ee27d Merge pull request #1718 from juls0730/refactor/mimo-extends/xiaomi
refactor(xiaomi): round xiaomi models to powers of 2 & fix small errors
2026-05-06 10:27:36 -05:00
Aiden Cline 438df7f03c Merge pull request #1723 from CloudFerro/fix/cloudferro-sherlock/minimax-m2.5
fix: cloudferro sherlock - update context values for minimax m2.5
2026-05-06 10:25:54 -05:00
Aiden Cline 7d18558aa3 Merge pull request #1722 from dpuyosa/chore/venice-model-updates
Venice: Remove deprecated models, enable reasoning on gpt-oss-120b
2026-05-06 10:25:36 -05:00
Jan Szypulski c82f736fcc fix: cloudferro sherlock - update context values for minimax m2.5 2026-05-06 10:52:39 +02:00
dpuyosa 6a436805b3 [venice] Remove deprecated models, enable reasoning on gpt-oss-120b
- Remove kimi-k2-thinking, qwen3-coder-480b-a35b-instruct, and venice-uncensored models
- Enable reasoning capability on openai-gpt-oss-120b
2026-05-06 09:44:24 +02:00
Jack ce7823f073 Merge pull request #1720 from anomalyco/fix/opencode-go-kimi-k26-pricing
fix(opencode-go): restore kimi k2.6 pricing
2026-05-06 12:33:24 +08:00
Jack 033efdb7d4 fix(opencode-go): restore kimi k2.6 pricing 2026-05-06 12:32:06 +08:00
Alex-wuhu 0f1855c0a7 provider(novita-ai): use extends for kimi k2.6 2026-05-06 10:41:46 +08:00
Zoe bd9e0c2677 refactor(xiaomi): round xiaomi models to powers of 2 & fix small errors 2026-05-05 18:40:05 -05:00
Zoe 38545d63a5 refactor(zenmux): extends mimo models from xiaomi provider 2026-05-05 18:17:21 -05:00
Zoe 014be328d6 refactor(qiniu-ai): extends mimo models from xiaomi provider 2026-05-05 18:05:39 -05:00
Zoe c139147540 refactor(openrouter): extends mimo models from xiaomi provider 2026-05-05 17:49:39 -05:00
Zoe 59cd93cafc refactor(kilo/xiaomi): extends mimo models from xiaomi provider 2026-05-05 17:13:06 -05:00
Aiden Cline e91db96d83 Merge pull request #1710 from Spherrrical/add-digitalocean-kimi-2-6
feat(digitalocean): add kimi-k2.6 model
2026-05-05 14:07:50 -05:00
Spherrrical d70dd8dcdc feat(digitalocean): add kimi-k2.6 model 2026-05-05 12:05:16 -07:00
Frank b18e681457 update deepseek flash on deepinfra 2026-05-05 14:24:03 -04:00
Aiden Cline b73a6a2130 Merge pull request #1709 from xiaomochn/fix/xiaomi-mimo-v2.5-modalities
fix(xiaomi): swap modalities for MiMo-V2.5 and MiMo-V2.5-Pro
2026-05-05 11:36:43 -05:00
Aiden Cline 153c1cc420 Merge pull request #1614 from Yashwanth-Kumar-26/patch-1
Add Qwen 3.6 27B model configuration
2026-05-05 11:22:43 -05:00
Aiden Cline ca0b30569e update google vertex to include all anthropic models 2026-05-05 11:12:23 -05:00
xiaomochn 8345bfbd06 fix(xiaomi): correct modalities for MiMo V2.5 models across providers
Issues fixed:
1. MiMo-V2.5 and MiMo-V2.5-Pro had their modalities swapped in the
   xiaomi canonical source (affects OpenRouter/ZenMux via extends)
2. Removed 'pdf' from V2.5 models — not a supported input modality
3. Fixed vercel provider: V2.5-Pro incorrectly marked as multimodal
4. Fixed opencode-go and vercel V2.5: added missing 'video', removed pdf

Correct modalities:
- MiMo-V2.5: input = ["text", "image", "audio", "video"]
- MiMo-V2.5-Pro: input = ["text"]

Affected providers: xiaomi, opencode-go, vercel, openrouter (extends),
zenmux (extends)

Fixes #1708
2026-05-05 22:46:44 +08:00
Shoubhit Dash 28c0d9ce23 fix(sarvam): correct output limits 2026-05-05 15:30:47 +05:30
Aiden Cline c16f3da694 Merge pull request #1707 from deathbeam/revert-1664-fix/glm-qwen-ollama-output-limit
Revert "fix(ollama): set glm-5.1 and qwen3.5:397b output limits to match context"
2026-05-04 23:51:53 -05:00
Tomas Slusny 6aa6e55d60 fix(ollam): use correct output limit for qwen3.5:397b
{"error":"max_tokens (262144) exceeds model's maximum output tokens (65536) for model qwen3.5:397b (ref: 8554a681-e6a8-45d7-9fdd-433785eb6c67)"}

Signed-off-by: Tomas Slusny <slusnucky@gmail.com>
2026-05-05 01:31:20 +02:00
Tomas Slusny 9efaf754a5 Revert "fix(ollama): set glm-5.1 and qwen3.5:397b output limits to match context" 2026-05-05 01:04:11 +02:00
Aiden Cline 104e4bdc1f Merge pull request #1684 from TheBaconWizard/add-clarifai-kimi-k2.6
provider(clarifai): add Kimi-K2.6 (moonshotai/chat-completion)
2026-05-04 12:00:33 -05:00
Aiden Cline db16c113f7 Merge pull request #1704 from stylings/stylings/add-openrouter-grok-4-3
feat: add OpenRouter Grok 4.3
2026-05-04 12:00:08 -05:00
Alex 64a122a13d fix: update OpenRouter Grok 4.3 file 2026-05-04 12:44:07 -04:00
Alex fcc6521d1d fix: simplify OpenRouter Grok 4.3 file 2026-05-04 12:41:56 -04:00
Alex c623b4a55f feat: add OpenRouter Grok 4.3 2026-05-04 12:36:33 -04:00
Aiden Cline 1d730fea16 Merge pull request #1696 from cgilly2fast/dev
chore(frogbot): convert firmware provider to frogbot
2026-05-04 10:26:36 -05:00
Aiden Cline 5457215e29 Merge pull request #1650 from PedroACosta/feat/add-dinference-models
feat(dinference): add GLM-5.1 and MiniMax-M2.5 models
2026-05-04 10:26:02 -05:00
Aiden Cline b3ab45990f Merge pull request #1697 from rocuevas9511/feat/add-deepinfra-gemma4
add gemma4 26b a4b and 31b to deepinfra
2026-05-04 10:25:31 -05:00
Aiden Cline d906a07e31 Merge pull request #1703 from dpuyosa/feat/venice-grok-4-3
Venice: Add Grok 4.3 model configuration
2026-05-04 10:25:16 -05:00
dpuyosa 4b1f6edd52 [venice] Add Grok 4.3 model configuration
- Add Grok 4.3 model with 1M context and 32K output
- Configure standard and >200K cost tiers
- Enable text+image input with text output modalities
2026-05-04 09:54:01 +02:00
Aiden Cline a92a2cfe3d Merge pull request #1702 from langyo/fix/glm-5v-turbo-naming
fix: use proper GLM family casing for GLM-5V-Turbo
2026-05-03 16:53:44 -05:00
Aiden Cline 70891f58e5 Merge pull request #1701 from kaeltrn/add-perplexity-agent-opus-4-7-gpt-5-5
Add Claude Opus 4.7 and GPT-5.5 models for perplexity-agent
2026-05-03 16:53:26 -05:00
Aiden Cline 1600c827fc Merge pull request #1698 from tim-mcdonald/add-kimi-k2.6-nvidia
Add Kimi K2.6 model for NVIDIA provider
2026-05-03 16:53:01 -05:00
Aiden Cline 5851cdc136 Merge pull request #1700 from JDinABox/dev
Add Synthetic Kimi-K2.6 model configuration
2026-05-03 16:52:46 -05:00
langyo 4fd0e38c58 fix: use proper GLM family casing for GLM-5V-Turbo
- Rename glm-5v-turbo to GLM-5V-Turbo in zai, zhipuai, and 302ai providers
- Add GLM-5V-Turbo back to zhipuai-coding-plan (removed in #1589)

Ref: #1589
2026-05-04 00:51:54 +08:00
Pedro dd685ea42c refactor(dinference): use extends format for GLM and MiniMax models 2026-05-03 17:54:18 +02:00
kaeltrn 7835298241 Add Claude Opus 4.7 and GPT-5.5 models for perplexity-agent 2026-05-03 20:09:14 +07:00
Isaac Ng c5fbcc2c9b 📦 CHORE: remove senera 2026-05-03 16:17:37 +08:00
Isaac Ng ab2eb51b4e chore(nvidia): align Nemotron endpoint slugs
Replace stale NVIDIA Nemotron entries with the live Build catalog slugs so the local provider catalog matches current free and partner endpoints.
2026-05-03 15:47:19 +08:00
Isaac Ng 8e19ec580c 📦 CHORE: sync latest nvidia model 2026-05-03 15:19:17 +08:00
Isaac Ng 3aecc94c46 chore(nvidia): sync endpoint model catalog
Update NVIDIA model TOMLs to match the live Build endpoint list by removing stale entries and adding missing ones.

This keeps the provider catalog aligned with the current free and partner endpoint inventory.
2026-05-03 14:47:30 +08:00
JD Crawford 2ac7912ee7 use extends format 2026-05-03 01:04:53 -04:00
JD Crawford 9ac5b5f625 Add Synthetic Kimi-K2.6 model configuration 2026-05-03 00:17:37 -04:00
Aiden Cline 8c4d9f4696 Merge pull request #1699 from cfal/qwen3.6-max-preview
providers/alibaba/models/qwen3.6-max-preview.toml: add qwen 3.6 max
2026-05-02 21:35:02 -05:00
cfal c4bb0b4b11 providers/alibaba/models/qwen3.6-max-preview.toml: add qwen 3.6 max 2026-05-03 09:25:31 +08:00
Tim McDonald db4d03c171 Add Kimi K2.6 model for NVIDIA provider 2026-05-02 16:09:37 -06:00
rocuevas9511 60d1d4df77 add gemma4 26b a4b and 31b to deepinfra 2026-05-02 14:26:19 -06:00
Colby Gilbert 31654fc2ef chore(frogbot): convert firmware provider to frogbot 2026-05-02 12:36:20 -07:00
Aiden Cline 01e56b1e1e Merge pull request #1682 from varunrandery/poolside/laguna-openrouter
Add Poolside Laguna series models (OpenRouter)
2026-05-02 14:30:20 -05:00
Aiden Cline 4a7d9275d6 Merge pull request #1695 from hgraca/cortecs
Cortecs
2026-05-02 14:04:00 -05:00
Aiden Cline 978fe11e0c Merge pull request #1694 from cgilly2fast/dev
feat(firmware): add deepseek v4, remove gemini 3 pro add gpt 5.4 min,…
2026-05-02 14:03:14 -05:00
Herberto Graca 0b4198955f refactor(cortecs): use extends for models with canonical bases
Convert 7 Cortecs models to extends format, inheriting from their
canonical provider definitions (deepseek, llama, mistral, alibaba).
Reduces duplication by ~55 lines while preserving Cortecs-specific
cost overrides.
2026-05-02 20:56:11 +02:00
Herberto Graca 66b568b681 Add deepseek-v4-pro model for cortecs 2026-05-02 20:56:11 +02:00
Herberto Graca 589fddeed7 Add codestral-2508 model for cortecs 2026-05-02 20:56:10 +02:00
Herberto Graca 6f75266d42 Add deepseek-v3.2 model for cortecs 2026-05-02 20:56:10 +02:00
Herberto Graca 0f03115ee0 Add deepseek-r1-0528 model for cortecs 2026-05-02 20:56:09 +02:00
Herberto Graca ae2564edc2 Add mixtral-8x7B-instruct-v0.1 model for cortecs 2026-05-02 20:56:09 +02:00
Herberto Graca 629856cf41 Add hermes-4-70b model for cortecs 2026-05-02 20:56:08 +02:00
Herberto Graca 567bc13ab4 Add llama-3.3-70b-instruct model for cortecs 2026-05-02 20:56:08 +02:00
Herberto Graca 5eac173bc5 Add qwen3-235b-a22b-instruct-2507 model for cortecs 2026-05-02 20:56:07 +02:00
Herberto Graca cb0d640afd Add qwen3-coder-30b-a3b-instruct model for cortecs 2026-05-02 20:56:07 +02:00
Herberto Graca b5e27e652f Add nemotron-3-super-120b-a12b model for cortecs 2026-05-02 20:56:06 +02:00
Herberto Graca 650c27411f Add qwen3.5-122b-a10b model for cortecs 2026-05-02 20:56:06 +02:00
Herberto Graca 98c55325bf Add mistral-large-2512 model for cortecs 2026-05-02 20:56:05 +02:00
Herberto Graca 2fdd33b8a7 Add qwen3.5-397b-a17b model for cortecs 2026-05-02 20:55:57 +02:00
Colby Gilbert e4dea0a3d8 feat(firmware): grok 4.3 2026-05-02 10:53:24 -07:00
Colby Gilbert b4b3622bfd feat(firmware): add deepseek v4, remove gemini 3 pro add gpt 5.4 min, add gpt 5.4 nano, add gpt 5.5, and minimax m2.7 2026-05-02 09:23:42 -07:00
Aiden Cline 3b35b5598a Merge pull request #1693 from hgraca/add-deepseek-v4-flash-cortecs
Add deepseek-v4-flash model for cortecs
2026-05-02 10:46:57 -05:00
Aiden Cline d2e16bab34 Merge pull request #1610 from monotykamary/feat/neuralwatt-provider
feat: add neuralwatt provider with 14 models
2026-05-02 10:45:50 -05:00
Tom X Nguyen 051dc6236a fix(neuralwatt): sync model capabilities with provider API 2026-05-02 20:42:00 +07:00
Herberto Graca 5b9dee1f3d Add deepseek-v4-flash model for cortecs 2026-05-02 12:50:59 +02:00
8023 426dfe7be5 fix validate error 2026-05-02 12:15:50 +08:00
8023 fddfb083d1 add EmpirioLabs AI and deepseek v4 2026-05-02 11:14:51 +08:00
8023 4eccfaba87 Add Kimi-K2.6 model configuration file 2026-05-02 11:08:32 +08:00
Jeff Lim ea46d016d3 fix(clarifai): drop redundant cost override for Kimi-K2.6
Clarifai's published pricing ($0.95 input, $4.00 output) matches the
canonical moonshotai/kimi-k2.6, so the explicit [cost] block was just
duplicating upstream. Inherit it via extends instead.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-01 18:20:39 -07:00
Jeff Lim 1bd1449ec5 provider(clarifai): add Kimi-K2.6 (moonshotai/chat-completion)
Extends moonshotai/kimi-k2.6 with Clarifai-specific cost and modalities
(text+image only on Clarifai; cache pricing not exposed).

Model URL: https://clarifai.com/moonshotai/chat-completion/models/Kimi-K2_6

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-01 18:14:19 -07:00
Varun Randery 7d334a51c9 Add Laguna models 2026-05-01 23:35:13 +01:00
Aiden Cline 10ae0b5a1d Merge pull request #1664 from fernandoenzo/fix/glm-qwen-ollama-output-limit
fix(ollama): set glm-5.1 and qwen3.5:397b output limits to match context
2026-05-01 15:50:22 -05:00
Aiden Cline d25cce170d Merge pull request #1665 from Ardakilic/chore/cleanup-kilo-provider
Chore: Sync Kilo Gateway provider models with upstream API changes and add Owl Alpha model.
2026-05-01 15:49:53 -05:00
Aiden Cline 3e097a5d89 Merge pull request #1671 from hgraca/add-qwen-2.5-72b-instruct-cortecs
Add qwen-2.5-72b-instruct model for cortecs
2026-05-01 15:49:28 -05:00
Aiden Cline 074b38eb98 Merge pull request #1663 from fernandoenzo/fix/minimax-m2.7-ollama-context-output-limit
fix(ollama): set minimax-m2.7 context and output limits to match Ollama API
2026-05-01 14:24:35 -05:00
Aiden Cline d474922588 Merge pull request #1679 from Spherrrical/add-digitalocean-deepseek-v4-pro
feat(digitalocean): add deepseek-v4-pro model
2026-05-01 13:46:50 -05:00
Spherrrical 56ddb9017c feat(digitalocean): add deepseek-v4-pro model 2026-05-01 11:20:09 -07:00
Rohan Taneja a565bbebc0 Merge pull request #1677 from vercel/update-vercel-models-1777652649 2026-05-01 10:47:39 -07:00
github-actions[bot] 5b97fca592 chore(vercel): update Vercel model definitions
Auto-generated by weekly workflow from Vercel AI Gateway API.

Co-Authored-By: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-05-01 16:24:16 +00:00
Arda Kilicdagi aec3f94081 feat: owl alpha, chore: sync kilo code upstream
feat: owl alpha, chore: sync kilo code upstream
2026-05-01 14:09:51 +03:00
Fernando Guarini e5c63d671e fix(ollama): set glm-5.1 and qwen3.5:397b output limits to match context 2026-05-01 11:29:49 +02:00
Fernando Guarini 22e87ab31b fix(ollama): set minimax-m2.7 context and output limits to match Ollama API 2026-05-01 11:29:41 +02:00
Shoubhit Dash 90515f1913 provider(sarvam): add chat models 2026-05-01 14:41:47 +05:30
Herberto Graca 97d93676bc Add qwen-2.5-72b-instruct model for cortecs 2026-05-01 09:36:16 +02:00
Alex-wuhu 6c3c4a721c provider(novita-ai): sync latest models 2026-05-01 14:19:17 +08:00
Aiden Cline 692fbd0f19 Merge pull request #1628 from fanweixiao/dev
provider(vivgrid): remove GLM-5, add GPT-5.5 and DeepSeek-v4-Pro model
2026-04-30 23:57:52 -05:00
C.C. Fan c3bd263a67 provider(vivgrid): add deepseek-v4-pro model
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-01 11:46:39 +08:00
Aiden Cline 9b9685c297 Merge pull request #1658 from v1gnesh/dev
Create grok-4.3.toml
2026-04-30 22:46:08 -05:00
C.C. Fan b3f063da79 provider(vivgrid): use extends for gpt-5.5 instead of duplicating fields
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-01 11:45:13 +08:00
C.C. a33d0aea81 Merge branch 'anomalyco:dev' into dev 2026-05-01 11:38:42 +08:00
v1gnesh ca380a136e Create grok-4.3.toml 2026-05-01 08:17:12 +05:30
Arda Kılıçdağı dfa186a768 feat: owl alpha 2026-05-01 01:47:25 +03:00
Aiden Cline d63ffa53e8 Merge pull request #1654 from zainhas/dev
[Together AI] add qwen 3.6 plus
2026-04-30 16:34:28 -05:00
Aiden Cline 284def86ef Merge pull request #1653 from smakosh/feat/llmgateway-add-gpt-5-5-and-qwen3-6
feat(llmgateway): add gpt-5.5, gpt-5.5-pro, qwen3.6-35b-a3b, qwen3.6-plus, qwen3.6-max-preview
2026-04-30 16:34:18 -05:00
Siddharth Dhulipalla c19936565d Remove Fire Pass from Fireworks Kimi K2.5 Turbo description (#1655) 2026-04-30 17:28:36 -04:00
Zain Hasan 73b872e141 output 500_000 2026-04-30 14:22:41 -07:00
Zain Hasan 7373bb5878 [Together AI] add qwen 3.6 plus 2026-04-30 14:21:40 -07:00
smakosh d11c151c25 feat(llmgateway): add gpt-5.5, gpt-5.5-pro, qwen3.6-35b-a3b, qwen3.6-plus, qwen3.6-max-preview
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-30 22:05:40 +02:00
Aiden Cline f3f4fea66c Merge pull request #1645 from stylings/stylings/add-mistral-medium-3-5
feat: add Mistral Medium 3.5
2026-04-30 14:37:16 -05:00
Aiden Cline 90116256a6 Merge pull request #1652 from Spherrrical/add-digitalocean-provider
feat(digitalocean): sync model catalog
2026-04-30 14:32:07 -05:00
Spherrrical 5008df8bcc feat(digitalocean): sync model catalog with /v1/models API
Add 16 new models (anthropic, openai, alibaba, deepseek, google,
meta, mistral, nvidia, baai, intfloat, fal-hosted) to match the
current DigitalOcean Gradient AI Platform catalog, and rename
openai-gpt-5-2-pro to openai-gpt-5.2-pro to match the API id.
2026-04-30 12:08:57 -07:00
Alex 696aa80dec revert(openrouter): remove Mistral Medium 3.5 stub 2026-04-30 14:59:56 -04:00
Aiden Cline 7d00d863dc Merge pull request #1647 from dpuyosa/chore/venice-kimi-pricing
Venice: Update Kimi K2.5 and K2.6 pricing and dates
2026-04-30 11:29:08 -05:00
Aiden Cline ad9eb83b8c Merge pull request #1648 from Snat3r/patch-1
Fix casing in model name MiniMax m2.7 foor cortects provider
2026-04-30 11:28:55 -05:00
Aiden Cline 467da9a82c Merge pull request #1649 from berget-ai/feat/berget-mistral-medium-3.5
feat: add Mistral Medium 3.5 128B to berget.ai
2026-04-30 11:28:43 -05:00
Pedro 22786bcf4b feat(dinference): add GLM-5.1 and MiniMax-M2.5 models 2026-04-30 13:43:44 +02:00
Christian Landgren c8d258b7cb feat: add Mistral Medium 3.5 128B to berget.ai 2026-04-30 12:31:28 +02:00
Snat3r 70309829ca Fix casing in model name and update output limit 2026-04-30 11:59:44 +02:00
dpuyosa 71e00f193b [venice] Update Kimi K2.5 and K2.6 pricing and dates
- Bump kimi-k2-5 cache_read from 0.11 to 0.22
- Bump kimi-k2-6 input from 0.7448 to 0.85 and cache_read from 0.1463 to 0.22
- Update last_updated dates to 2026-04-30
2026-04-30 11:18:54 +02:00
Alex d44e724170 feat(openrouter): add Mistral Medium 3.5 2026-04-29 18:58:26 -04:00
Alex 414695db9f feat(mistral): add Mistral Medium 3.5 2026-04-29 18:44:28 -04:00
Aiden Cline e8b5a27723 Merge pull request #1642 from Sewer56/add-wafer-deepseek-v4-pro
feat(wafer.ai): add DeepSeek V4 Pro
2026-04-29 17:14:17 -05:00
Aiden Cline 6dc9d805db Merge pull request #1643 from Sawyerb/patch-1
Delete providers/vercel/models/inception/mercury-coder-small.toml
2026-04-29 17:14:00 -05:00
Aiden Cline bdf56c9111 add kimi k2.6 to azure cognitive services 2026-04-29 17:13:19 -05:00
Sewer56 293cc3e82f feat(wafer.ai): add DeepSeek V4 Pro 2026-04-29 23:12:04 +01:00
Sawyer Birnbaum 7f5bd4f231 Delete providers/vercel/models/inception/mercury-coder-small.toml
Mercury Coder Small has been deprecated. People should use Mercury Edit 2 instead.
2026-04-29 14:50:35 -07:00
Aiden Cline c4826babc5 Merge pull request #1497 from Lydanne/fix/302ai-models
Update 302ai model metadata and add GPT-5.4 configs
2026-04-29 14:26:01 -05:00
Rohan Taneja 91e8bb985e Merge pull request #1641 from vercel/update-vercel-models-1777480545
Update Vercel models
2026-04-29 11:29:45 -07:00
Aiden Cline 56723051d4 Merge pull request #1615 from deaquino/dev
Add Qwen3.5-9B model configuration file to OVHCloud
2026-04-29 13:09:19 -05:00
Aiden Cline 0bb3e55c08 Merge pull request #1640 from dpuyosa/chore/venice-update-pricing
Venice: Update DeepSeek v4 and Qwen 3.6 model pricing and metadata
2026-04-29 13:02:40 -05:00
github-actions[bot] 080b7a328b chore(vercel): update Vercel model definitions
Auto-generated by weekly workflow from Vercel AI Gateway API.

Co-Authored-By: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-04-29 16:35:47 +00:00
Misha Skvortsov c59c4aae6c feat(atomic-chat): add curated initial model list
Re-introduces a small curated list of models that ship preconfigured
in Atomic Chat, so opencode users get a working `models.dev` entry
out of the box instead of an empty `models: {}`.

Models (ids match the normalized form returned by Atomic Chat's
/v1/models endpoint, i.e. dots replaced with underscores):

- gemma-4-E4B-it-IQ4_XS
- gemma-4-E4B-it-MLX-4bit
- Qwen3_5-9B-Q4_K_M
- Qwen3_5-9B-MLX-4bit
- Meta-Llama-3_1-8B-Instruct-GGUF

Qwen 3.5 9B dates are taken from the verified providers/venice entry
for the same base model; quantization does not change release dates.

Made-with: Cursor
2026-04-29 17:52:56 +03:00
Frank c5d696583e update zen models 2026-04-29 09:38:00 -04:00
Mike Sukmanowsky 2cb5a99b98 fix: add model card links for Kimi K2 and Kimi K2.5 2026-04-29 09:29:36 -04:00
dpuyosa 70490d892f [venice] Update DeepSeek v4 and Qwen 3.6 model pricing and metadata
- Reduce DeepSeek v4 Flash/Pro input and output pricing
- Add cache_read pricing for DeepSeek v4 models
- Fix Qwen 3.6 27B model name formatting
2026-04-29 09:39:11 +02:00
Aiden Cline f858a85ba6 Merge pull request #1625 from xinrui-z/fix-aihubmix-2026-04-28
fix: sync AIHubMix models (2026-04-28)
2026-04-28 23:03:28 -05:00
Aiden Cline 44e4c92882 Merge pull request #1620 from kill74/add-zai-coding-plan-glm-5v-turbo
Add GLM-5V-Turbo to Z.ai coding plan
2026-04-28 19:28:48 -05:00
Aiden Cline 43eafcb258 Merge pull request #1581 from xiaojiezj/zenmux_0425
feat: add models for zenmux provider
2026-04-28 19:27:38 -05:00
Aiden Cline b382ac7af9 Merge branch 'dev' into zenmux_0425 2026-04-28 19:08:09 -05:00
Tom X Nguyen ca21110644 fix: sync neuralwatt models with updated API pricing and capabilities
The Neuralwatt API now returns accurate pricing and capabilities,
eliminating the need for manual patches (patch.json is now empty).

Changes:
- Update pricing for all 14 models from API (significant changes for
  GLM, GPT-OSS, Qwen, and MiniMax models)
- Devstral Small 2 now supports image input (vision)
- kimi-k2.5-fast now supports image input (vision)
- kimi-k2.6-fast now supports reasoning + image input (was non-reasoning)
- Qwen3.6-35B-A3B now supports reasoning (was non-reasoning)
- GLM models context window: 202,752 → 200,000
- Rename fast variant model IDs to match API (dropped org prefix):
  zai-org/glm-5-fast → glm-5-fast
  zai-org/glm-5.1-fast → glm-5.1-fast
  moonshotai/kimi-k2.5-fast → kimi-k2.5-fast
  moonshotai/kimi-k2.6-fast → kimi-k2.6-fast
  Qwen/qwen3.5-397b-fast → qwen3.5-397b-fast
  Qwen/qwen3.6-35b-fast → qwen3.6-35b-fast
2026-04-29 07:05:23 +07:00
Mike Sukmanowsky 0c2e47e8ba Fix token limits for Amazon Bedrock Kimi K2 models
Correct context and output limits for moonshot.kimi-k2-thinking and
moonshotai.kimi-k2.5 on Amazon Bedrock:
- context: 256_000 → 262_143
- output: 256_000 → 16_000
2026-04-28 17:45:59 -04:00
Aiden Cline 6a0704574b Merge pull request #1621 from YuzhongHuangCS/dev
feat(wandb): Add GLM-5.1
2026-04-28 15:51:43 -05:00
Aiden Cline 1cb1341516 Merge pull request #1635 from stylings/feat/nemotron-3-nano-omni
feat: add Nemotron 3 Nano Omni model
2026-04-28 15:04:07 -05:00
Alex bc47e95427 fix: rename Nemotron Omni metadata 2026-04-28 15:20:24 -04:00
Aiden Cline b071e8add8 Merge pull request #1619 from fernandoenzo/fix/deepseek-v4-pro-ollama-cloud
fix(ollama-cloud): correct deepseek-v4-pro model config
2026-04-28 14:00:42 -05:00
Aiden Cline 23e527753e Merge pull request #1623 from itsnebulalol/dev
feat: add gpt-5.5 pro on openai and openrouter
2026-04-28 14:00:34 -05:00
Aiden Cline e81c045ed0 Merge pull request #1636 from dsingal0/feat/openrouter-deepseek-v4
feat(baseten): add DeepSeek V4 Pro
2026-04-28 13:49:11 -05:00
Dhruv Singal 0c602ca936 feat(baseten): update DeepSeek V4 Pro pricing 2026-04-28 11:45:02 -07:00
Dhruv Singal 9866f84989 feat(baseten): add DeepSeek V4 Pro 2026-04-28 11:38:22 -07:00
Alex 6b397ffe37 fix: align nvidia output limit 2026-04-28 14:35:31 -04:00
Alex bc21596889 fix: drop openrouter provider prefix 2026-04-28 14:22:04 -04:00
Alex 20abba3190 feat: add Nemotron 3 Nano Omni 2026-04-28 14:17:22 -04:00
Dominic Frye 5881bf98a0 fix: enable pdf input modality for gpt-5.5 pro 2026-04-28 13:33:31 -04:00
Aiden Cline 595f7d028c Merge pull request #1632 from rocuevas9511/feat/deepinfra-deepseek-v4-pro
feat: add DeepSeek-V4-Pro to deepinfra
2026-04-28 12:07:22 -05:00
rocuevas9511 c81dec9c5d feat: add DeepSeek-V4-Pro to deepinfra 2026-04-28 10:56:44 -06:00
Guiii 4d45ed25d2 Use extended GLM-5V-Turbo config
Removed various fields and added extends section.
2026-04-28 17:49:34 +01:00
Yuzhong Huang 03cf48de53 use extends instead 2026-04-28 09:19:26 -07:00
Aiden Cline 0d3a284395 Merge pull request #1622 from eduqr/feat/fireworks-ai-deepseek-v4-pro
feat(fireworks-ai): add deepseek-v4-pro
2026-04-28 10:52:54 -05:00
Aiden Cline 5b1bb0fc80 Merge pull request #1624 from shelvick/add-azure-kimi-k2-6
Add Kimi K2.6 to Azure
2026-04-28 10:38:07 -05:00
Aiden Cline 332ebb8811 Merge pull request #1627 from ceoAppsknight/kilo/add-mimo-models
Add Kilo Mimo v2.5 models
2026-04-28 10:37:40 -05:00
Aiden Cline 2111813bd4 Merge pull request #1629 from ndeybach/PR-azure-5.4-limits
fix(azure): correct GPT-5.4 series limits and cleanup
2026-04-28 10:37:01 -05:00
Nils DEYBACH f5b8521af6 fix: use extends and not symlinks 2026-04-28 17:34:44 +02:00
Nils DEYBACH 79481cff40 fix(azure): update GPT-5.4 metadata
Use `extends` for Azure GPT-5.4 variants and keep Azure-specific overrides for
PDF input and omitted fast mode.

Validated with `bun validate`.

Azure runtime manual probing confirmed GPT-5.4 uses the documented 1.05M context /
922K input / 128K output limits.
2026-04-28 14:00:20 +02:00
Nils DEYBACH 40dc356d4c fix(azure): correct GPT-5.4 and GPT-5.4 Pro limits (and convert to extend)
Correct Azure GPT-5.4 and GPT-5.4 Pro limits to `1_050_000` context,
`922_000` input, and `128_000` output based on Azure runtime results and
Microsoft Learn docs. Mini and Nano already matched and are unchanged.

The limits were tested directly (see script at : https://github.com/ndeybach/Azure_endpoint_limit_test_script )
2026-04-28 12:33:27 +02:00
C.C. Fan f929fe89e7 provider(vivgrid): remove GLM-5, add GPT-5.5 model 2026-04-28 16:44:59 +08:00
Syed Assadullah Shah cbd245d454 add Kilo Mimo v2.5 models 2026-04-28 13:04:36 +05:00
xinrui e5289e9b3a fix: sync AIHubMix models (2026-04-28) 2026-04-28 11:33:25 +08:00
Scott Helvick bb623f3ff9 Add Kimi K2.6 to Azure 2026-04-28 02:28:46 +00:00
Dominic Frye 37fffafafc feat: add gpt-5.5 pro on openai and openrouter 2026-04-27 22:24:32 -04:00
eduqr d329310745 feat(fireworks-ai): add deepseek-v4-pro 2026-04-27 21:05:55 -05:00
Yuzhong Huang 8016a6c45a Add GLM-5.1 to wandb provider 2026-04-27 17:35:38 -07:00
Guilherme Sales 1eeaa0b756 Add GLM-5V-Turbo to Z.ai coding plan 2026-04-28 00:47:15 +01:00
Frank dd3533b4e0 update zen models 2026-04-27 19:31:24 -04:00
Fernando Guarini 3a5867834f fix(ollama-cloud): correct deepseek-v4-pro model config
- Remove fields that don't belong in ollama-cloud: temperature, structured_output, knowledge, interleaved
- Set output = context (1048576) per ollama-cloud convention
- Set name to lowercase per ollama-cloud convention
- Reorder fields to match existing ollama-cloud model files
2026-04-28 00:24:54 +02:00
Aiden Cline 1e83bca7a3 Merge pull request #1617 from JoshuaDietz/dev
feat(ollama cloud): add deepseek v4 pro
2026-04-27 16:42:56 -05:00
Aiden Cline cd8853f88b Merge pull request #1616 from fhennerkes/dev
poe: add GPT-5.5 and GPT-5.5-Pro models
2026-04-27 16:08:36 -05:00
Joshua Dietz 23b290c6a8 fix(ollama cloud): fix model name
Model name was inconsistent with naming schema of flash model on ollama cloud
2026-04-27 21:47:30 +02:00
fhennerkes 4e7849cee7 poe: reduce omits in gpt-5.5 extends configs
Inherit family, knowledge, and structured_output from base models
instead of omitting them. Only omit fields that genuinely don't
apply to Poe (provider-specific pricing tiers, different context
limits, opencode-specific provider config).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-27 12:44:49 -07:00
Joshua Dietz e3e63a7247 feat(ollama cloud): add deepseek v4 pro 2026-04-27 21:42:10 +02:00
Aiden Cline fb297153e4 Merge pull request #1572 from YoshiTabletopGamer/qwen3.5-3.6-alibaba-open
[alibaba] Add remaining open Qwen 3.5 and 3.6 models, fix Qwen-3.5 397B-A17B
2026-04-27 14:36:51 -05:00
fhennerkes e8dd06e0ce poe: use extends format for gpt-5.5-pro
Address PR review comment to use extends format. Inherit from
opencode/gpt-5.5-pro since no openai/gpt-5.5-pro base exists yet.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-27 10:49:36 -07:00
fhennerkes bdee3d438b poe: use extends format for gpt-5.5
Address PR review comment to use extends format and inherit from
openai/gpt-5.5 base model.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-27 10:36:10 -07:00
fhennerkes b410bc3ef2 poe: add GPT-5.5 and GPT-5.5-Pro models 2026-04-27 10:34:52 -07:00
Aiden Cline 870e3d1d26 Merge pull request #1612 from hanouticelina/add-deepseek-v4-for-huggingface
feat(huggingface): add DeepSeek V4 Pro
2026-04-27 11:20:12 -05:00
Aiden Cline 5f21f3b603 Merge pull request #1586 from fernandoenzo/add-ollama-cloud-deepseek-v4-flash
feat(ollama-cloud): add deepseek-v4-flash model
2026-04-27 10:42:53 -05:00
Celina Hanouti 27dad05e25 extend deepseek/deepseek-v4-pro 2026-04-27 16:38:36 +01:00
Aiden Cline 2ed88cbcc0 Merge pull request #1604 from ndeybach/PR-gpt-5.5
feat(azure): add GPT-5.5 model metadata
2026-04-27 10:20:32 -05:00
Nils DEYBACH 4d199c932e fix: base azure-cognitive-services model not on azure
extend of extend does not seem to be supported
2026-04-27 17:04:20 +02:00
Jaime de Aquino 2d142f920c Add Qwen3.5-9B model configuration file 2026-04-27 16:46:04 +02:00
Celina Hanouti 47dea9e551 fix 2026-04-27 15:40:35 +01:00
Celina Hanouti 0d25c3dcac use extends 2026-04-27 15:37:31 +01:00
Aiden Cline 3d7f9256cb Merge pull request #1583 from abliteration-ai/codex/add-abliteration-provider
Add abliteration.ai provider
2026-04-27 09:29:26 -05:00
Aiden Cline 6aa1ebd4be Merge pull request #1595 from Contraboi/contra/add-openrouter-nano-banana-2
feat(openrouter): add Gemini 3.1 flash image preview (Nano Banana 2)
2026-04-27 09:28:23 -05:00
Aiden Cline f9ebebaffd Merge pull request #1601 from shikbupt/alibaba-deepseek
add alibaba-cn deepseek-v4
2026-04-27 09:28:08 -05:00
sk 7b3fe83c09 use extend format 2026-04-27 21:48:26 +08:00
Yashwanth Kumar 0a06b3efc2 Update Qwen model configuration in TOML file 2026-04-27 16:40:28 +05:30
Yashwanth Kumar 90dcbbbcc5 Add Qwen3.6 27B model configuration 2026-04-27 16:29:56 +05:30
Yashwanth Kumar b17f5fd8ae Delete providers/openrouter/models/qwen/qwen-3.6-27b.toml 2026-04-27 16:28:19 +05:30
Yashwanth Kumar 68691ac3f9 Update providers/openrouter/models/qwen/qwen-3.6-27b.toml
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-04-27 16:27:56 +05:30
Yashwanth Kumar 78fe905fcb Add Qwen 3.6 27B model configuration 2026-04-27 16:22:24 +05:30
Nils DEYBACH 6b488802cf fix: parsing error and add context over price
- adds the context over X price capability from parent (awaiting refactor to be correct on exact limit threashold)
- fix parsing since anything must be before extends.
2026-04-27 12:27:47 +02:00
Jack 4d0505b70e Merge pull request #1611 from anomalyco/fix/opencode-go-deepseek-v4-flash-cache-read-20260427
fix(opencode-go): update deepseek v4 flash cache pricing in Go
2026-04-27 17:34:52 +08:00
Jack b729923bd9 fix(opencode-go): correct deepseek v4 flash cache pricing 2026-04-27 17:31:41 +08:00
Celina Hanouti 34c7aa7dfe update context limit 2026-04-27 09:33:57 +01:00
Celina Hanouti 09b4d3548b add support for DeepSeek V4 Pro for Hugging Face provider 2026-04-27 09:31:55 +01:00
xiaojie.zj f1cad8fdc0 feat: add zenmux models 2026-04-27 16:27:46 +08:00
Tom X Nguyen b2f7f57f26 feat: add neuralwatt provider with 14 models
Add Neuralwatt as an OpenAI-compatible inference provider with
energy-aware GPU optimization. Includes 14 models across 6
sub-providers (Mistral, ZAI, OpenAI, Moonshot, MiniMax, Qwen).

Models include reasoning variants (Kimi K2.5/K2.6, GLM 5.1 FP8,
MiniMax M2.5, Qwen3.5 397B, GPT OSS 20B) and fast non-reasoning
variants (Kimi K2.5/K2.6 Fast, GLM 5/5.1 Fast, Qwen3.5/3.6 Fast),
plus Devstral Small 2 and Qwen3.6 35B A3B.

Logo derived from official Neuralwatt favicon (currentColor variant).
Pricing sourced from Neuralwatt's published rates.
2026-04-27 15:01:56 +07:00
Aiden Cline 925d4eba1f Merge pull request #1536 from philipmat/add-openrouter-pareto-code-router
Adds support for openrouter/pareto-code
2026-04-26 23:52:04 -05:00
Aiden Cline bc1e4b870b Merge pull request #1608 from Alex-wuhu/dev
add deepseek-v4, qwen3.6 on novita
2026-04-26 23:16:56 -05:00
Alex-wuhu ef913f9645 refactor: use extends format for novita deepseek v4 models
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-27 12:00:04 +08:00
Alex-wuhu cec747ade3 fix: add cache_read pricing for deepseek v4 models 2026-04-27 11:09:15 +08:00
Aiden Cline 2ced32d52f Merge pull request #1596 from NathanDrake2406/add-cf-ai-gateway-gpt-5.5
feat(cloudflare-ai-gateway): add openai/gpt-5.5
2026-04-26 21:57:13 -05:00
Alex-wuhu 92cc5a79df feat: add deepseek-v4, qwen3.6 on novita 2026-04-27 10:49:13 +08:00
Aiden Cline 4cf8661f92 Merge pull request #1602 from shikbupt/alibaba-qwen3.6-max
add alibaba-cn qwen3.6 max
2026-04-26 17:48:14 -05:00
Aiden Cline ebe431c0dc Merge pull request #1606 from LightAndy1/dev
Add gemini-3.1-flash-preview for google-vertex
2026-04-26 17:30:05 -05:00
LightAndy 8b2c5f30a0 ✏️ Fix typo 2026-04-26 21:48:54 +03:00
Nils DEYBACH 0fc92e1c47 fix: align limit on base 5.5 model
now that limits were fixed in base, we align azure on it
2026-04-26 20:48:00 +02:00
Nils DEYBACH d73ca9024a Merge remote-tracking branch 'upstream/dev' into PR-gpt-5.5 2026-04-26 20:45:20 +02:00
LightAndy bff48f9fde Merge branch 'anomalyco:dev' into dev 2026-04-26 21:43:13 +03:00
Aiden Cline c5c803f415 fix: ensure openai gpt-5.5 limits are exact 2026-04-26 13:38:56 -05:00
Nils DEYBACH cd69509b48 fix: simplify by extending the azure model from opeani 2026-04-26 20:04:27 +02:00
Aiden Cline 83d15fd756 Merge pull request #1574 from juls0730/dev
feat: add mimo v2.5/pro to xiaomi and openrouter providers
2026-04-26 13:55:57 -04:00
LightAndy b3c09451d9 Add gemini-3.1-flash-preview model configuration 2026-04-26 20:27:17 +03:00
Frank d98bdb5eff Merge pull request #1560 from TigerBeanst/patch-1
fix: opencode go mimo-v2.5 context limit to 1,000,000
2026-04-26 13:16:33 -04:00
Frank ea205913ce update zen models 2026-04-26 12:49:37 -04:00
Frank 3532801639 update zen models 2026-04-26 11:48:32 -04:00
Nils DEYBACH 1bb50141c2 feat(azure): add GPT-5.5 model metadata
## Summary

Adds GPT-5.5 metadata for:

- Azure
- Azure Cognitive Services

The Azure Cognitive Services entry mirrors the existing local convention of full TOML model definitions.

## Sources

- Microsoft Learn lists `gpt-5.5` for Azure OpenAI / Microsoft Foundry with version `2026-04-24`, `1,050,000` context, `922,000` input, `128,000` output, structured outputs, tools, image input, and December 2025 training data.
- Microsoft’s Azure GPT-5.5 announcement lists pricing at `$5.00` input, `$0.50` cached input, and `$30.00` output per 1M tokens.
- Azure Responses API docs list PDF input support for vision-capable models and include `gpt-5.5` version `2026-04-24`.

## Notes

This intentionally does not add `gpt-5.5-pro`, since Azure Learn currently lists `gpt-5.5` but not `gpt-5.5-pro` in the Azure model catalog.

This also intentionally omits OpenAI-specific `context_over_200k` and `experimental.modes.fast` metadata because the Azure sources confirm the standard pricing and limits, but not those OpenAI-specific fields.
2026-04-26 17:45:25 +02:00
sk fa8bdd63fb add alibaba-cn qwen3.6 max 2026-04-26 19:39:41 +08:00
sk 56f64577ce add alibaba-cn deepseek-v4 2026-04-26 19:23:04 +08:00
Nathan Nguyen f726af5767 refactor(cloudflare-ai-gateway): use [extends] for openai/gpt-5.5
The model entry duplicated every field from providers/openai/models/gpt-5.5.toml,
so any future change to the upstream OpenAI definition would silently drift here.

Switch to the `[extends] from = "openai/gpt-5.5"` form already used by sibling
providers (openrouter, requesty), omitting `experimental.modes.fast` since the
gateway does not surface the OpenAI priority service tier. Validation output is
byte-identical to the prior expanded form.
2026-04-26 13:33:39 +10:00
Zoe 4838e3cb9b feat: add mimo v2.5/pro to xiaomi and openrouter providers 2026-04-25 21:32:24 -05:00
Muhammad Mugni Hadi dbe92646c3 chore(chutes): add header comments to generated TOML files
Each generated TOML now includes a comment noting which fields are
auto-managed vs manually overridable on re-run.
2026-04-26 06:52:21 +07:00
Muhammad Mugni Hadi 4717c67054 feat(chutes): add API-driven model generator script
Add generate-chutes.ts that fetches models from https://llm.chutes.ai/v1/models
and generates/updates TOML files, following the same pattern as generate-vercel.ts.

Supports --dry-run, --new-only, and --keep-orphans flags. Auto-deletes TOML files
for models no longer in the API (with empty directory cleanup).

Preserves manually-set fields (family, knowledge, interleaved, status) when merging
with API data. Also syncs current models from the API.
2026-04-26 06:51:16 +07:00
Nathan Nguyen d4c77c14fd feat(cloudflare-ai-gateway): add openai/gpt-5.5
Mirrors the existing direct openai/gpt-5.5 entry under the
cloudflare-ai-gateway provider so opencode and other consumers can
route GPT-5.5 traffic through Cloudflare AI Gateway without hitting
ProviderModelNotFoundError.

Pricing, limits, modalities, and dates copied from
providers/openai/models/gpt-5.5.toml; provider stanza follows the
sibling gpt-5.4 entry (npm = "ai-gateway-provider").
2026-04-26 05:22:29 +10:00
Selmir Nedzibi 96b3d65307 feat(openrouter): add Gemini 3.1 flash image preview (Nano Banana 2) 2026-04-25 21:14:44 +02:00
Aiden Cline b491c29cf9 Merge pull request #1573 from zainhas/dev
[Together AI] add deepseek-v4
2026-04-25 13:47:14 -04:00
Aiden Cline d937abd849 Merge pull request #1539 from manascb1344/fix-xiaomi-provider-ids
feat: add MiMo-V2.5 and MiMo-V2.5-Pro to xiaomi-token-plan providers
2026-04-25 13:33:42 -04:00
Aiden Cline df52175b0c Merge pull request #1580 from LeGazeon/add-nvidia-deepseek-v4-pro/flash
Add NVIDIA DeepSeek-V4 models
2026-04-25 13:32:41 -04:00
Aiden Cline bee8339c07 Merge pull request #1589 from MiyakoMeow/feat/restrict-zai-zhipuai-coding-plan-models
rm: unavailable models in zai/zhipuai coding plan
2026-04-25 13:30:39 -04:00
Aiden Cline 181bf96fa3 Merge pull request #1585 from saju01/add-copilot-gpt-5.5
feat(github-copilot): add gpt-5.5
2026-04-25 13:30:16 -04:00
Aiden Cline 9d49d2fd52 Merge pull request #1587 from smakosh/claude/rebase-add-llmgateway-models-yqKLn
feat(llmgateway): add deepseek-v4-pro, deepseek-v4-flash, kimi-k2.6
2026-04-25 13:29:39 -04:00
Aiden Cline 648776aa85 Merge pull request #1590 from dpuyosa/feat/venice-models
Venice: Add GPT-5.5 and Qwen3.6 model configs
2026-04-25 13:29:03 -04:00
Aiden Cline 421cb099b0 Merge pull request #1591 from dpuyosa/fix/venice-deepseek-family
Venice: Fix DeepSeek V4 Flash family classification
2026-04-25 13:28:54 -04:00
Aiden Cline f458b19994 Merge pull request #1592 from MiyakoMeow/feat/deepseek-1m-context
fix(deepseek): all has 1M context / 384k output / adjusted price
2026-04-25 13:28:45 -04:00
MiyakoMeow d347093b03 feat(deepseek): 1M context / 384k output 2026-04-25 18:58:12 +08:00
MiyakoMeow 3328712262 feat: restrict zai/zhipuai coding plan models to glm-5.1, glm-5-turbo, glm-4.7, glm-4.5-air only
Based on official documentation:
- ZAI DevPack Coding Plan: https://docs.z.ai/devpack/overview
- Zhipu AI BigModel Coding Plan: https://docs.bigmodel.cn/cn/coding-plan/overview

Both providers only officially support the following GLM models for coding plans:
- glm-5.1
- glm-5-turbo
- glm-4.7
- glm-4.5-air

Removed unsupported models from zai-coding-plan:
- glm-4.5, glm-4.5-flash, glm-4.5v
- glm-4.6, glm-4.6v
- glm-4.7-flash, glm-4.7-flashx
- glm-5, glm-5v-turbo

Removed unsupported models from zhipuai-coding-plan:
- glm-4.5, glm-4.5-flash, glm-4.5v
- glm-4.6, glm-4.6v, glm-4.6v-flash
- glm-4.7-flash, glm-4.7-flashx
- glm-5, glm-5v-turbo
2026-04-25 18:49:10 +08:00
dpuyosa 60edc1b52d [venice] Add GPT-5.5 and Qwen3.6 model configs
- Add OpenAI GPT-5.5 with 1M context window and tiered pricing
- Add OpenAI GPT-5.5 Pro with premium pricing and 128K output limit
- Add Qwen3.6 27B with text, image, and video input modalities
2026-04-25 12:41:31 +02:00
dpuyosa eee44cd080 [venice] Fix DeepSeek V4 Flash family classification
- Correct family from "deepseek" to "deepseek-flash" for accurate model categorization
2026-04-25 12:36:06 +02:00
smakosh 048a3235e8 feat(llmgateway): add deepseek-v4-pro, deepseek-v4-flash, kimi-k2.6 2026-04-25 12:19:40 +02:00
Fernando Guarini 1db03ec1e6 feat(ollama-cloud): add deepseek-v4-flash model 2026-04-25 11:24:12 +02:00
Saju Sarangdharan 6d283349ad feat(github-copilot): add gpt-5.5
GitHub Copilot now serves gpt-5.5 (verified via GET https://api.githubcopilot.com/models with a Copilot Enterprise token). Adding the catalog row so downstream consumers (e.g. pi-ai) can route requests.
2026-04-25 10:31:21 +02:00
Abliteration.ai 7e07302ecd add abliteration.ai provider 2026-04-24 22:46:54 -07:00
LeGazeon 8bc407a617 chore: remove deepseek-v4-pro config (duplicated by #1578)
The Pro model configuration was already added via #1578 which
has been merged. Removing the duplicate from this branch to
keep only the Flash variant.
2026-04-25 13:17:12 +08:00
LeGazeon 5305d2bae2 refactor: extend flash config from deepseek base
Remove duplicated fields by inheriting common settings
from providers/deepseek base config via [extends].

This addresses the review comment in #1580
2026-04-25 13:11:26 +08:00
Aiden Cline fee96c27b9 Merge pull request #1578 from panwar-stack/dev
feat(nvidia): add DeepSeek V4 model
2026-04-25 00:41:03 -04:00
Aiden Cline 66520adbc6 Merge pull request #1577 from ezShroom/dev
add openrouter gpt-5.5
2026-04-25 00:40:34 -04:00
Zain Hasan 40714995cc Add interleaved section to DeepSeek-V4-Pro.toml 2026-04-24 18:59:45 -07:00
LeGazeon 66c4896003 Add NVIDIA DeepSeek-V4 models
Add model entries for DeepSeek V4 Pro and DeepSeek V4 Flash to the NVIDIA NIM provider.

## Changes
- Added `providers/nvidia/deepseek-v4-pro.toml`
- Added `providers/nvidia/deepseek-v4-flash.toml`

## Data Sources
- NVIDIA NIM Model Cards:
  - DeepSeek V4 Pro: https://build.nvidia.com/deepseek-ai/deepseek-v4-pro/modelcard
  - DeepSeek V4 Flash: https://build.nvidia.com/deepseek-ai/deepseek-v4-flash/modelcard
2026-04-25 09:57:43 +08:00
panwar-stack 31091f3d4e Rename deepseek-v4.toml to deepseek-v4-pro.toml 2026-04-24 17:09:12 -07:00
panwar-stack 5fe512c1b1 Follow extends pattern
Follow extends pattern
2026-04-24 17:08:49 -07:00
panwar-stack 63efa131e7 feat(nvidia): add DeepSeek V4 model
add DeepSeek V4 model
2026-04-24 17:05:12 -07:00
Shroom 29cd503070 Add gpt-5.5.toml configuration file 2026-04-25 00:08:04 +01:00
Rohan Taneja a9b704c656 Merge pull request #1575 from vercel/update-vercel-models-1777063875 2026-04-24 15:29:39 -07:00
Aiden Cline 0a88e412e5 Merge pull request #1576 from dsingal0/feat/openrouter-deepseek-v4
Add OpenRouter DeepSeek V4 models
2026-04-24 17:42:48 -04:00
Dhruv Singal b46e29ccd5 fix(openrouter): use DeepSeek reasoning content field 2026-04-24 14:06:05 -07:00
Jerilyn Zheng a181b770d6 Update kimi-k2.6.toml 2026-04-24 13:55:27 -07:00
Jerilyn Zheng fa71201f20 Update deepseek-v4-pro.toml 2026-04-24 13:54:56 -07:00
Jerilyn Zheng 3ac17aefb6 Enable open_weights in deepseek-v4-flash configuration 2026-04-24 13:54:34 -07:00
Jerilyn Zheng 1f2ceb91a5 Update qwen-3.6-max-preview.toml 2026-04-24 13:53:57 -07:00
github-actions[bot] d82681900c chore(vercel): update Vercel model definitions
Auto-generated by weekly workflow from Vercel AI Gateway API.

Co-Authored-By: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-04-24 20:51:22 +00:00
Zain Hasan 7e296f4cbd ds recommend 384,000 2026-04-24 12:39:09 -07:00
Zain Hasan f202ff51e4 Reduce output limit from 512000 to 300000 2026-04-24 12:13:53 -07:00
Zain Hasan 4085a0b536 Merge branch 'anomalyco:dev' into dev 2026-04-24 12:12:28 -07:00
Zain Hasan 935fdeca65 [Together AI] Add deepseekv4 pro 2026-04-24 12:08:33 -07:00
Frank cef8828fbe update zen models 2026-04-24 14:51:59 -04:00
Frank 9277a23a29 update zen models 2026-04-24 14:50:50 -04:00
Frank d7bfb16b0f update zen models 2026-04-24 14:42:25 -04:00
Frank 37ae6fe7c8 update zen models 2026-04-24 12:11:33 -04:00
Aiden Cline 87ce527476 Merge pull request #1571 from cgilly2fast/dev
fix(firmware): glm 5.1 name
2026-04-24 11:49:51 -04:00
Aiden Cline 34bed30fa1 Merge pull request #1567 from dsingal0/feat/openrouter-deepseek-v4
feat(openrouter): add DeepSeek V4 Pro and V4 Flash
2026-04-24 11:49:35 -04:00
Dhruv Singal 8a0c3cb75f refactor(openrouter): extend official DeepSeek V4 Pro/Flash
Use [extends] from deepseek/ with OpenRouter-specific overrides
(attachment, interleaved reasoning_details, limits).

Made-with: Cursor
2026-04-24 08:43:38 -07:00
Colby Gilbert f65460ac16 fix(firmware): glm 5.1 name 2026-04-24 08:40:19 -07:00
YoshiTabletopGamer 8ea92aed9a [alibaba] Add remaining open Qwen 3.5 models, fix Qwen-3.5 397B-A17B, add open Qwen 3.6 models
- Added Qwen 3.5 122B-A10B
- Added Qwen 3.5 27B
- Added Qwen 3.5 35B-A3B
- Fixed Qwen 3.5 397B-A17B (see below)
- Added Qwen 3.6 27b
- Added Qwen 3.6-35B-A3B

I was not able to find a reliable source for the knowledge cutoff of any of these models.
2025-04 was already set as the cutoff for Qwen 3, and Qwen 3.5 is newer.
All data is from the ModelStudio webpage.
It seems to not include audio, but the ModelStudio page clearly has an audio symbol and the model is capable of this.
And I found no data for a price for reasoning tokens in particular, unlike what was in the file for Qwen 3.5 397B-A17B.
The models are all capable of structured output.
2026-04-24 12:38:52 -03:00
Dhruv Singal f340d82fc3 feat(openrouter): add DeepSeek V4 Pro and V4 Flash
Add model configs aligned with OpenRouter pricing and limits
(1M context, 384K max output, cache read rates from provider page).

Made-with: Cursor
2026-04-24 08:25:17 -07:00
Frank c7431ae24c update zen models 2026-04-24 10:53:10 -04:00
Frank 3d1888b7b5 update zen models 2026-04-24 10:24:34 -04:00
Misha Skvortsov 16a8fa5c20 improve(atomic-chat): drop hardcoded model list per maintainer feedback
Made-with: Cursor
2026-04-24 17:20:26 +03:00
Aiden Cline dcd37ccdbb add deepseek v4 flash 2026-04-24 08:34:03 -04:00
Aiden Cline d18c3f910c Merge pull request #1562 from dpuyosa/update/venice-kimi-pricing
Venice: Update kimi-k2-6 pricing
2026-04-24 08:08:23 -04:00
Aiden Cline 2cec5a492c Merge pull request #1563 from dpuyosa/feat/venice-deepseek-v4
Venice: Add DeepSeek V4 Flash and Pro models
2026-04-24 08:08:13 -04:00
dpuyosa 61dd0ec489 [venice] Add DeepSeek V4 Flash and Pro models
- Add DeepSeek V4 Flash with 1M context, reasoning, and tool support
- Add DeepSeek V4 Pro with 1M context, reasoning, and tool support
- Set pricing and interleaved reasoning_content field for both
2026-04-24 12:21:07 +02:00
dpuyosa c7758204b5 [venice] Update kimi-k2-6 pricing
- Update input, output, and cache_read costs to current rates
- Update last_updated timestamp to 2026-04-24
2026-04-24 12:17:51 +02:00
manascb1344 ed91520aa2 feat: add MiMo-V2.5 and MiMo-V2.5-Pro to xiaomi-token-plan providers 2026-04-24 15:38:55 +05:30
Frank 3e82669a82 Merge pull request #1561 from wenbindu/dev
add deepseek new moels
2026-04-24 03:04:52 -04:00
Frank 1cc0c9c074 sync 2026-04-24 03:03:06 -04:00
TigerBeanst d73d7f6453 fix: opencode go mimo-v2.5 context limit to 1,000,000
https://platform.xiaomimimo.com/docs/pricing
2026-04-24 12:48:34 +08:00
Aiden Cline afb59f86ee Merge pull request #1557 from seffhunnn/dev
feat: add AU Sonnet and Opus models for Amazon Bedrock
2026-04-24 00:30:51 -04:00
wenbindu 05242f68d4 add deepseek new moel 2026-04-24 12:06:19 +08:00
Mohd Saif c1b029dcc1 feat: add AU Opus model for Amazon Bedrock 2026-04-24 03:26:28 +05:30
Mohd Saif bc2dd5137a feat: add AU Sonnet model for Amazon Bedrock 2026-04-24 03:25:38 +05:30
Aiden Cline 99ec4900c7 Merge pull request #1555 from brentdurksen/add-azure-claude-sonnet-4-6
feat(azure): add Claude Sonnet 4.6 model
2026-04-23 17:33:44 -04:00
Brent Durksen a8c124ac9e refactor: use extends to inherit from anthropic/claude-sonnet-4-6 2026-04-23 15:16:38 -06:00
Aiden Cline 0d20a363a9 Merge pull request #1556 from fhennerkes/dev
poe: add GPT-Image-2 model
2026-04-23 17:12:20 -04:00
fhennerkes 3ac613678b poe: add GPT-Image-2 model 2026-04-23 12:38:22 -07:00
Brent Durksen e2ead1b4e6 feat(azure): add Claude Sonnet 4.6 model 2026-04-23 13:37:50 -06:00
Aiden Cline be53c33588 Merge pull request #1550 from BlockListed/cortecs-kimi-k2.6
Add kimi k2.6 to cortecs
2026-04-23 15:26:58 -04:00
Aiden Cline 55cf5fa310 Merge pull request #1554 from mattyatea/add-gpt-5-5
[codex] Add GPT-5.5
2026-04-23 15:17:20 -04:00
mattyatea 3e0fe362f2 add gpt-5.5 model 2026-04-24 04:13:51 +09:00
BlockListed 89d06ae31f add kimi k2.6 to cortecs 2026-04-23 19:49:18 +02:00
Aiden Cline c994b116ae Merge pull request #1542 from u007/patch-1
Add Chutes: Kimi K2.6 TEE
2026-04-23 12:47:49 -04:00
Aiden Cline 833e8f7a66 Merge pull request #1548 from fernandoenzo/fix/gemma4-ollama-output-limit
fix(ollama): set gemma4:31b output limit to match context
2026-04-23 12:46:00 -04:00
Aiden Cline 32bd1427fb Merge pull request #1545 from Alex-wuhu/dev
Add deepseek, gemma, ling, llama, kimi on NovitaAI
2026-04-23 12:36:06 -04:00
Frank ae7672b87e update zen models 2026-04-23 11:11:30 -04:00
Fernando Guarini 9b27cc5a76 fix(ollama): set gemma4:31b output limit to match context
Ollama does not impose official output limits. The existing convention for Gemma models on Ollama (gemma3:4b, gemma3:12b, gemma3:27b) is to set output equal to context. gemma4:31b was the only exception with output=8192 vs context=262144.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 11:42:30 +02:00
Alex-wuhu 7014e3e318 feat: add missing Novita AI model configurations
Add 6 models served by Novita:
- deepseek/deepseek-r1-distill-qwen-14b
- deepseek/deepseek-r1-distill-qwen-32b
- google/gemma-3-12b-it
- inclusionai/ling-2.6-1t
- meta-llama/llama-3.2-3b-instruct
- moonshotai/kimi-k2.6

Capabilities, pricing, context, and modalities sourced from Novita's
/v1/models API; family slugs and release dates aligned with existing
same-model entries in the repo.
2026-04-23 14:58:43 +08:00
Frank e0e153e8d6 update zen models 2026-04-23 02:51:28 -04:00
mickalchen a0fbef93e4 revert 2026-04-23 14:41:05 +08:00
mickalchen e4a89229be add model by openrouter 2026-04-23 14:23:06 +08:00
mickalchen 9ad15e97cd add model by openrouter 2026-04-23 14:18:51 +08:00
James e3b4df4e87 Update Kimi-K2.6-TEE.toml
fix reasoning
2026-04-23 13:53:37 +08:00
Aiden Cline e3e2066c83 Merge pull request #1544 from GodTamIt/deepinfra/kimi-k2.6
deepinfra: Add Kimi-K2.6 support
2026-04-23 00:40:50 -04:00
Aiden Cline 208dcd12a2 Merge pull request #1533 from qychen2001/dev
Add Kimi-K2.6 and Qwen3.6-35B-A3B, update Kimi-K2.5 config for siliconflow and siliconflow-cn
2026-04-23 00:40:40 -04:00
Aiden Cline d166444aa1 Merge pull request #1541 from zainhas/dev
[Together AI] add Kimi k2.6 support
2026-04-23 00:40:15 -04:00
Aiden Cline cd35f96e73 Merge pull request #1528 from seffhunnn/dev
Fix incorrect model ID for Gemma 4 26B (Google provider)
2026-04-23 00:39:12 -04:00
Christopher Tam 2b0c21e0b4 deepinfra: Add Kimi-K2.6 support 2026-04-22 23:39:42 -04:00
James 787b0bf9e9 Update Kimi K2.5 TEE to Kimi K2.6 TEE 2026-04-23 10:58:39 +08:00
Zain Hasan 77fbf02ff6 remove interleaved 2026-04-22 16:19:10 -07:00
Zain Hasan 89973fd122 [Together AI] add Kimi k2.6 support 2026-04-22 16:16:08 -07:00
Frank e458a9f5b8 Merge pull request #1540 from dsingal0/feat/baseten-kimi-k2.6
feat(baseten): add Kimi K2.6
2026-04-22 16:59:51 -04:00
Dhruv Singal 61d95afae2 feat(baseten): add Kimi K2.6 2026-04-22 13:53:46 -07:00
Jack 4a2df5e008 Merge pull request #1537 from anomalyco/feat/opencode-go-mimo-v2.5
Feat/opencode go mimo-v2.5-pro & mimo-v2.5
2026-04-23 00:51:49 +08:00
Aiden Cline 3db907f3ce Merge pull request #758 from regolo-ai/dev
Add Regolo-ai Provider
2026-04-22 12:33:02 -04:00
Jack 70d8f9cc6e update mimo v2 output limits to 128k 2026-04-22 23:32:16 +08:00
Jack b9b354ada0 update mimo v2.5 output limits to 128k 2026-04-22 23:17:40 +08:00
Jack 95632ad376 remove mimo-v2.5-omni (renamed to mimo-v2.5) 2026-04-22 23:15:00 +08:00
Philip M 7153506989 Adds support for openrouter/pareto-code
The Pareto Router is a way to have OpenRouter always pick a strong coding model for your needs without committing to a specific one. You express a single min_coding_score preference between 0 and 1, and the router routes your request to a coding model that meets that bar.

The Pareto Router is tuned for coding use cases. Under the hood it keeps a curated shortlist of strong coding models currently available on OpenRouter. The exact shortlist and selection logic evolve over time as new models land and benchmarks shift.
2026-04-22 10:14:46 -05:00
Jack c73bab2e7e providers(opencode-go): rename mimo-v2.5-omni to mimo-v2.5 2026-04-22 23:14:27 +08:00
Jack a783dc808d providers(opencode-go): add mimo v2.5 models and separate v2 families 2026-04-22 23:07:40 +08:00
Daniele Scasciafratte 58e72802bc feat(models): update 2026-04-22 16:05:48 +02:00
Mohd Saif 19233d93c4 fix: remove unnecessary id field 2026-04-22 15:19:47 +05:30
QiyuanChen 7eea45e078 feat(siliconflow-cn): add Kimi-K2.6, Qwen3.6-35B-A3B and update Kimi-K2.5 config 2026-04-22 13:38:34 +08:00
QiyuanChen 001ec226f6 feat(siliconflow): add Kimi-K2.6 and update Kimi-K2.5 config 2026-04-22 13:37:59 +08:00
Jack 32461d5b44 Merge pull request #1532 from chl-0537/feature/add-tencent
Remove tencent token plan
2026-04-22 13:12:06 +08:00
mickalchen 9f078294c0 Remove tencent token plan 2026-04-22 13:07:03 +08:00
Aiden Cline c885ed49cd Merge pull request #1531 from zhiyuan1024/zhiyuan/alibaba-cn_kimi-k2.6
feat(alibaba-cn): add Kimi K2.6 model configuration
2026-04-21 23:41:29 -04:00
Aiden Cline 2fc434062f Merge pull request #1529 from compumike/compumike/fix-openrouter-openai-gpt-5.4-pricing
Fix pricing for openrouter/openai gpt-5.4-[mini,nano] off by 10^6
2026-04-21 23:40:51 -04:00
Aiden Cline dbcb7e6d69 Merge pull request #1530 from cgilly2fast/dev
feat(firmware): kimi k2.6 model
2026-04-21 23:40:22 -04:00
Zhiyuan Hou b58392fc62 feat(alibaba-cn): add Kimi K2.6 model configuration
Signed-off-by: Zhiyuan Hou <zhiyuan2048@outlook.com>
2026-04-22 10:37:37 +08:00
Frank a4818c90ca update zen models 2026-04-21 20:18:35 -04:00
Colby Gilbert 49fbdba49f feat(firmware): kimi k2.6 model 2026-04-21 17:14:46 -07:00
Mike Robbins f2dd4da7f9 Fix pricing for openrouter/openai gpt-5.4-[mini,nano] off by 10^6 2026-04-21 18:41:02 -04:00
Frank a3ed215038 update zen models 2026-04-21 17:43:38 -04:00
Mohd Saif d45df0530b fix: correct Gemma 4 26B model ID for Google provider
Updated model ID from gemma-4-26b-it to gemma-4-26b-a4b-it to match actual Gemini API. Also added missing id field and renamed the file accordingly.
2026-04-22 01:51:23 +05:30
Jack 990531258b Merge pull request #1527 from anomalyco/feat/opencode-go-kimi-k2.6-3x-name
providers(opencode-go): rename kimi k2.6
2026-04-21 22:59:26 +08:00
Jack cd2c9e3b62 providers(opencode-go): rename kimi k2.6 2026-04-21 22:54:53 +08:00
Aiden Cline a114991278 Merge pull request #1505 from rocuevas9511/feat/deepinfra-qwen-3.5-35b
feat: add Qwen 3.5 35B A3B to deepinfra
2026-04-21 10:02:27 -04:00
Aiden Cline 5ff2035cee Merge pull request #1520 from Marenz/add-deepinfra-qwen3.6-35b-a3b
Add Qwen3.6-35B-A3B to Deep Infra
2026-04-21 10:01:56 -04:00
Aiden Cline a5993cc140 Merge pull request #1515 from llc1123/chore/zenmux-update
providers(zenmux): add support for kimi k2.6
2026-04-21 10:00:06 -04:00
Aiden Cline aebe4b6cd0 Merge pull request #1517 from otterDeveloper/kimi2.6-pull
add Firework's kimi k2.6
2026-04-21 09:59:54 -04:00
Aiden Cline 214adb1154 Merge pull request #1522 from ceoAppsknight/kilo/kimi-k2.6
Added kilo/kimi-k2.6
2026-04-21 09:59:33 -04:00
Aiden Cline b301c1f8b6 Merge pull request #1523 from sk0x0y/feature/nanogpt-kimi-k2.6-qwen-3.6
feat(nano-gpt): add Kimi K2.6 and Qwen 3.6 models
2026-04-21 09:58:45 -04:00
Aiden Cline b81c8b385b Merge pull request #1507 from rocuevas9511/feat/deepinfra-qwen-3.5-397b
feat: add Qwen 3.5 397B A17B to deepinfra
2026-04-21 09:58:28 -04:00
rocuevas9511 1caa438b3e fix: remove id field (per Marenz feedback) 2026-04-21 07:35:52 -06:00
rocuevas9511 673bc92f4d fix: remove id field (per Marenz feedback) 2026-04-21 07:35:38 -06:00
Jack 0159eaa158 Merge pull request #1526 from anomalyco/feat/moonshotai-cn-kimi-k2.6
providers(moonshotai-cn): add kimi k2.6
2026-04-21 20:39:05 +08:00
Jack efdc7b9a54 providers(moonshotai-cn): add kimi k2.6 2026-04-21 20:26:19 +08:00
Jack b08721206d Merge pull request #1525 from anomalyco/feat/moonshotai-kimi-k2.6
providers(moonshotai): add kimi k2.6
2026-04-21 19:35:13 +08:00
Jack fe0d4cd9fa providers(moonshotai): add kimi k2.6 2026-04-21 19:33:06 +08:00
sk0x0y 738ad6ed70 feat(nano-gpt): add Kimi K2.6 and Qwen 3.6 model family 2026-04-21 19:22:38 +09:00
Syed Assadullah Shah 19b66fbaf2 Added kilo/kimi-k2.6 2026-04-21 15:19:17 +05:00
Mathias L. Baumann c416836497 Add Qwen3.6-35B-A3B to Deep Infra
35B-total / 3B-active MoE (256 experts, 8 routed + 1 shared).
262K native context, vision + video input, thinking mode, tool calls.
Apache 2.0, $0.20 in / $1.00 out per 1M tokens.
2026-04-21 11:58:04 +02:00
rocuevas9511 059cc4b91f fix: update model id to match DeepInfra API 2026-04-21 00:33:20 -06:00
rocuevas9511 116bd328a6 fix: update model id to match DeepInfra API 2026-04-21 00:31:22 -06:00
Frank aa30ce3ef2 update zen models 2026-04-21 02:12:27 -04:00
Frank 9533a47906 update zen models 2026-04-21 01:20:47 -04:00
Miguel Medina ad18f780f0 add firework's kimi 2.6 2026-04-20 23:12:11 -06:00
粒粒橙 a48519e557 providers(zenmux): add support for kimi k2.6 2026-04-21 10:13:22 +08:00
Aiden Cline 23f5e74392 Merge pull request #1514 from mfbalestra/add/kimi-k2.6-ollama-cloud
providers/ollama-cloud: add kimi-k2.6:cloud
2026-04-20 21:47:51 -04:00
Aiden Cline 7a50ea28a1 Merge pull request #1510 from dpuyosa/feat/venice-add-kimi-k2-6
Venice: Add Kimi K2.6 model configuration
2026-04-20 21:45:49 -04:00
mfbalestra 5944f94197 providers(ollama-cloud): add kimi-k2.6:cloud 2026-04-20 22:45:01 -03:00
Aiden Cline 98732b7d76 Merge pull request #1512 from SomeoneWithOptions/dev
add kimi-K2.6 for OpenRouter provider
2026-04-20 21:44:39 -04:00
SomeoneWithOptions c6412d7e59 add kimi-K2.6 for OpenRouter provider 2026-04-20 18:59:49 -05:00
dpuyosa b5a7a6e974 [venice] Add Kimi K2.6 model configuration
- Add new model definition for Venice provider
- Include cost, limits, and modality specs
- Enable reasoning, tool calling, and image input
2026-04-21 00:40:19 +02:00
Aiden Cline ba7c3d7b0b Merge pull request #1509 from kostiak/patch-1
Add support for Kimi-K2.6 in Kimi For Coding provider
2026-04-20 18:02:04 -04:00
Aiden Cline 53a9a2a36d Merge pull request #1508 from hanouticelina/add-kimi-k2.6-modeling
feat(huggingface): add Kimi K2.6
2026-04-20 18:01:32 -04:00
kostiak 3b6bca9b90 Add support for Kimi-K2.6 for Kimi For Coding provider 2026-04-21 00:24:51 +03:00
Celina Hanouti f5a048060f add support for Kimi-K2.6 for Hugging Face provider 2026-04-20 21:41:14 +01:00
rocuevas9511 9e6178a5e3 fix: update cost for Qwen 3.5 397B A17B 2026-04-20 13:38:45 -06:00
rocuevas9511 e4150361b3 fix: update cost for Qwen 3.5 35B A3B 2026-04-20 13:38:06 -06:00
rocuevas9511 8de0fc059d add Qwen 3.5 397B A17B to deepinfra 2026-04-20 13:34:56 -06:00
rocuevas9511 054733884f add Qwen 3.5 35B A3B to deepinfra 2026-04-20 13:32:54 -06:00
Aiden Cline 3d09981eda Merge pull request #1499 from rovo89/patch-1
[google] Fix cache_read cost in gemini-2.5-flash model
2026-04-20 14:43:53 -04:00
Aiden Cline 6877af7770 Merge pull request #1501 from mchenco/kimi-k2.6
Add Kimi K2.6 to Workers AI and AI Gateway
2026-04-20 14:41:58 -04:00
Nacho F. Lizaur 802985f76c feat: update kiro provider to use kiro-acp-ai-provider, add opus 4.7 2026-04-20 20:13:43 +02:00
mchen 794993fd48 Add Kimi K2.6 to Workers AI and AI Gateway 2026-04-20 13:54:31 -04:00
Jack 00b53a422a separate opencode-go kimi k2 families 2026-04-21 01:00:50 +08:00
Jack 2ccecb6011 Merge pull request #1500 from chl-0537/feature/add-tencent
feat: rename model
2026-04-20 22:49:09 +08:00
mickalchen 9b7e3abf00 rename model 2026-04-20 22:02:37 +08:00
Robert Vollmer 27d6a3d503 [google] Fix cache_read cost in gemini-2.5-flash model
https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash

There's no cache_read_audio, is there?
2026-04-20 15:02:54 +02:00
Lyda 6beb1f8be2 feat(302ai): standardize Claude model metadata and capabilities
- Add family field for all Claude models (claude-haiku, claude-opus, claude-sonnet)
- Standardize knowledge cutoff dates to full date format (YYYY-MM-DD)
- Enable reasoning capability for Claude Opus 4.x and Sonnet 4.x series models
- Add PDF input modality support for claude-opus-4-1-20250805
- Update claude-opus-4-7 context limit to 1,000,000 tokens
2026-04-20 16:10:52 +08:00
Lyda e0c1124fe2 feat(302ai): update GPT model capabilities and specifications
- Add structured_output capability for GPT-4.1, GPT-4o, and GPT-5 series models
- Enable reasoning capability and disable temperature for GPT-5 series models
- Update context limits: GPT-4.1 series to 1,047,576 tokens, GPT-5.4 series to 1,050,000 tokens
- Add input token limits for GPT-5 series models (272,000 or 922,000 tokens)
- Update knowledge cutoffs across GPT-5 series (2024-05-30 to 2025-08-31)
- Add PDF input modality support for GPT-4
2026-04-20 15:58:32 +08:00
Lyda bf4ceb7baa feat(302ai): update GLM model capabilities and knowledge cutoffs
- Enable reasoning capability for GLM-4.5-air, GLM-4.5, GLM-4.5V, and GLM-4.6V models
- Update knowledge cutoff to 2025-04 for GLM-4.5, GLM-4.5V, GLM-4.6, GLM-4.6V, and GLM-4.7
- Add video input modality support for GLM-4.5V and GLM-4.6V
- Add structured_output capability for GLM-5-turbo and GLM-5.1
- Add interleaved reasoning_content field for GLM-4.7, GLM-5, GLM-5-turbo, GLM-5.1, and GLM-5V-turbo
2026-04-20 15:48:29 +08:00
Aiden Cline 1a41934e55 Merge pull request #1448 from Lydanne/dev
feat(302ai): supplement commonly missing models
2026-04-19 22:19:18 -05:00
Aiden Cline aeb4caec9f Merge pull request #1488 from Sewer56/add-wafer-provider
Add wafer.ai provider
2026-04-19 22:19:06 -05:00
Aiden Cline ccb8dcc65f Merge pull request #1493 from rovo89/patch-1
Add context_over_200k for gemini-2.5-pro and adjust cache_read costs
2026-04-19 22:17:45 -05:00
Lyda 435ec1df7b feat(302ai): add claude-opus-4-7 model 2026-04-20 11:14:27 +08:00
Robert Vollmer 7c9d609143 Add context_over_200k for gemini-2.5-pro and adjust cache_read costs
https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro
https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models-2.5 (rounds 0.125 to 0.13)
2026-04-20 00:09:11 +02:00
Aiden Cline add7947164 Merge pull request #1492 from dpuyosa/feat/venice-add-gemma4-uncensored
Venice: Add Gemma 4 and Venice Uncensored 1.2 models
2026-04-19 16:52:28 -05:00
Aiden Cline dd0c1af12a Merge pull request #1491 from dpuyosa/chore/venice-pricing-update
Venice: Update pricing for Grok 4.20 and Qwen3.5 9B
2026-04-19 16:52:15 -05:00
Aiden Cline 0c93cc03be Merge pull request #1485 from anomalyco/more-extends-cases
migrate more providers to extends format
2026-04-19 16:51:58 -05:00
Aiden Cline 62e25b73f8 Merge branch 'dev' into more-extends-cases 2026-04-19 16:47:05 -05:00
Aiden Cline 17093e0031 Merge pull request #1489 from berget-ai/update/berget-prices-gemma4
chore: update berget.ai models - prices and Gemma 4
2026-04-19 16:42:06 -05:00
Aiden Cline ae542978f0 Merge pull request #1490 from BlockListed/cortecs-add-claude-opus-4-7
add claude opus 4.7
2026-04-19 16:41:36 -05:00
dpuyosa 7f16117bba [venice] Add Gemma 4 and Venice Uncensored 1.2 models
- Add Gemma 4 Uncensored with 256K context, image support
- Add Venice Uncensored 1.2 with 128K context, image support
- Both models support tool calls and structured output
2026-04-19 23:41:17 +02:00
dpuyosa 2b96a2d3d6 [venice-models] Update pricing for Grok 4.20 and Qwen3.5 9B
- Update cache_read pricing for Grok 4.20 context_over_200k (0.23 → 0.45)
- Update input cost for Qwen3.5 9B (0.05 → 0.1)
2026-04-19 23:38:20 +02:00
BlockListed 9799a841c6 add claude opus 4.7
yes this model id is correct, cortecs is weird.
2026-04-19 23:13:58 +02:00
Christian Landgren 71c59b4235 chore: update berget.ai models - prices and Gemma 4
- Add Google Gemma 4 31B Instruct model
- Update prices for existing models (EUR to USD conversion)
- Remove non-coding models (bge-reranker, multilingual-e5 embeddings, kb-whisper)
- Remove deprecated Llama-3.1-8B-Instruct

Updated models:
- GLM-4.7: 0.77/2.75 USD/M (was 0.7/2.3)
- Llama-3.3-70B: 0.99/0.99 USD/M (was 0.9/0.9)
- Mistral-Small-3.2: 0.33/0.33 USD/M (was 0.3/0.3)
- GPT-OSS-120B: 0.44/0.99 USD/M (was 0.3/0.9)

New models:
- Gemma-4-31B-it: 0.275/0.55 USD/M

Removed models (not relevant for coding):
- BAAI/bge-reranker-v2-m3 (reranker)
- intfloat/multilingual-e5-large/* (embeddings)
- KBLab/kb-whisper-large (speech-to-text)
- meta-llama/Llama-3.1-8B-Instruct (deprecated)
2026-04-19 12:19:32 +02:00
Sewer56 0568b412aa Add wafer.ai provider with GLM-5.1 and Qwen3.5-397B-A17B models 2026-04-19 03:02:04 +01:00
Aiden Cline 812612465a Merge pull request #1484 from smakosh/feat/llmgateway-new-models
feat: update LLM Gateway to 182 models
2026-04-18 18:37:26 -05:00
Aiden Cline ac8a79dd74 Merge pull request #1487 from WJQSERVER/add/nvidia(nim)-z-ai-glm-5.1
Add Z.AI GLM-5.1 to NVIDIA(NIM)
2026-04-18 18:36:55 -05:00
smakosh 9460d981d4 fix: replace broken extends with concrete glm-4.6v-flash def
zhipuai/glm-4.6v-flash.toml is a symlink to zai/models/glm-4.6v-flash.toml
which does not exist, causing validate to fail with 'Unable to resolve
extends.from'. Inline the concrete definition instead.
2026-04-18 13:36:52 +02:00
smakosh 91db9d81ec feat: update LLM Gateway to 182 models
- Uses extends to reference canonical providers where
  possible (116 models), keeping 66 full definitions
- Only includes active text/chat models
- Adds new models: Claude Opus 4.7, Grok 4 Fast,
  Kimi K2, Mimo V2, GLM 5.1, Qwen 3 Coder, and more

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-18 13:20:41 +02:00
Jack d8d5f08df6 Merge pull request #1486 from chl-0537/feature/add-tencent
feat: add new provider and model
2026-04-18 17:30:53 +08:00
WJQSERVER 11d5443ab1 follow the nim modelcard change context length to 131072
https://build.nvidia.com/z-ai/glm-5.1/modelcard
Other Properties Related to Input: Supports multi-turn conversations, tool calling, system prompts, and extended agentic sessions. Input context length: 131,072 tokens.
2026-04-18 16:48:29 +08:00
wjqserver 90558e9eed add glm-5.1 2026-04-18 16:41:02 +08:00
Aiden Cline cb7d258e33 migrate more providers to extends format 2026-04-17 23:02:34 -05:00
Frank 2af43dc4f8 update zen models 2026-04-17 19:08:05 -04:00
Aiden Cline 93ddb6b131 Merge pull request #1482 from sopial42/ovhcloud/update-models-clean
chore(ovhcloud): remove 3 models no longer available in AI Endpoints
2026-04-17 16:50:53 -05:00
Aiden Cline 04bf671f18 Merge pull request #1481 from Spherrrical/add-digitalocean-provider
feat(provider): add DigitalOcean provider
2026-04-17 16:49:44 -05:00
Aiden Cline 1f3ba4ba21 Merge pull request #1483 from anomalyco/add-extends-support
feat: add extends support
2026-04-17 16:49:23 -05:00
Aiden Cline 305bdb6cdc Merge branch 'dev' into add-extends-support 2026-04-17 16:22:41 -05:00
Aiden Cline 2e5b4b44ae update some modes 2026-04-17 16:22:14 -05:00
aadhondt bb1c08dd41 chore(ovhcloud): remove 3 models no longer available in AI Endpoints
- deepseek-r1-distill-llama-70b
- mixtral-8x7b-instruct-v0.1
- qwen2.5-coder-32b-instruct

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-17 22:38:35 +02:00
Spherrrical 86d0f14397 feat(digitalocean): add DigitalOcean Gradient AI Platform provider
Adds the DigitalOcean provider with 46 models (Anthropic, OpenAI,
Arcee, fal, and DO-hosted open-source/embedding models) served via
the OpenAI-compatible endpoint at https://inference.do-ai.run/v1.
2026-04-17 13:07:47 -07:00
Aiden Cline f93c1a8998 Merge pull request #1478 from Kaspazza/dev
Add Github Copilot Claude Opus 4.7
2026-04-17 15:01:04 -05:00
Aiden Cline 27a6758eb7 new gen script 2026-04-17 14:57:57 -05:00
Aiden Cline 9dbafb81fa add script 2026-04-17 14:57:41 -05:00
Aiden Cline 419f8a3a20 add migration checker script 2026-04-17 14:57:32 -05:00
Aiden Cline 785a091073 Merge pull request #1480 from nicocasaisd/openai/remove-deprecated-codex-mini-latest
chore(openai): remove deprecated model codex-mini-latest
2026-04-17 14:52:34 -05:00
nicocasaisd ad2409dce1 chore(openai): remove deprecated model codex-mini-latest 2026-04-17 15:35:43 -03:00
kaspazza 63450ab67d Add Github Copilot Claude Opus 4.7 2026-04-17 20:19:36 +02:00
Aiden Cline 4002cb6739 model 2026-04-17 13:11:51 -05:00
Aiden Cline 72fa27a91e Merge pull request #1474 from vglafirov/add-gitlab-duo-chat-opus-4-7
feat(gitlab): add duo-chat-opus-4-7 model definition
2026-04-17 12:37:36 -05:00
Aiden Cline ddb3a0ff05 update agents.md 2026-04-17 12:14:04 -05:00
Aiden Cline 96c12042bc remeda 2026-04-17 12:13:54 -05:00
Misha Skvortsov 7336b3619c atomic-chat: add provider with initial blessed models
Adds Atomic Chat as a local OpenAI-compatible provider at
http://127.0.0.1:1337/v1. Includes logo and three curated models:

- unsloth/Qwen3.5-9B-IQ4_XS  (id: Qwen3_5-9B-IQ4_XS)
- unsloth/gemma-4-E4B-it-IQ4_XS  (id: gemma-4-E4B-it-IQ4_XS)
- unsloth/MiniMax-M2.5-UD-TQ1_0  (id: MiniMax-M2_5-UD-TQ1_0)

Model ids match the normalized form returned by Atomic Chat's
/v1/models endpoint (dots replaced with underscores).

Made-with: Cursor
2026-04-17 13:03:53 +03:00
mickalchen 73b81ac027 add tencent provider 2026-04-17 17:27:35 +08:00
Vladimir Glafirov 9c5839a414 feat(gitlab): add duo-chat-opus-4-7 model definition 2026-04-17 08:54:07 +02:00
Aiden Cline 721464bc3c Merge pull request #1469 from GrahamCampbell/ops-4-7-fixes
Corrected and normalized claude opus 4.7 knowledge cut-off dates
2026-04-16 22:30:13 -05:00
Aiden Cline b6b45a9d25 Merge pull request #1463 from GrahamCampbell/claude-4-6
Correct Anthropic Claude 4.6 model knowledge cut-off dates
2026-04-16 21:36:19 -05:00
Aiden Cline 7b8f98bb23 Merge pull request #1471 from cfbender/fix/openrouter-opus-4-7
feat: add openrouter opus 4.7
2026-04-16 21:35:52 -05:00
Aiden Cline 92ac48b07f Merge pull request #1473 from fhennerkes/dev
Poe: add Claude-Opus-4.7
2026-04-16 20:57:21 -05:00
fhennerkes 36a455ce4a Merge branch 'anomalyco:dev' into dev 2026-04-16 18:11:32 -07:00
fhennerkes 0bf5c60319 poe: add Claude-Opus-4.7 model
Add new Anthropic model from Poe API (released 2026-04-15):
- Reasoning support
- 1M context window with 128K output
- Cost: $4.3/M input, $21/M output, $0.43/M cache read, $5.4/M cache write
- Modalities: text, image, pdf
2026-04-16 18:08:02 -07:00
Kit Langton b123711494 Merge pull request #1472 from elithrar/patch-4
cloudflare: add opus 4.7
2026-04-16 19:38:46 -04:00
Matt Silverlock 832064c1d1 cloudflare: add opus 4.7 2026-04-16 18:51:54 -04:00
Cody Bender c16e1c817b fix: add openrouter opus 4.7 2026-04-16 18:38:36 -04:00
Aiden Cline 8aaf31711b Merge pull request #1468 from heimoshuiyu/fix/opus-4-7-temperature
fix: set temperature=false for Claude Opus 4.7
2026-04-16 14:34:52 -05:00
Graham Campbell ca6acf0b3e Corrected and normalized claude opus 4.7 knowledge cut-off dates 2026-04-16 20:33:49 +01:00
heimoshuiyu 660a672647 fix: set temperature=false for firmware and venice Opus 4.7 2026-04-17 03:23:11 +08:00
heimoshuiyu 147cb3138a fix: set temperature=false for Claude Opus 4.7 across all providers 2026-04-17 03:22:33 +08:00
Aiden Cline 5c1fb729fd Merge pull request #1462 from dpuyosa/dev
Venice: Add Claude Opus 4.7 and remove deprecated models
2026-04-16 14:10:03 -05:00
Aiden Cline 0d34900078 Merge pull request #1464 from cgilly2fast/dev
feat(firmware): opus 4.7 remove old claude models
2026-04-16 14:09:39 -05:00
Aiden Cline 4bc71918f5 Merge pull request #1467 from vercel/update-vercel-models-20260416-1812
Update Vercel models
2026-04-16 13:34:40 -05:00
Jerilyn Zheng 6f62522505 Set temperature to false in claude-opus-4.7 configuration
Changed temperature setting from true to false.
2026-04-16 11:23:29 -07:00
Aiden Cline 7680a1d169 Merge pull request #1466 from vercel/fix-reranking-type-upstream
fix(vercel): accept reranking model type from API
2026-04-16 13:22:29 -05:00
github-actions[bot] bdc15a57ce chore(vercel): update Vercel model definitions
Auto-generated by weekly workflow from Vercel AI Gateway API.

Co-Authored-By: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-04-16 18:12:52 +00:00
R-Taneja c7d324fed8 fix(vercel): accept reranking model type from API
The Vercel AI Gateway API now returns models with type "reranking",
which caused the generate-vercel script to fail schema validation.

Add "reranking" to the ModelType enum and skip these models in the
main loop, matching the existing pattern for image/video types that
OpenCode does not consume.
2026-04-16 11:05:26 -07:00
Colby Gilbert 863bada2cf feat(firmware): opus 4.7 remove old claude models 2026-04-16 10:37:52 -07:00
dpuyosa 28c4af0631 [venice] Add Claude Opus 4.7 and update Qwen models
- Add Claude Opus 4.7 with 1M context, 128K output, multimodal support
- Update Qwen 3.5 35B and 397B to open_weights=true and refresh last_updated
- Remove deprecated models: Grok Code Fast 1, Mercury Edit 2, MiniMax M2.1
2026-04-16 18:30:45 +02:00
Aiden Cline 38f6b7dfc5 Merge pull request #1456 from Snat3r/dev
Add GML5.1.toml model to cortecs provider
2026-04-16 11:16:51 -05:00
Aiden Cline 1ba010f66e Merge pull request #1461 from llc1123/chore/zenmux-update
chore(zenmux): add claude-opus-4.7
2026-04-16 11:16:41 -05:00
粒粒橙 132a5ade8d chore(zenmux): add claude-opus-4.7 2026-04-17 00:02:58 +08:00
Graham Campbell 2ef2b10847 Correct anthropic 4.6 knowledge cut-off dates 2026-04-16 16:52:15 +01:00
Frank 87e1dcb70f update zen modles 2026-04-16 11:31:20 -04:00
Aiden Cline 43d2e058d9 Merge pull request #1449 from shikbupt/alibaba-glm5.1
add alibaba-cn glm5.1
2026-04-16 10:25:58 -05:00
Aiden Cline 0a6c2ca49d Merge pull request #1459 from itsnebulalol/dev
feat: add anthropic claude opus 4.7 models
2026-04-16 10:25:04 -05:00
Dominic Frye 2f954fc838 feat: add anthropic claude opus 4.7 models 2026-04-16 11:19:19 -04:00
Frank 91b7851971 update zen models 2026-04-16 04:51:30 -04:00
Jack 80e23ab90e Merge pull request #1266 from lioZ129/feature/add-hpc-ai-provider
feat: add HPC-AI model provider support
2026-04-16 15:09:44 +08:00
Snat3r 6e574da2e4 Update input modalities in minimax-M2.7.toml 2026-04-16 08:21:20 +02:00
Snat3r 5b68565783 Add MiniMax-M2.7 model configuration file cortecs 2026-04-16 08:19:51 +02:00
lioZ129 65dafb56a3 add [cost] and glm5.1 support 2026-04-16 14:13:27 +08:00
Snat3r 32c0c88600 Update context and output limits in glm-5.1.toml 2026-04-16 08:08:09 +02:00
Snat3r d911b6f610 Add GLM-5.1 model configuration file 2026-04-16 08:06:37 +02:00
Aiden Cline 5cf28a566f Merge pull request #1424 from WJQSERVER/feat/nvidia-minimax-m2.7
Add MiniMax M2.7 to NVIDIA(NIM)
2026-04-15 20:19:01 -05:00
Aiden Cline 52cdb783a1 Merge pull request #1452 from wwth8819/dev
For aihubmix add GPT-5.4 \ GPT-5.4-mini, remove Incorrect value from old models, update cost
2026-04-15 20:18:24 -05:00
wwth8819 4a14ce5ae6 Remove temperature setting from gpt-5.2-codex.toml
Removed the temperature setting from the configuration.
2026-04-16 03:12:14 +08:00
wwth8819 f17c352027 Update cost values in coding-glm-4.7.toml 2026-04-16 03:11:16 +08:00
wwth8819 46ec19ab02 add gpt-5.4-mini gpt-5.4 2026-04-16 03:09:26 +08:00
Frank f12aae094e update zen models 2026-04-15 10:55:02 -04:00
sk 377d0f1c8d add alibaba-cn glm5.1 2026-04-15 22:02:52 +08:00
WJQSERVER 884b799012 Merge branch 'dev' into feat/nvidia-minimax-m2.7 2026-04-15 21:53:54 +08:00
Lyda ac7e35af4e feat(302ai): supplement commonly missing models 2026-04-15 17:32:18 +08:00
Frank 6f04d267cf update zen models 2026-04-15 02:17:31 -04:00
Aiden Cline a0b89e739b Merge pull request #1425 from ceyhanmolla/add-minimax-m2.7-nvidia
feat(nvidia): add MiniMax-M2.7
2026-04-14 22:59:38 -05:00
Frank 0ce000a521 update go models 2026-04-14 23:09:06 -04:00
Frank 4b7dda6cc6 update go models 2026-04-14 22:50:12 -04:00
Aiden Cline 7220310828 Merge pull request #1447 from Sawyerb/dev
Removed deprecated models and added ME2 to all relevant providers.
2026-04-14 21:49:22 -05:00
Aiden Cline 15746b9845 Merge pull request #1444 from wwth8819/dev
Add glm-5.1,  coding-glm-5.1  TO  AiHubMix
2026-04-14 21:49:06 -05:00
Aiden Cline e9be42b4bc Merge pull request #1443 from teodortomas/add-minimax-m2.7
add minimax-m2p7 to fireworks-ai provider
2026-04-14 17:11:09 -05:00
Aiden Cline c0d21d802f Merge pull request #1429 from Lee-Si-Yoon/fix/cache-read-friendli
fix: cache read costs for friendliAI models
2026-04-14 17:10:56 -05:00
Aiden Cline 4937952a52 Merge pull request #1437 from Ardakilic/dev
feat: kilo gateway: elephant alpha
2026-04-14 17:10:37 -05:00
Aiden Cline 1bb5deadea Merge pull request #1439 from fhennerkes/dev
poe: update models with pricing, deprecations, and display name fixes
2026-04-14 17:10:26 -05:00
Aiden Cline c2ad18c87d Merge pull request #1445 from cantalupo555/chore/openrouter-remove-deprecated-free-models
chore(openrouter): remove deprecated free-tier models no longer available via API
2026-04-14 17:10:01 -05:00
Sawyer e4b0a53e26 Removed deprecated models and added ME2 to all relevant providers. 2026-04-14 12:33:35 -07:00
cantalupo555 61ea2e2093 chore(openrouter): remove deprecated free-tier models no longer available via API 2026-04-14 08:11:45 -03:00
wwth8819 162fd8b72b Add configuration for Coding-GLM-5.1 model 2026-04-14 17:35:23 +08:00
wwth8819 b8fae048db Add GLM-5.1 model configuration file 2026-04-14 17:32:59 +08:00
Teodor Tomáš ca6cf794c1 add minimax-m2p7 to fireworks-ai provider 2026-04-14 11:06:47 +02:00
fhennerkes 152b401976 poe: update models with pricing, deprecations, and display name fixes
Mark 11 models no longer on the Poe API as deprecated:
- anthropic: claude-sonnet-3.5, claude-sonnet-3.5-june
- cerebras: qwen3-235b-2507-cs, qwen3-32b-cs, llama-3.3-70b-cs
- google: gemini-3-pro, gemini-deep-research
- novita: glm-4.7
- openai: chatgpt-4o-latest, gpt-4-classic-0314, gpt-4-classic

Update existing models with latest API data:
- Cerebras (gpt-oss-120b-cs, llama-3.1-8b-cs): Add pricing and correct context (128K)
- kimi-k2.5: Add pricing, fix display name, temperature/reasoning from API
- gpt-4o: Fix output formatting (8_192)
- gpt-5.1-codex-max: Fix display name

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-13 16:55:18 -07:00
Nacho F. Lizaur 8f340e1eb2 feat: update kiro provider to use kiro-ai-provider npm package 2026-04-13 23:12:11 +02:00
Aiden Cline d99a1581df Merge pull request #1435 from cantalupo555/feat/add-openrouter-elephant-alpha
feat(openrouter): add Elephant Alpha model
2026-04-13 15:01:55 -05:00
Nacho F. Lizaur 62da5b0cbd feat: enable reasoning on Kiro Claude models 2026-04-13 19:49:25 +02:00
Nacho F. Lizaur 4e49abc10c feat: add Kiro provider 2026-04-13 19:49:25 +02:00
Arda Kilicdagi 21cf1fb1e9 feat: kilo gateway: elephant alpha 2026-04-13 20:39:54 +03:00
cantalupo555 970a00c3ad feat(openrouter): add Elephant Alpha model 2026-04-13 13:43:56 -03:00
cantalupo555 d611fc2ef7 feat(core): add elephant model family 2026-04-13 13:35:10 -03:00
Aiden Cline 7d7711878d Merge pull request #1434 from cantalupo555/chore/openrouter-step-3.5-flash-free
chore(openrouter): remove Step 3.5 Flash free-tier model
2026-04-13 10:45:25 -05:00
cantalupo555 fc5d5ec67f chore(openrouter): remove deprecated step-3.5-flash free-tier variant
- Remove the free-tier variant of Step 3.5 Flash as it is no longer needed
2026-04-13 11:51:10 -03:00
Aiden Cline bd5050a15f Merge pull request #1423 from spiffytech/dev
Add Synthetic support for GLM-5.1
2026-04-13 09:18:49 -05:00
Aiden Cline ac67c648a2 Merge pull request #1422 from hanouticelina/add-minimax-2.7-huggingface
feat(huggingface): add MiniMax-M2.7
2026-04-13 09:18:35 -05:00
Aiden Cline f58038fc21 Merge pull request #1421 from zainhas/dev
[Together AI]add minimax m2.7
2026-04-13 09:18:14 -05:00
Aiden Cline 3ea7d56b96 Merge pull request #1428 from dpuyosa/feat/venice-glm-5-models
Venice: Add Z-AI GLM-5 Turbo and GLM-5V Turbo models
2026-04-13 09:17:45 -05:00
Aiden Cline e23657368e Merge pull request #1426 from dpuyosa/venice/update-model-configs-0412
Venice: Update model configs and pricing
2026-04-13 09:17:33 -05:00
Aiden Cline d59ad3ffa3 Merge pull request #1427 from dpuyosa/refactor/venice-model-naming
Venice: Update model naming convention
2026-04-13 09:17:08 -05:00
siyoon dcbb415960 fix: add cache_read parameter to cost section 2026-04-13 16:05:36 +09:00
dpuyosa e302956dc4 [venice] Update model naming convention
- Rename files to use dashes instead of dots
- Rename opus/sonnet 45 to 4-5 format
- Remove beta suffix from Grok 4.20 models
- Update family from grok-beta to grok
- Remove knowledge field from Claude models
- Update output limits
2026-04-13 01:10:06 +02:00
dpuyosa 5d100a8243 [venice] Add Z-AI GLM-5 Turbo and GLM-5V Turbo models
- Add Z-AI GLM-5 Turbo (text-only, reasoning, tool_call)

- Add Z-AI GLM-5V Turbo (vision, reasoning, tool_call)
2026-04-13 01:05:47 +02:00
dpuyosa 9ff52ee539 [venice] Update model configs and pricing
- Update last_updated dates for 5 models

- Set open_weights to false for 4 models

- Add context_over_200k cache pricing for qwen-3-6-plus
2026-04-13 00:59:21 +02:00
ceyhanmolla 8114522671 feat(nvidia): add MiniMax-M2.7 2026-04-12 16:56:04 +02:00
wjqserver 5e534d84bc feat: add NVIDIA MiniMax M2.7 model 2026-04-12 22:51:46 +08:00
spiffytech 1f79cd8fd0 Added Synthetic support for GLM-5.1 2026-04-12 08:46:10 -04:00
Celina Hanouti 462b822e60 add minimax M2.7 for hugging face provider 2026-04-12 11:06:30 +02:00
Zain Hasan 8021e1afd0 Merge branch 'anomalyco:dev' into dev 2026-04-11 22:23:20 -07:00
Zain Hasan 304d85fa43 [Together AI]add minimax m2.7 2026-04-11 22:14:05 -07:00
Aiden Cline f07262370f Merge pull request #1418 from Ardakilic/dev
Kilo Gateway: Sync model list with upstream (2026-04-11)
2026-04-11 16:48:46 -05:00
Aiden Cline 7cfaa0393e Merge pull request #1419 from nicopujia/add-openrouter-deepseek-r1
Add OpenRouter support for DeepSeek R1
2026-04-11 16:46:58 -05:00
Arda Kilicdagi c93de9f54f chore: sync all kilo gw models 2026-04-11 03:31:00 +03:00
Aiden Cline 2b17d9efc2 Merge pull request #1414 from Ardakilic/dev
Feat: Kilo Gateway: Add MiniMax M2.7
2026-04-10 13:31:50 -05:00
Arda Kilicdagi 8d8521e0e1 feat: kilo gateway: MiniMax M2.7 2026-04-10 20:42:45 +03:00
Aiden Cline c9f22d26b9 Merge pull request #1413 from Ardakilic/dev
Kilo Gateway: Add GLM 5.1, Remove MiniMax M2.5 Free
2026-04-10 10:33:18 -05:00
Aiden Cline 61e8ea2a2e Merge pull request #1410 from gjtiquia/dev
Poe: add GLM-5 model
2026-04-10 10:26:57 -05:00
Aiden Cline 7d2cd9818f Merge pull request #1411 from Alex-wuhu/dev
novita-ai: add 8 new models and remove 2 deprecated models
2026-04-10 10:26:45 -05:00
Arda Kilicdagi 385b4fbcf6 feat: kilo gateway: glm-5.1 2026-04-10 15:11:37 +03:00
Alex-wuhu 2f0890c9a9 Add new model configurations for Gemma, MiniMax, Qwen, and GLM 2026-04-10 16:28:34 +08:00
GJ Tiquia 9d377b768f poe: GLM-5 temperature set to true 2026-04-10 15:57:25 +08:00
GJ Tiquia aa4f3f550a poe: add GLM-5 model 2026-04-10 14:13:03 +08:00
Aiden Cline f82d6fc61a Merge pull request #1404 from nicopujia/add-openrouter-qwen3.5-flash-02-23
Add OpenRouter support for Qwen3.5 Flash 2026-02-23
2026-04-09 22:37:05 -05:00
Aiden Cline 4222b040b7 Merge pull request #1407 from line72/deepinfra-glm-5.1
[DeepInfra] Add GLM 5.1
2026-04-09 22:36:53 -05:00
Aiden Cline d2e4174103 Merge pull request #1397 from qychen2001/dev
Add GLM-5.1 and GLM-5V-Turbo model configurations for siliconflow
2026-04-09 22:35:52 -05:00
Aiden Cline f30b5fc754 Merge pull request #1408 from nanai10a/dev
Add MiniMax M2.5 (free) configuration file
2026-04-09 22:35:37 -05:00
Aiden Cline 10239c95e2 Merge pull request #1401 from dpuyosa/venice-open-weights-fix
Venice: Remove private field fallback for open weights
2026-04-09 20:05:03 -05:00
Aiden Cline 59831a9a0e Merge pull request #1399 from dpuyosa/venice-model-updates-2026-04-09
Venice: Update model configs with refreshed pricing and limits
2026-04-09 20:04:55 -05:00
Aiden Cline c7552d0e00 Merge pull request #1396 from shelvick/add-azure-grok-4-20
Add Grok 4.20 reasoning and non-reasoning to Azure
2026-04-09 20:04:04 -05:00
Aiden Cline 76d53c9e96 Merge pull request #1382 from cgilly2fast/dev
feat(firmware): add zai 5.1 and qwen 3.6 plus
2026-04-09 20:03:50 -05:00
Aiden Cline 61573f666a Merge pull request #1395 from zainhas/dev
[Together AI] add GLM-5.1 + Gemma 4 31B it
2026-04-09 20:03:13 -05:00
Aiden Cline 1d30640400 Merge branch 'dev' into dev 2026-04-09 20:02:59 -05:00
Aiden Cline 1f1eafe173 Merge pull request #1406 from riccardogiorato/dev
Update GLM to version 5.1 for together provider
2026-04-09 20:02:08 -05:00
Aiden Cline a75c0f0fe9 Merge pull request #1400 from dpuyosa/venice-add-new-models
Venice: Add 4 new AI models
2026-04-09 17:34:55 -05:00
Marcus Dillavou 57c6d817d5 DeepInfra: Add GLM 5.1 2026-04-09 15:50:04 -05:00
Riccardo Giorato 3d1d77da76 Merge pull request #2 from riccardogiorato/orchestrator/add-glm-5-1-together-r8k9f
add GLM-5.1 for together provider
2026-04-09 22:42:54 +02:00
orchestrator-build[bot] e7cfed72ff fix GLM-5.1 open_weights to true 2026-04-09 20:40:20 +00:00
orchestrator-build[bot] b748364a20 fix GLM-5.1 pricing for together provider 2026-04-09 20:39:49 +00:00
orchestrator-build[bot] 30439f4409 replace GLM-5 with GLM-5.1 for together provider 2026-04-09 20:37:34 +00:00
orchestrator-build[bot] 7baad3cc22 add GLM-5.1 for together provider 2026-04-09 20:35:51 +00:00
Nicolás Pujia 564992885b Add OpenRouter support for DeepSeek R1 2026-04-09 11:54:16 -03:00
Nicolás Pujia 57a53889db Add OpenRouter support for Qwen3.5 Flash 2026-02-23 2026-04-09 11:53:53 -03:00
Nanai Jua 0f019a5e9a Add MiniMax M2.5 (free) configuration file
https://openrouter.ai/provider/open-inference
2026-04-09 18:11:40 +09:00
dpuyosa d6fec11252 [venice] Remove private field fallback for open weights
- Rely solely on modelSource for open weights detection
- Remove privacy field fallback per new ZDR policies
2026-04-09 11:03:03 +02:00
dpuyosa 7604313114 [venice] Add 4 new AI models
- Add Mercury 2 (reasoning model)
- Add Mistral Small 4 (multimodal)
- Add Nemotron Cascade 2 30B A3B
- Add Qwen 3.5 397B (multimodal)
2026-04-09 10:31:24 +02:00
dpuyosa c3a2b1a1db [venice] Update model configs with refreshed pricing and limits
- Update last_updated dates to 2026-04-09 across 6 models
- Adjust Grok pricing to reflect current rates
- Add context_over_200k pricing for Qwen 3.6 Plus
- Correct Gemma 4 output limits from 12288 to 8192
- Rename Qwen 3.6 Plus to "Uncensored" variant
2026-04-09 10:17:05 +02:00
QiyuanChen 68294f3bd6 Add GLM-5V-Turbo model configuration for siliconflow provider 2026-04-09 11:18:25 +08:00
QiyuanChen ad10ce6232 Add GLM-5.1 model configuration files for siliconflow provider 2026-04-09 11:08:53 +08:00
Scott Helvick 5a09420d65 Add Grok 4.20 reasoning and non-reasoning to Azure 2026-04-09 02:30:55 +00:00
Zain Hasan f1b3177ff7 add gemma 4 31b instruct 2026-04-08 18:49:38 -07:00
Zain Hasan a7d0152fd1 [Together AI] add GLM-5.1 2026-04-08 17:55:11 -07:00
Aiden Cline 46c6aef51b Merge pull request #1393 from spiffytech/dev
Add Synthetic support for GLM-5 and Nemotron 3 Super
2026-04-08 16:01:12 -05:00
Aiden Cline 7c34bf01b5 Merge pull request #1394 from spiffytech/ollama-changes
Add Ollama Cloud support for Gemma 4. Updated properties on Gemini 3 Flash
2026-04-08 16:00:12 -05:00
spiffytech 5ce20c0978 Added Ollama Cloud support for Gemma 4. Updated properties on Gemini 3 Flash. 2026-04-08 15:03:29 -04:00
spiffytech 6055551b33 Added Synthetic support for GLM-5 and Nemotron 3 Super 2026-04-08 14:57:51 -04:00
Aiden Cline a96094c059 Merge pull request #1390 from GoGoris/add-qwen3-coder-next-cortecs
Add qwen3-coder-next model for cortecs
2026-04-08 11:26:42 -05:00
Aiden Cline 39e86eb055 Merge pull request #1384 from dpuyosa/feat/add-venice-claude-opus-4-6-fast-glm-5-1
Venice: Add Claude Opus 4.6 Fast and GLM 5.1 models
2026-04-08 11:25:56 -05:00
Aiden Cline 119f421437 Merge pull request #1387 from cantalupo555/feat/add-gemma-4-free-openrouter
feat(openrouter): add Gemma 4 free models
2026-04-08 11:25:30 -05:00
Aiden Cline 6ab4c1be04 Merge pull request #1386 from cantalupo555/chore/remove-qwen3.6-plus-free-openrouter
chore(openrouter): remove discontinued Qwen3.6 Plus free
2026-04-08 11:25:15 -05:00
Aiden Cline f1eaa4bd9d Merge pull request #1392 from Solidsilver/feat/fireworks-add-glm-5-1-qwen-3-6-plus
feat(fireworks): add GLM 5.1 and Qwen 3.6 Plus models
2026-04-08 11:24:52 -05:00
Aiden Cline 2f4693b9cf Merge pull request #1391 from CassiusXiang/fix/openrouter-qwen3.6-plus
fix(openrouter): replace discontinued qwen3.6-plus free with paid model
2026-04-08 11:24:41 -05:00
Luke M 5c867d5fba feat(fireworks): add GLM 5.1 and Qwen 3.6 Plus models 2026-04-08 09:06:50 -07:00
XiangChang 682a486f09 fix(openrouter): replace discontinued qwen3.6-plus free with paid model 2026-04-08 22:31:52 +08:00
Steven Goris ea10c5674b Add qwen3-coder-next model for cortecs 2026-04-08 15:14:31 +02:00
cantalupo555 5829a9174c feat(openrouter): add Gemma 4 26B A4B free
- Add google/gemma-4-26b-a4b-it:free (MoE, 256K context, multimodal, reasoning)
2026-04-08 08:32:07 -03:00
cantalupo555 4717e5a902 feat(openrouter): add Gemma 4 31B free
- Add google/gemma-4-31b-it:free (256K context, multimodal, reasoning)
2026-04-08 08:31:55 -03:00
cantalupo555 20f225d6a6 chore(openrouter): remove discontinued Qwen3.6 Plus free
- Model no longer available on OpenRouter API
2026-04-08 08:16:47 -03:00
dpuyosa 04ada2c06e [venice] Add Claude Opus 4.6 Fast and GLM 5.1 models
- Add claude-opus-4-6-fast model with 1M context
- Add zai-org-glm-5-1 model with reasoning and tool_call
2026-04-08 11:40:46 +02:00
Frank 23fd440f57 update zen models 2026-04-08 02:20:44 -04:00
Colby Gilbert a4c09d58c3 feat(firmware): add zai 5.1 and qwen 3.6 plus 2026-04-07 22:18:54 -07:00
Aiden Cline 82924aa6f2 Merge pull request #1376 from mugnimaestra/feat/add-glm-5.1-tee-chutes
feat(chutes): add zai-org/GLM-5.1-TEE model
2026-04-07 23:55:23 -05:00
Aiden Cline c8f0b6d573 Merge pull request #1377 from mchenco/mchen/update-cf-workers-ai-models
update cloudflare-workers-ai: add gemma-4, remove non-LLMs, fix metadata
2026-04-07 23:55:07 -05:00
Aiden Cline 09c3cb3e0a Merge pull request #1379 from zhongruan0522/dev
add GLM-5.1 to zhipuai and zai providers
2026-04-07 23:54:32 -05:00
Aiden Cline 555662ec80 Merge pull request #1381 from llc1123/chore/zenmux-update
chore(zenmux): add GLM-5.1 model configuration
2026-04-07 23:54:20 -05:00
Aiden Cline fc63cc19c3 feat: add experimental modes to models to express things like "fast" that induce additional price changes 2026-04-07 23:47:19 -05:00
Aiden Cline 26d2f3e8e9 Merge pull request #1378 from friendliai/minpeter/add-friendli-glm-5.1
feat(friendli): add GLM-5.1 and remove deprecated models
2026-04-07 22:30:44 -05:00
粒粒橙 92374dd74d chore(zenmux): add GLM-5.1 model configuration 2026-04-08 11:30:14 +08:00
minpeter ee4de44fbe fix(friendli): align model display names with cross-provider majority convention 2026-04-08 11:39:05 +09:00
zhongruan0522 5513af5b6c add GLM-5.1 to zhipuai and zai providers 2026-04-08 02:34:12 +00:00
minpeter 755509be95 feat(friendli): add GLM-5.1 and remove deprecated models 2026-04-08 11:31:50 +09:00
mchen 392b0988f2 update cloudflare-workers-ai: add gemma-4, remove non-LLMs, fix metadata
- Add gemma-4-27b-a4b-it (multimodal, reasoning, tool calling)

- Remove non-LLM models: embeddings, TTS, translation, sentiment analysis

- Remove redundant models: Llama 2/3.x variants, Qwen, Mistral, DeepSeek, Gemma 3

- Update metadata: tool_call, reasoning, open_weights, attachment for remaining models

- Final models: gemma-4, llama-4-scout, kimi-k2.5, nemotron-3, gpt-oss-20b/120b, glm-4.7-flash
2026-04-07 21:00:44 -04:00
Muhammad Mugni Hadi 7f1e94f571 feat(chutes): add zai-org/GLM-5.1-TEE model 2026-04-08 06:40:30 +07:00
Aiden Cline 61c596874c feat: add new provider.body and provider.headers support 2026-04-07 17:36:40 -05:00
Frank ca0e64451d update zen models 2026-04-07 18:01:31 -04:00
Aiden Cline d2870fcfeb Merge pull request #1374 from fhennerkes/dev
Poe: adding Gemma-4-31B (free model)
2026-04-07 16:48:52 -05:00
fhennerkes 9c8e1e0fa0 Merge branch 'anomalyco:dev' into dev 2026-04-07 14:02:06 -07:00
Frank 30d42207cb update zen models 2026-04-07 16:48:49 -04:00
fhennerkes c450a6ffaf poe: add Gemma-4-31B model
Add new Google model from Poe API (released 2026-04-02):
- Free during preview
- 262K context, 8K output
- Modalities: text, image

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 13:04:03 -07:00
Frank e889bd7c3b update zen models 2026-04-07 13:43:40 -04:00
Aiden Cline dcd3803dea Merge pull request #1359 from rdbisme/dev
Add missing Qwen3 Coder Next model to Amazon Bedrock
2026-04-07 12:41:41 -05:00
Aiden Cline 05b22d8f8e Merge pull request #1372 from JoshuaDietz/dev
feat(ollama-cloud): add GLM-5.1
2026-04-07 12:30:52 -05:00
Aiden Cline 5c1a00bbe8 Merge pull request #1373 from cantalupo555/feat/openrouter-glm-5.1
feat(openrouter): add z-ai/glm-5.1 model
2026-04-07 12:30:12 -05:00
cantalupo555 27cbd6557d feat(openrouter): add z-ai/glm-5.1 model
- Add GLM-5.1 with 202K context, reasoning, tool call, and structured output

- Pricing: $1.40/M input, $4.40/M output, $0.26/M cache read
2026-04-07 14:02:55 -03:00
JoshuaDietz 8114fa2f13 Merge branch 'anomalyco:dev' into dev 2026-04-07 19:01:23 +02:00
Joshua Dietz 5dc325bf09 feat(ollama-cloud): add GLM-5.1
unsure about temperature=true which is not set for GLM-5 but is set for GLM-5.1 huggingface.
2026-04-07 19:00:54 +02:00
Aiden Cline d27ce785fe Merge pull request #1370 from gary149/feat/huggingface-glm-5.1
feat(huggingface): add GLM-5.1
2026-04-07 11:55:12 -05:00
Aiden Cline f47f9e8414 Merge pull request #1225 from mixlayer/add_mixlayer
New provider: Mixlayer
2026-04-07 11:46:19 -05:00
Victor Muštar df41a38c6f feat(huggingface): add GLM-5.1 2026-04-07 18:33:53 +02:00
Aiden Cline 5b37d05f82 Merge pull request #1367 from cantalupo555/feat/stepfun-step-3.5-flash-2603
feat(stepfun): add step-3.5-flash-2603 model
2026-04-07 11:21:02 -05:00
Aiden Cline 99e046916c Merge pull request #1360 from jonathancaevans/update-kimi-k2p5-turbo-name
Update Kimi K2.5 Turbo display name for Firepass clarity
2026-04-07 11:09:02 -05:00
Aiden Cline 98baf7eaca Merge pull request #1364 from seffhunnn/fix-openrouter-glm-5-turbo-web
fix: correct glm-5-turbo pricing and context for openrouter
2026-04-07 11:08:29 -05:00
Aiden Cline 462d7fa620 Merge pull request #1365 from dpuyosa/feat/venice-add-qwen-3-6-plus
Venice: Add Qwen 3.6 Plus model
2026-04-07 11:08:15 -05:00
cantalupo555 7eea1dec18 feat(stepfun): add step-3.5-flash-2603 model
- Add Step 3.5 Flash 2603 model optimized for agent workflows

- Released April 2, 2026, same pricing as step-3.5-flash
2026-04-07 12:01:26 -03:00
dpuyosa 10652fb8dc feat(venice): add Qwen 3.6 Plus model
- Add Qwen 3.6 Plus with 1M context window

- Support text, image, and video input modalities

- Enable reasoning, tool calling, and structured output
2026-04-07 13:41:42 +02:00
Mohd Saif 816f9bb585 fix: correct glm-5-turbo pricing and context 2026-04-07 14:45:31 +05:30
Jonathan Evans 03376e9986 Update Kimi K2.5 Turbo display name
Add (firepass) suffix to clarify this is the Firepass router endpoint.

Follow-up to #1256
2026-04-06 13:10:01 -07:00
Ruben Di Battista 91d73da942 Enable reasoning capability for Qwen3 Coder Next model 2026-04-06 21:51:16 +02:00
Ruben Di Battista db7e4ff9ba Add missing Qwen3 Coder Next model to Amazon Bedrock 2026-04-06 21:07:36 +02:00
Aiden Cline d6145d1479 Merge pull request #1354 from llc1123/chore/zenmux-updates
zenmux: remove deprecated models and add Agnes 1.5 entries
2026-04-06 08:27:09 -07:00
粒粒橙 ec314aa0f1 fix(zenmux): add image support for agnes-1.5-lite 2026-04-06 14:28:22 +08:00
粒粒橙 188c36696e zenmux: remove deprecated models and add models from sapiens-ai 2026-04-06 14:08:08 +08:00
Aiden Cline 2b5f3f961d Merge pull request #1340 from battall/patch-1
fix: google/gemma-4 -it suffixes
2026-04-05 21:10:43 -07:00
Aiden Cline bf8ce0b8f8 Merge pull request #1342 from seffhunnn/fix-deepseek-context-window
fix: correct deepseek-chat context window to 131072
2026-04-05 21:06:53 -07:00
Aiden Cline 5e3eb74da2 Merge pull request #1341 from u1630022/feat-openrouter-trinity-large-thinking
add trinity large thinking to openrouter provider
2026-04-05 21:06:19 -07:00
Aiden Cline 542620b288 Merge pull request #1343 from spyridonas/patch-1
Fix capitalization in model name
2026-04-05 21:05:15 -07:00
Aiden Cline f6576ffb0f Merge pull request #1344 from dpuyosa/venice/gemma4-trinity
Venice: Add Gemma 4 and Arcee Trinity models, enable GLM 4.6 reasoning
2026-04-05 21:05:00 -07:00
Aiden Cline 88649810a6 Merge pull request #1346 from GHagui/add-gemma-4-openrouter
feat(openrouter): add Gemma 4 26B A4B and Gemma 4 31B models
2026-04-05 21:04:42 -07:00
Aiden Cline 1367d90f32 Merge pull request #1353 from cyberofficial/vultr
[Vultr] Update Inference Models
2026-04-05 21:03:58 -07:00
Cyber Official 322b1154be Update Inference Models
Vultr Updated Inference API endpoint with different versions of models, this commit adds in new models and corrects some information
2026-04-05 17:12:13 -04:00
Gabriel Hagui 7336867f65 Apply suggestions from code review
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-04-04 21:17:55 -03:00
GHagui caaf4d8b0a Merge branch 'add-gemma-4-openrouter' of https://github.com/GHagui/models.dev into add-gemma-4-openrouter 2026-04-05 00:09:19 +00:00
GHagui 08c2b928b6 fix(openrouter) Normalize formatting in Gemma 4 26B A4B and Gemma 4 31B TOML files 2026-04-05 00:03:44 +00:00
Gabriel Hagui 3a4b5e50cb Add files via upload
Fixing CRLF to LF
2026-04-04 20:51:25 -03:00
Gabriel Hagui 3244ef835e feat(openrouter) Add Gemma 4 26B A4B and Gemma 4 31B 2026-04-04 20:43:15 -03:00
GHagui 346b12f42f feat(openrouter) Add Gemma 4 26B A4B and Gemma 4 31B 2026-04-04 23:38:56 +00:00
dpuyosa 116d91a0cc [venice] Add Gemma 4 and Arcee Trinity models, enable GLM 4.6 reasoning
- Add Google Gemma 4 26B A4B and 31B instruct models with multimodal support
- Add Arcee Trinity Large Thinking reasoning model
- Enable reasoning capability for GLM 4.6
- Reduce Qwen3 5-9B output limit to 32K
2026-04-05 00:08:47 +02:00
Spyros Sakellaropoulos 778036c53c Fix capitalization in model name 2026-04-05 00:10:17 +03:00
Mohd Saif Ansari e86cc85dd4 fix: update deepseek-chat context window 2026-04-05 01:59:40 +05:30
Eavan Pattie a6f030fe1c add trinity large thinking to openrouter provider
* fixes trinity-large-thinking erroneously marked as not open_weight in
  vercel provider
2026-04-04 22:44:25 +03:00
Aiden Cline 1eb0b8c8e1 Merge pull request #1338 from anthraxx/alibaba-qwen3.6-plus
feat(alibaba): add Qwen3.6 Plus model configuration to all regions
2026-04-04 11:55:23 -07:00
Aiden Cline 1bc0b9d81f Merge pull request #1335 from branchgrove/dev
Add google-vertex DeepSeek V3.2 model
2026-04-04 11:51:37 -07:00
Battal Doğukan Hazar eca166ed4d fix: -it suffix for google/gemma-4 2026-04-04 21:48:31 +03:00
Aiden Cline e64404b173 Merge pull request #1336 from WJQSERVER/dev
Add Google Gemma 4 31B IT to NVIDIA(NIM) provider
2026-04-04 11:48:19 -07:00
Battal Doğukan Hazar e9c8425b32 fix: google/gemma-4 -it suffix 2026-04-04 21:47:27 +03:00
Aiden Cline 8618de3429 Merge pull request #1333 from riccardogiorato/dev
Remove deprecated models from TogetherAI provider
2026-04-04 11:28:46 -07:00
Aiden Cline 6e64316225 Merge pull request #1337 from fanweixiao/vivgrd/gpt-5.4
provider(vivgrid): add GPT-5.3 Codex, GPT-5.4 Mini, and GPT-5.4 Nano models
2026-04-04 11:28:33 -07:00
Aiden Cline a36d032e93 Merge pull request #1339 from cantalupo555/remove/qwen3.6-plus-preview-free
chore(openrouter): remove discontinued Qwen3.6 Plus Preview free
2026-04-04 11:28:18 -07:00
Aiden Cline e74dce023f Merge pull request #1315 from seffhunnn/fix-pdf-modalities
fix: add missing pdf modality to supported OpenAI models
2026-04-04 11:28:07 -07:00
cantalupo555 47f9b2b910 chore(openrouter): remove discontinued Qwen3.6 Plus Preview free
- Remove qwen3.6-plus-preview:free model after Qwen3.6 Plus free replaced it
2026-04-04 15:08:11 -03:00
Levente Polyak 6ba0af61d6 feat(alibaba): add Qwen3.6 Plus model configuration to all regions
- Add missing regions
- Add coding-plan variants
- Use pricing from model info page

Link: https://bailian.console.alibabacloud.com/cn-beijing?tab=model#/model-market/detail/qwen3.6-plus
2026-04-04 19:52:15 +02:00
C.C. Fan 24d4a9b8dd provider(vivgrid): add GPT-5.3 Codex, GPT-5.4 Mini, and GPT-5.4 Nano models
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-04 23:07:49 +08:00
wjqserver d5b420768a feat: add Google Gemma 4 31B IT to NVIDIA provider 2026-04-04 22:26:39 +08:00
Riccardo Giorato 66ada85298 more deprecations 2026-04-04 14:18:08 +02:00
Elias Lundgren 2ffb1d9181 Add google-vertex DeepSeek V3.2 model 2026-04-04 13:57:42 +02:00
Riccardo Giorato 04768ff141 Merge pull request #1 from riccardogiorato/orchestrator/remove-deprecated-models-g5nx
Remove deprecated models from togetherai provider
2026-04-03 21:51:02 +02:00
orchestrator-dev[bot] 9560d51908 Remove deprecated models from togetherai provider 2026-04-03 19:49:40 +00:00
Aiden Cline 6a41e31306 Merge pull request #1326 from michaelnchin/fix/amazon-bedrock-structured-output
fix: set correct structured output values for Amazon Bedrock models
2026-04-03 14:03:05 -05:00
Aiden Cline 133c529ebf Merge pull request #1327 from llc1123/chore/zenmux-new-models
zenmux: add KAT-Coder-Pro-V2, Qwen3.6-Plus, and GLM 5V Turbo
2026-04-03 14:02:40 -05:00
Aiden Cline 0a6b828e42 Merge pull request #1331 from zhongruan0522/feat/xiaomi-token-plan
feat: add Xiaomi Token Plan providers (cn/sgp/ams)
2026-04-03 14:00:46 -05:00
Aiden Cline 406f2f66c6 Merge pull request #1323 from Pxys-io/fix-xiaomi-mimo-cache-pricing
fix(openrouter): add missing cache_read pricing for xiaomi/mimo-v2-pro and xiaomi/mimo-v2-omni
2026-04-03 13:59:51 -05:00
Aiden Cline 948ce76d8d Merge pull request #1325 from DEAN-Cherry/dev
revert: alibaba-cn MiniMax-M2.5 to MiniMax-M2.7
2026-04-03 13:47:53 -05:00
Aiden Cline e3dd89ba2e Merge pull request #1332 from vercel/update-vercel-models-20260403-1639
Update Vercel models
2026-04-03 13:47:33 -05:00
Aiden Cline 7e5ae3bb06 Merge pull request #1329 from Track07-cda/alibaba-cn-qwen3.6
feat(alibaba-cn): add Qwen3.6 Plus model configuration
2026-04-03 13:47:19 -05:00
Aiden Cline 5392c185d2 Merge pull request #1328 from sadoclaw/add-gemma-4-models
Add Gemma 4 26B and 31B models
2026-04-03 13:47:00 -05:00
github-actions[bot] 72613f5dbf chore(vercel): update Vercel model definitions
Auto-generated by weekly workflow from Vercel AI Gateway API.

Co-Authored-By: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-04-03 16:39:32 +00:00
zhongruan0522 01098f81a9 feat: add Xiaomi Token Plan providers (cn/sgp/ams) 2026-04-03 11:22:04 +00:00
Track07-cda 65e798c8f2 feat(alibaba-cn): add Qwen3.6 Plus model configuration 2026-04-03 15:58:53 +08:00
sadoclaw 28a75176c4 Add Gemma 4 26B and 31B models 2026-04-03 08:34:41 +03:00
粒粒橙 61e63db8e3 zenmux: add new models 2026-04-03 13:09:53 +08:00
Michael Chin 95cd6196fa set correct structured_output values for Amazon Bedrock models 2026-04-02 21:15:18 -07:00
Bryan 19c1f2ebe2 revert: alibaba-cn MiniMax-M2.5 to MiniMax-M2.7
Revert PR #1002 - MiniMax-M2.5 is no longer available, now using MiniMax-M2.7
2026-04-03 12:09:05 +08:00
pxys-io 4d25bb5622 fix(openrouter): add missing cache_read pricing for xiaomi/mimo-v2-pro and xiaomi/mimo-v2-omni
OpenRouter charges bash.20/M cache_read tokens for mimo-v2-pro and
bash.08/M for mimo-v2-omni, but these were missing from the cost section.

Source: https://openrouter.ai/api/v1/models

Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
2026-04-03 04:08:55 +02:00
Aiden Cline 8845bf3f3b Merge pull request #1321 from BlockListed/cortecs-add-glm-5
Add glm-5 to cortecs
2026-04-02 19:28:50 -05:00
Aiden Cline 9b5bcde109 Merge pull request #1322 from fhennerkes/dev
poe: add GPT-5.3-Codex-Spark and Kimi-K2.5-FW models
2026-04-02 19:28:41 -05:00
Frank fa75002f19 update zen models 2026-04-02 19:01:00 -04:00
fhennerkes 69b6f3e94a poe: add GPT-5.3-Codex-Spark and Kimi-K2.5-FW models
Add 2 new free models
2026-04-02 15:11:34 -07:00
BlockListed 26f6b602fc add glm-5 to cortecs 2026-04-02 21:45:20 +02:00
Aiden Cline 287c69acaf Merge pull request #1314 from dpark01/add-kimi-k2-thinking-vertex
feat(google-vertex): add moonshotai/kimi-k2-thinking-maas model
2026-04-02 11:30:08 -05:00
Aiden Cline 2b46c3aef2 Merge pull request #1320 from cantalupo555/feature/qwen3.6-plus-free
feat: add Qwen3.6 Plus free on OpenRouter
2026-04-02 11:29:46 -05:00
cantalupo555 a9b7faa409 feat(openrouter): add qwen3.6-plus free model configuration
- Add Qwen3.6 Plus (free) provider configuration
- $0 pricing with 1M context window
- Multimodal input support (text, image, video)
- Full capabilities: reasoning, tool calls, structured output
- Attachment enabled for vision modality
2026-04-02 13:23:09 -03:00
Jack ad3305bc08 Merge branch 'dev' of github.com:anomalyco/models.dev into dev 2026-04-03 00:12:23 +08:00
Jack 0198228bbb Add MiMo V2 Pro/Omni models and family entries
Register two new MiMo V2 models and update model family values. Added "mimo-pro" and "mimo-omni" to ModelFamilyValues in packages/core/src/family.ts, and added corresponding TOML model descriptors under providers/opencode-go/models: mimo-v2-pro.toml and mimo-v2-omni.toml. The Pro model includes very large context (1,048,576) and tiered costs for >200k context, while the Omni model exposes multimodal input (text, image, audio, pdf) and a large 262,144 context. Both files set metadata (release_date, last_updated, knowledge cutoff, open_weights) and define interleaved reasoning field, costs, limits, and modalities.
2026-04-03 00:11:58 +08:00
Aiden Cline 165bc7df94 Merge pull request #1316 from NIKU-SINGH/remove-claude-3-7-sonnet-latest
Remove invalid claude-3-7-sonnet-latest model entry
2026-04-02 10:51:44 -05:00
NIKU-SINGH 36956dc4f4 Remove invalid claude-3-7-sonnet-latest model entry
Anthropic's API does not accept claude-3-7-sonnet-latest as a model ID
(returns 404). The versioned alias claude-3-7-sonnet-20250219 should be
used instead.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-02 16:27:15 +05:30
Mohd Saif Ansari 5ec371653b fix: add missing pdf modality to supported OpenAI models 2026-04-02 12:40:50 +05:30
Frank bb62fc43c1 update zen models 2026-04-01 22:59:53 -04:00
Frank c1465447ab update zen models 2026-04-01 17:53:17 -04:00
Daniel Park 471e9ec492 feat(google-vertex): add moonshotai/kimi-k2-thinking-maas model 2026-04-01 16:24:14 -04:00
Aiden Cline 57c3d38c21 Merge pull request #1313 from zhongruan0522/dev
Add GLM-5V-Turbo
2026-04-01 13:08:38 -05:00
Aiden Cline d19d2508b0 Merge pull request #1273 from Cahl-Dee/add-the-grid-ai
feat: add thegrid.ai provider and associated models
2026-04-01 12:25:35 -05:00
zhongruan0522 d0d2fffcfb Add GLM-5V-Turbo 2026-04-01 16:30:38 +00:00
Aiden Cline 07f48b1f2a Merge pull request #1311 from Moniet/feat/add-gpt-image-models
feat(openai): add openai gpt-image models
2026-04-01 10:52:12 -05:00
Moniet a33e15d095 feat(openai): add openai gpt-image models 2026-04-01 17:03:36 +05:30
Aiden Cline b64c2100f4 Merge pull request #1306 from dinhkim/feat/add-openrouter-glm-5-turbo
feat: add GLM-5-Turbo model in OpenRouter AI provider
2026-03-31 23:11:14 -05:00
Kim Truong 7ba7237633 feat: add GLM-5-Turbo model in OpenRouter AI provider 2026-03-31 23:18:02 +07:00
Aiden Cline 6e1ca23e6c Merge pull request #1305 from marcelarie/dev
Update synthetic.new model: Qwen3.5-397B
2026-03-31 10:43:23 -05:00
Aiden Cline 8ffb4ed5a7 Merge pull request #1301 from xinrui-z/fix/aihubmix-zod-validation-provider
fix(aihubmix): zod-validation-error
2026-03-31 10:43:12 -05:00
Xinrui 6b12398083 Replace @ai-sdk/openai-compatible with the official aihubmix/ai-sdk-provider package and remove the hardcoded api URL, as the dedicated package handles schema validation and endpoint configuration internally. 2026-03-31 23:29:10 +08:00
Aiden Cline 751745f200 Merge pull request #1304 from dpuyosa/add-gpt-54-mini-venice
Venice: Add GPT-5.4 Mini and remove discontinued models
2026-03-31 10:19:03 -05:00
marcelarie 593308b596 Merge branch 'dev' of github.com:marcelarie/models.dev into dev 2026-03-31 13:05:29 +02:00
marcelarie 54386f35b7 Added: Missing synthetic.new Qwen3.5-397B model 2026-03-31 13:02:19 +02:00
dpuyosa 73a83971e8 [venice] Add GPT-5.4 Mini and remove discontinued models
- Add GPT-5.4 Mini with reasoning and tool_call
- Update Aion 2.0 with reasoning capability
- Remove discontinued mistral-31-24b and qwen3-4b
2026-03-31 09:49:09 +02:00
Xinrui b5d8da29bb fix(aihubmix): switch to dedicated provider package to resolve Zod validation error
Replace @ai-sdk/openai-compatible with the official aihubmix/ai-sdk-provider
package and remove the hardcoded api URL, as the dedicated package handles
schema validation and endpoint configuration internally.
2026-03-31 12:37:56 +08:00
Aiden Cline 798538f9ae Merge pull request #1254 from llc1123/dev
feat(zenmux): route models through protocol-specific SDKs
2026-03-30 18:50:02 -05:00
Aiden Cline d4ce566f27 Merge pull request #1296 from sylviezhang37/update-vercel-models-20260330-1655
Update Vercel models
2026-03-30 18:49:47 -05:00
Aiden Cline 2042e3dd71 Merge pull request #1298 from cantalupo555/feature/qwen3.6-plus-preview-free
feat: add Qwen3.6 Plus Preview free on OpenRouter
2026-03-30 18:49:34 -05:00
Aiden Cline 08b577b6c9 Merge pull request #1299 from cyberofficial/vultr
Remove discontinued Vultr models
2026-03-30 18:49:24 -05:00
Cyber Official 01c3d44f99 Remove discontinued Vultr models
Vultr no longer supports these models on Serverless Inference:
- DeepSeek R1 Distill Llama 70B
- DeepSeek R1 Distill Qwen 32B
- GPT OSS 120B
- Llama 3.1 Nemotron Ultra 253B v1
- NVIDIA Nemotron 3 Super 120B A12B NVFP4

Remaining active models:
- MiniMax-M2.5: $0.30/M in, $1.20/M out
- DeepSeek-V3.2: $0.55/M in, $1.65/M out
- Kimi-K2.5: $0.55/M in, $2.75/M out
- GLM-5-FP8: $0.85/M in, $3.10/M out
2026-03-30 17:39:00 -04:00
cantalupo555 1695bfb958 feat: add Qwen3.6 Plus Preview free on OpenRouter
- Add free variant of Qwen3.6 Plus Preview to OpenRouter provider
- 1M context, 65K max output, /bin/bash.00 pricing
- Text-only modality (OpenRouter API reports text->text)
- Source: OpenRouter /api/v1/models API

---
Co-Authored-By: opencode https://opencode.ai
2026-03-30 18:08:54 -03:00
Frank bad8bedd25 update zen models 2026-03-30 16:50:10 -04:00
github-actions[bot] ad26e881ce chore(vercel): update Vercel model definitions
Auto-generated by weekly workflow from Vercel AI Gateway API.

Co-Authored-By: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-03-30 16:55:28 +00:00
Aiden Cline 348932f00c Merge pull request #1290 from zhongruan0522/dev
feat: add gpt-5.3-chat-latest model to openai
2026-03-29 22:25:52 -05:00
Aiden Cline d564c80b78 Merge pull request #1289 from pedrxd/mistral-add-mistral-small-4
Adding mistral small 4
2026-03-29 22:23:57 -05:00
Aiden Cline cba38e4707 Merge pull request #1287 from aeonzh/patch-1
Use correct name for Nemotron 3 Super (free) on OpenRouter
2026-03-29 12:35:18 -05:00
Aiden Cline 7ce9e95d62 Merge pull request #1294 from sk0x0y/add-glm-5.1-nanogpt
feat(nano-gpt): add glm-5.1 and glm-5.1:thinking models
2026-03-29 12:34:31 -05:00
sk0x0y a05b2a6be7 add glm-5.1 model to nano-gpt provider 2026-03-29 23:12:38 +09:00
zhongruan0522 17f41b72ad feat: add gpt-5.3-chat-latest model to openai 2026-03-29 11:18:44 +00:00
Pedro Ruiz 16cc382572 feat(mistral): Adding mistral small 4 2026-03-29 09:46:58 +02:00
Aiden Cline 3d456e3798 Merge pull request #1286 from khda-tech/dev
Add gemma family for google provider
2026-03-28 20:07:16 -05:00
Aiden Cline 0223ab3107 Merge pull request #1288 from cgilly2fast/dev
fix(firmware): incorrect model name for glm-5
2026-03-28 20:06:57 -05:00
Colby Gilbert 28ad50f6e9 fix(firmware): incorrect model name for glm-5 2026-03-27 22:26:19 -07:00
Zheng He Hu bf8fb378a4 Rename nemotron-3-super-120b-a12b-free.toml to nemotron-3-super-120b-a12b:free.toml 2026-03-28 02:54:35 +01:00
Aiden Cline b74242fdbf Merge pull request #1278 from fhennerkes/dev
poe: add Grok-4.20-Multi-Agent and DeepSeek-V3.2 models
2026-03-27 15:48:08 -05:00
Aiden Cline 8131cc947c Update providers/poe/models/novita/deepseek-v3.2.toml
Co-authored-by: Oleg Voronkovich <oleg-voronkovich@yandex.ru>
2026-03-27 15:21:16 -05:00
Khrulev Danil 95a73581cc Add gemma family for google provider 2026-03-27 21:39:52 +03:00
Zack Angelo 39ee133c98 mixlayer: adhere to logo standards, remove fill and size attributes 2026-03-27 09:23:09 -07:00
Aiden Cline c5e4e2c740 Merge pull request #1276 from voronkovich/feat-update-groq
feat(groq): Update Groq models
2026-03-27 10:51:40 -05:00
Aiden Cline 357c3021fb Merge pull request #1281 from zhongruan0522/dev
Added support for Zhipu AI's official CodingPlan GLM-5.1 model.
2026-03-27 09:49:49 -05:00
Aiden Cline 6afb0fea06 Merge pull request #1280 from dpuyosa/dev
Venice: Add Aion 2.0, update DeepSeek V3.2, remove Gemini 3 Pro Preview
2026-03-27 09:46:58 -05:00
dd781c4c15 feat: add glm-5.1 model to zai-coding-plan and zhipuai-coding-plan 2026-03-27 11:51:14 +00:00
dpuyosa 04e3b7c008 [venice] Add Aion 2.0, update DeepSeek V3.2, remove Gemini 3 Pro Preview
- feat(venice): add Aion 2.0 model
- fix(venice): enable tool_call and structured_output on DeepSeek V3.2
- fix(venice): remove deprecated Gemini 3 Pro Preview
2026-03-27 09:19:28 +01:00
Oleg Voronkovich ca40cb538d Updates 2026-03-27 00:37:40 +03:00
Aiden Cline f03de60559 Merge pull request #1259 from smakosh/llmgateway-models
feat: update LLM Gateway to 204 models
2026-03-26 15:25:22 -05:00
fhennerkes 0226a37a51 poe: add Grok-4.20-Multi-Agent and DeepSeek-V3.2 models 2026-03-26 12:18:13 -07:00
smakosh c2ba40d7d5 fix: logo format, remove README, minimax weights
- Normalize logo to 24x24, viewBox 0 0 40 40, currentColor
- Remove README.md (other providers don't have one)
- Mark all MiniMax models as open_weights = true

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-26 20:02:58 +01:00
smakosh d77bee4f29 fix: correct reasoning, vision, tools flags
The export script only checked the first active
provider for capabilities. Now checks all providers
and uses model ID patterns for reasoning detection.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-26 19:55:28 +01:00
Oleg Voronkovich 5ec0ac2807 feat(groq): Update Groq models 2026-03-26 18:59:09 +03:00
Aiden Cline 62015086c6 Merge pull request #1274 from petit-blaireau/copilot/add-openrouter-mistral-small-4
Add Mistral Small 4 for OpenRouter
2026-03-25 19:47:51 -05:00
copilot-swe-agent[bot] 2d86bafb20 feat(openrouter): add Mistral Small 4 (mistral-small-2603)
Co-authored-by: petit-blaireau <1893252+petit-blaireau@users.noreply.github.com>
Agent-Logs-Url: https://github.com/petit-blaireau/models.dev/sessions/871bbf50-3ef0-4926-afd1-e95c79f6bd57
2026-03-26 00:03:38 +00:00
Cahl-Dee bf4e5aab17 remove family property and add open_weight 2026-03-25 16:57:02 -05:00
Cahl-Dee 1590791225 adding thegrid.ai provider and associated models 2026-03-25 16:09:54 -05:00
Aiden Cline 047f3356d6 Merge pull request #1265 from MiyakoMeow/add-glm-4.7-flashx
Add glm-4.7-flashx to ZAI/ZhipuAI
2026-03-25 16:09:24 -05:00
Aiden Cline 1394d2ca4d Merge pull request #1270 from NachoFLizaur/feat/bedrock-add-nemotron-super-3-120b
feat(amazon-bedrock): add NVIDIA Nemotron 3 Super 120B
2026-03-25 15:05:31 -05:00
Aiden Cline 5b73677b33 Merge pull request #1272 from NachoFLizaur/fix/bedrock-minimax-m2.5-glm-5-limits
fix(amazon-bedrock): correct MiniMax M2.5 and GLM-5 context/output limits
2026-03-25 15:05:18 -05:00
Nacho F. Lizaur 780db038c4 fix(amazon-bedrock): correct MiniMax M2.5 and GLM-5 context/output limits 2026-03-25 16:49:31 +01:00
Nacho F. Lizaur 29c1249d64 feat(amazon-bedrock): add NVIDIA Nemotron 3 Super 120B 2026-03-25 15:44:56 +01:00
lioZ129 1b0633b172 Update providers/hpc-ai/models/moonshotai/kimi-k2.5.toml
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-03-25 17:15:16 +08:00
lioZ129 aed0ee3bb7 Update providers/hpc-ai/models/moonshotai/kimi-k2.5.toml
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-03-25 17:15:03 +08:00
Contributor 9fa7856fc6 feat: add HPC-AI model provider support 2026-03-25 16:55:45 +08:00
MiyakoMeow 8b80a2b34b Add glm-4.7-flashx to ZAI/ZhipuAI 2026-03-25 06:13:03 +08:00
Aiden Cline 897aa53905 Merge pull request #1257 from fhennerkes/dev
poe: add GPT-5.4-Nano and GPT-5.4-Mini models
2026-03-24 15:19:13 -05:00
Aiden Cline 5c36e54a43 Merge pull request #1260 from Happily-Coding/dev
Add MiniMax 2.5 to siliconflow
2026-03-24 15:18:39 -05:00
Aiden Cline a38f9373ab Merge pull request #1261 from cyberofficial/vultr
[Vultr] Delete Qwen2.5-Coder-32B-Instruct.toml
2026-03-24 10:14:38 -05:00
Aiden Cline fb72c181f8 Merge pull request #1263 from fanweixiao/vivgrd/gpt-5.4
provider(vivgrid): add gpt-5.4 and upgrade gemini-3 to gemini-3.1
2026-03-24 10:14:20 -05:00
C.C. Fan 601300c7e7 provider(vivgrid): add gpt-5.4 and upgrade gemini-3 to gemini-3.1 2026-03-24 21:04:59 +08:00
Cyber Official 8d9e966867 Delete Qwen2.5-Coder-32B-Instruct.toml
Model no longer offered
2026-03-24 02:48:38 -04:00
UrielS cf8f12b375 Add MiniMax 2.5 to siliconflow
Add MiniMax 2.5 to siliconflow
2026-03-24 01:14:36 -03:00
UrielS 116e35a32a Add MiniMax 2.5 to siliconflow 2026-03-24 01:13:37 -03:00
Aiden Cline 87a02b897a Merge pull request #1258 from vglafirov/feat/gitlab-gpt-5-4-models
feat(gitlab): add GPT-5.4, GPT-5.4 Mini, GPT-5.4 Nano, and GPT-5.3 Codex models
2026-03-23 22:00:07 -05:00
Vladimir Glafirov 849a529a42 fix(gitlab): use unscoped gitlab-ai-provider npm package name 2026-03-23 23:52:13 +01:00
smakosh c2f0bd08e6 feat: update LLM Gateway models to 204
Regenerated model exports from latest LLM Gateway
source. Adds 66 new models including Claude 4.6,
GPT-5.x, Gemini 3.1, Grok 4, and more. Removes
deprecated model aliases.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-23 22:28:46 +01:00
Vladimir Glafirov 5257d0919a feat(gitlab): add GPT-5.4, GPT-5.4 Mini, GPT-5.4 Nano, and GPT-5.3 Codex models 2026-03-23 21:41:11 +01:00
fhennerkes 379ab2757f poe: add GPT-5.4-Nano and GPT-5.4-Mini models
Add 2 new OpenAI models from Poe API:

GPT-5.4-Nano (released 2026-03-11):
- Reasoning support, 400K context, 128K output
- Cost: $0.18/M input, $1.1/M output
- Modalities: text, image

GPT-5.4-Mini (released 2026-03-12):
- Reasoning support, 400K context, 128K output
- Cost: $0.68/M input, $4/M output
- Modalities: text, image

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-23 13:13:10 -07:00
Aiden Cline 9838c55e29 Merge pull request #1256 from jonathancaevans/add-kimi-k2p5-turbo-router
Add Fireworks Kimi K2.5 Turbo router
2026-03-23 15:08:32 -05:00
Aiden Cline 4235bc6432 Merge pull request #1249 from tobwen/cleanup/openrouter-deprecated-models
chore(openrouter): remove deprecated and unavailable models
2026-03-23 15:07:27 -05:00
Jonathan Evans 29c3e9cbf4 Add Kimi K2.5 Turbo router for Fireworks
- Model ID: accounts/fireworks/routers/kimi-k2p5-turbo

- Pricing set to 0 (handled at subscription layer)

- Supports text and image input, text output

- Includes reasoning capabilities
2026-03-23 16:01:08 -04:00
Aiden Cline b0c1f37aad Merge pull request #1255 from sylviezhang37/update-vercel-models-20260323-1954
Update Vercel models
2026-03-23 15:00:14 -05:00
github-actions[bot] bd07f155f5 chore(vercel): update Vercel model definitions
Auto-generated by weekly workflow from Vercel AI Gateway API.

Co-Authored-By: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-03-23 19:54:44 +00:00
粒粒橙 0f95849d38 fix(zenmux): align model metadata with runtime support 2026-03-23 23:06:36 +08:00
粒粒橙 8dc90a4097 feat(zenmux): route models through protocol-specific SDKs 2026-03-23 21:48:00 +08:00
Aiden Cline 0a19559e4e Merge pull request #1252 from tarun1793/add-glm-5-fastrouter
Add GLM-5 model to fastrouter provider
2026-03-23 08:13:45 -05:00
Aiden Cline f27f83bdf9 Merge pull request #1253 from jacksonwilliamsva/add-bedrock-minimax-m2.5-glm-5
feat(amazon-bedrock): add MiniMax M2.5 and GLM-5 models
2026-03-23 08:13:35 -05:00
Aiden Cline 7b050ec719 Merge pull request #1244 from BlockListed/cortecs-add-claude-models
Add more claude models to cortecs
2026-03-23 08:13:27 -05:00
Aiden Cline 443cfd7703 Merge pull request #1247 from wojons/dev
Add Nemotron 3 Super model to OpenRouter and NVIDIA providers
2026-03-23 08:11:12 -05:00
Aiden Cline 6d648bf471 Merge pull request #1250 from dsingal0/dev
correct model name for nemotron super 3 on baseten
2026-03-23 08:10:45 -05:00
Jackson Williams e1a83a6812 feat(amazon-bedrock): add MiniMax M2.5 and GLM-5 models
Add two newly available Amazon Bedrock models:

- minimax.minimax-m2.5: 1M context, /bin/bash.30/.20 per 1M tokens
- zai.glm-5: 200K context, .00/.20 per 1M tokens

Both models were added to Amazon Bedrock on March 18, 2026.
Specs sourced from AWS Bedrock pricing page and vendor documentation.
2026-03-23 11:41:21 +11:00
Tarun b8606ed0e4 use latest price from fastrouter 2026-03-22 23:47:13 +00:00
Tarun 69c4600842 Override fastrouter glm-5 with zai glm-5 values 2026-03-22 23:43:09 +00:00
Tarun 5eb4a369f3 Add GLM-5 model to fastrouter provider 2026-03-22 23:31:53 +00:00
Dhruv Singal 17df1b49ce Update Baseten Nemotron model name 2026-03-22 13:04:40 -07:00
Dhruv Singal f18bc9b95b Update Baseten Nemotron display name 2026-03-22 13:00:49 -07:00
Dhruv Singal 485c37e862 Rename Baseten Nemotron model to match API ID 2026-03-22 12:57:10 -07:00
tobwen 0f092e3f62 chore(openrouter): remove expired/revealed/ended endpoints 2026-03-22 12:28:08 +00:00
tobwen a7bcd7e632 chore(openrouter): remove models without endpoints 2026-03-22 12:27:59 +00:00
Alexis Okuwa 6d081af472 Add Nemotron 3 Super model to OpenRouter and NVIDIA providers 2026-03-22 05:45:00 -05:00
Aiden Cline 8ee9ea1d96 Merge pull request #1243 from v1gnesh/dev
Update Grok 4.2 model names
2026-03-21 11:56:37 -05:00
Aiden Cline c71a365320 Merge pull request #1245 from Daltonganger/add-nanogpt-minimax-m2-7
Add NanoGPT MiniMax M2.7 model metadata
2026-03-21 11:55:15 -05:00
Ruben Beuker bb0e828b77 add NanoGPT MiniMax M2.7 model metadata 2026-03-21 14:58:35 +01:00
BlockListed 58cb222125 add more claude models to cortecs 2026-03-21 09:18:00 +01:00
v1gnesh 33f67289ee Rename model and remove beta status 2026-03-21 11:29:13 +05:30
v1gnesh ad34d7948c Update model name and status in TOML file 2026-03-21 11:28:22 +05:30
v1gnesh 7132293513 Add grok-4.20-0309-non-reasoning.toml file 2026-03-21 11:27:53 +05:30
Aiden Cline 495bc263e7 Merge pull request #1241 from BlockListed/add-minimax-2.5-cortecs
Add minimax M2.5 to cortecs
2026-03-20 15:55:28 -05:00
Aiden Cline 3811a45efe Merge pull request #1235 from anomalyco/github-sync
sync github copilot limits
2026-03-20 15:55:09 -05:00
BlockListed c4d04d2ed9 add minimax m2.5 to cortecs 2026-03-20 21:51:30 +01:00
Aiden Cline 20fcbbc336 Merge pull request #1240 from sylviezhang37/update-vercel-models-20260320-1642
Update Vercel models
2026-03-20 13:08:30 -05:00
github-actions[bot] 482b8ed69d chore(vercel): update Vercel model definitions
Auto-generated by weekly workflow from Vercel AI Gateway API.

Co-Authored-By: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-03-20 16:42:15 +00:00
Aiden Cline b77e95b84e Merge pull request #1236 from LYY/update/zenmux-sync
Sync ZenMux models with latest website data
2026-03-20 10:23:40 -05:00
Aiden Cline 463006f80c Merge pull request #1237 from vincentbernat/fix/scaleway-qwen3.5
fix(scaleway): set the correct family for Qwen 3.5 for Scaleway
2026-03-20 10:23:17 -05:00
Vincent Bernat 45b5abb875 fix(scaleway): set the correct family for Qwen 3.5 for Scaleway 2026-03-20 06:32:51 +01:00
LYY 4255e420ec Sync zenmux models with website
Add 17 new models found on zenmux.ai:
- google/gemini-3-pro-image-preview
- google/gemini-3.1-flash-lite-preview
- minimax/minimax-m2.7
- minimax/minimax-m2.7-highspeed
- openai/gpt-5.3-chat
- openai/gpt-5.3-codex
- openai/gpt-5.4
- openai/gpt-5.4-mini
- openai/gpt-5.4-nano
- openai/gpt-5.4-pro
- qwen/qwen3.5-flash
- qwen/qwen3.5-plus
- volcengine/doubao-seed-2.0-code
- x-ai/grok-4.2-fast
- x-ai/grok-4.2-fast-non-reasoning
- xiaomi/mimo-v2-omni
- xiaomi/mimo-v2-pro
- z-ai/glm-5-turbo

Mark anthropic/claude-3.5-sonnet as deprecated (not found on website)
2026-03-20 12:46:16 +08:00
Zack Angelo 7a2ec5ab95 New provider: Mixlayer 2026-03-18 11:19:35 -07:00
massaindustries 6ecd9ec509 add qwen-next-coder-2 2026-02-05 09:11:08 +00:00
massaindustries bb42d0b855 add qwen-next-coder 2026-02-05 09:09:30 +00:00
massaindustries a46966efef add-regolo-02 2026-01-29 15:14:02 +00:00
massaindustries 19ace4436f add-regolo-01 2026-01-29 12:36:44 +00:00
Luca Steeb 92269282eb fix: use correct family for gemma and gpt-oss models
- Gemma models now use "gemma" family instead of "gemini"
- GPT OSS models now use "gpt-oss" family instead of "gpt"

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-23 01:36:29 +00:00
Luca Steeb 6b9b340fbc fix: map llmgateway family to auto
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-23 01:28:38 +00:00
Luca Steeb e8a6793654 fix: use valid models.dev family enum values
Maps internal family names to valid models.dev families:
- moonshot → kimi
- bytedance → seed
- zai → glm
- nvidia → nemotron

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-23 01:27:15 +00:00
Luca Steeb b22ff136a8 fix: add required output limit to all models
models.dev schema requires limit.output field.
Defaults to 16384 when not specified.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-23 01:25:53 +00:00
Luca Steeb e28d4e387f chore: trigger CI 2026-01-23 01:21:06 +00:00
Luca Steeb 09b5dd4d84 refactor: remove scripts/ dir, link to repo script
Removes empty generate.ts file and scripts/ directory.
README now links to llmgateway repo for regeneration.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-23 01:18:53 +00:00
Luca Steeb 24e575a86e refactor: flatten model structure to models/ directory
Removes provider subdirectories, exports all models directly
to models/ folder for simpler structure.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-23 01:15:27 +00:00
Luca Steeb 3549abec36 feat: add LLM Gateway provider with 153 models
Add LLM Gateway (llmgateway.io) as a new provider with all supported models
organized by upstream provider subdirectory.

LLM Gateway is an OpenAI-compatible API gateway that provides unified
access to 40+ LLM providers through a single API endpoint.

Directory structure:
  providers/llmgateway/
  ├── provider.toml
  ├── README.md
  ├── scripts/
  │   └── generate.ts
  └── models/
      ├── anthropic/ (16 models)
      ├── openai/ (28 models)
      ├── google/ (19 models)
      ├── zai/ (17 models - GLM, CogView)
      ├── alibaba/ (27 models - Qwen)
      ├── meta/ (12 models - Llama)
      ├── xai/ (9 models - Grok)
      ├── deepseek/ (5 models)
      ├── bytedance/ (6 models - Seed)
      ├── moonshot/ (4 models - Kimi)
      ├── mistral/ (3 models)
      ├── perplexity/ (3 models - Sonar)
      ├── minimax/ (1 model)
      ├── nvidia/ (1 model)
      └── llmgateway/ (2 models - auto, custom)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-23 01:10:53 +00:00
4392 changed files with 58881 additions and 23381 deletions
@@ -0,0 +1,68 @@
name: Close stale pull requests
on:
schedule:
- cron: "17 3 * * *"
workflow_dispatch:
permissions:
issues: write
pull-requests: write
jobs:
close-stale-pull-requests:
runs-on: ubuntu-latest
steps:
- uses: actions/github-script@v8
env:
REVIEWER: rekram1-node
with:
script: |
const { owner, repo } = context.repo
const now = Date.now()
const weekAgo = now - 7 * 24 * 60 * 60 * 1000
const monthAgo = now - 30 * 24 * 60 * 60 * 1000
const pulls = await github.paginate(github.rest.pulls.list, {
owner,
repo,
state: "open",
per_page: 100,
})
const feedbackPulls = new Set()
for (const qualifier of ["commenter", "reviewed-by"]) {
const results = await github.paginate(
github.rest.search.issuesAndPullRequests,
{
q: `repo:${owner}/${repo} is:pr is:open ${qualifier}:${process.env.REVIEWER}`,
per_page: 100,
},
)
for (const result of results) feedbackPulls.add(result.number)
}
for (const pull of pulls) {
const updatedAt = Date.parse(pull.updated_at)
const monthStale = updatedAt < monthAgo
const feedbackStale = updatedAt < weekAgo && feedbackPulls.has(pull.number)
if (!monthStale && !feedbackStale) continue
const reason = monthStale
? "it has not been updated in 30 days"
: `it has not been updated in 7 days after feedback from @${process.env.REVIEWER}`
await github.rest.issues.createComment({
owner,
repo,
issue_number: pull.number,
body: `Closing this pull request as stale because ${reason}. Feel free to reopen it or submit a new pull request if the work is resumed.`,
})
await github.rest.pulls.update({
owner,
repo,
pull_number: pull.number,
state: "closed",
})
}
+2
View File
@@ -10,6 +10,7 @@ concurrency: ${{ github.workflow }}-${{ github.ref }}
jobs:
deploy:
if: github.repository == 'anomalyco/models.dev'
runs-on: ubuntu-latest
steps:
- name: Checkout code
@@ -35,3 +36,4 @@ jobs:
- run: bun sst deploy --stage=dev
env:
CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
CLOUDFLARE_DEFAULT_ACCOUNT_ID: ${{ secrets.CLOUDFLARE_DEFAULT_ACCOUNT_ID }}
+114
View File
@@ -0,0 +1,114 @@
name: Sync Model Catalogs
on:
schedule:
- cron: "17 * * * *"
workflow_dispatch:
permissions:
contents: write
issues: write
pull-requests: write
concurrency: ${{ github.workflow }}-${{ github.ref }}
jobs:
providers:
if: github.repository == 'anomalyco/models.dev'
runs-on: ubuntu-latest
outputs:
matrix: ${{ steps.providers.outputs.matrix }}
steps:
- name: Checkout code
uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5
with:
ref: dev
- name: Setup Bun
uses: oven-sh/setup-bun@f4d14e03ff726c06358e5557344e1da148b56cf7
with:
bun-version: latest
- name: Install dependencies
run: bun install
- name: List sync providers
id: providers
run: |
matrix="$(bun models:sync --list-providers)"
echo "matrix=$matrix" >> "$GITHUB_OUTPUT"
sync:
needs: providers
if: github.repository == 'anomalyco/models.dev'
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix: ${{ fromJSON(needs.providers.outputs.matrix) }}
steps:
- name: Checkout code
uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5
with:
ref: dev
- name: Setup Bun
uses: oven-sh/setup-bun@f4d14e03ff726c06358e5557344e1da148b56cf7
with:
bun-version: latest
- name: Install dependencies
run: bun install
- name: Sync model catalogs
run: bun models:sync ${{ matrix.provider }}
env:
BASETEN_API_KEY: ${{ secrets.BASETEN_API_KEY }}
OPENROUTER_API_KEY: ${{ secrets.OPENROUTER_API_KEY }}
VENICE_API_KEY: ${{ secrets.VENICE_API_KEY }}
GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
GOOGLE_GENERATIVE_AI_API_KEY: ${{ secrets.GOOGLE_GENERATIVE_AI_API_KEY }}
XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
CLOUDFLARE_WORKERS_AI_SYNC_ACCOUNT_ID: ${{ secrets.CLOUDFLARE_WORKERS_AI_SYNC_ACCOUNT_ID }}
CLOUDFLARE_WORKERS_AI_SYNC_API_TOKEN: ${{ secrets.CLOUDFLARE_WORKERS_AI_SYNC_API_TOKEN }}
- name: Validate models
run: bun validate
- name: Create pull request
env:
GH_TOKEN: ${{ github.token }}
BRANCH: automation/sync-models-${{ matrix.provider }}
LABELS: automation,model-sync,provider:${{ matrix.provider }}
TITLE: "chore(sync): update ${{ matrix.name }} model catalog"
run: |
if [ -z "$(git status --porcelain -- models providers)" ]; then
echo "No model catalog changes found."
exit 0
fi
git config user.name "github-actions[bot]"
git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
git fetch --no-tags --depth=1 origin "+refs/heads/$BRANCH:refs/remotes/origin/$BRANCH" || true
git checkout -B "$BRANCH"
git add models providers
git commit -m "$TITLE"
git push --force-with-lease origin "$BRANCH"
label_args=()
IFS=',' read -ra labels <<< "$LABELS"
for label in "${labels[@]}"; do
gh label create "$label" --color "0E8A16" --description "Automated model catalog sync" >/dev/null 2>&1 || true
label_args+=(--label "$label")
done
pr_number="$(gh pr list --head "$BRANCH" --base dev --json number --jq '.[0].number')"
if [ -n "$pr_number" ]; then
gh pr edit "$pr_number" --title "$TITLE" --body-file .sync/model-sync-report.md
for label in "${labels[@]}"; do
gh pr edit "$pr_number" --add-label "$label"
done
else
gh pr create --base dev --head "$BRANCH" --title "$TITLE" --body-file .sync/model-sync-report.md "${label_args[@]}"
fi
+1
View File
@@ -3,6 +3,7 @@
.idea
dist
.DS_Store
.sync/
node_modules
data/tokenspeed-monitor.sqlite
data/tokenspeed-monitor.sqlite-shm
+380
View File
@@ -0,0 +1,380 @@
{
"name": ".opencode",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"dependencies": {
"@opencode-ai/plugin": "1.15.13"
}
},
"node_modules/@msgpackr-extract/msgpackr-extract-darwin-arm64": {
"version": "3.0.4",
"resolved": "https://registry.npmjs.org/@msgpackr-extract/msgpackr-extract-darwin-arm64/-/msgpackr-extract-darwin-arm64-3.0.4.tgz",
"integrity": "sha512-LCkGo6JDfaBhgST7UpPWgNgLINpcpabaHfyz5OBx75nUYxBsaEPxjnyNjWpeb/xBup/682QnBfRBy2/LvPutZQ==",
"cpu": [
"arm64"
],
"license": "MIT",
"optional": true,
"os": [
"darwin"
]
},
"node_modules/@msgpackr-extract/msgpackr-extract-darwin-x64": {
"version": "3.0.4",
"resolved": "https://registry.npmjs.org/@msgpackr-extract/msgpackr-extract-darwin-x64/-/msgpackr-extract-darwin-x64-3.0.4.tgz",
"integrity": "sha512-zExlW9zUJKZH/tOtVMttwjKa4Xm/3KcNjnE3dPN92uCktwavMxpgCA3MoJK/DOnTWsQgo224OaST27/mPNAf+w==",
"cpu": [
"x64"
],
"license": "MIT",
"optional": true,
"os": [
"darwin"
]
},
"node_modules/@msgpackr-extract/msgpackr-extract-linux-arm": {
"version": "3.0.4",
"resolved": "https://registry.npmjs.org/@msgpackr-extract/msgpackr-extract-linux-arm/-/msgpackr-extract-linux-arm-3.0.4.tgz",
"integrity": "sha512-Tg3yX65f5GbtXLkrYEHE5oibZG9epyYWas7FogTTEJeDEF9JlXJzKgXaNhT3UXlTOeA+AfZpYZYZ0uPj7Cfquw==",
"cpu": [
"arm"
],
"license": "MIT",
"optional": true,
"os": [
"linux"
]
},
"node_modules/@msgpackr-extract/msgpackr-extract-linux-arm64": {
"version": "3.0.4",
"resolved": "https://registry.npmjs.org/@msgpackr-extract/msgpackr-extract-linux-arm64/-/msgpackr-extract-linux-arm64-3.0.4.tgz",
"integrity": "sha512-dgX0P/9wGPJeHFBG+ZmhgE6bmtMt7NP5CRBGyyktpopdk/mW4POnrpQsSLtKI1dwpc+pPLuXHDh6vvskyQE/sw==",
"cpu": [
"arm64"
],
"license": "MIT",
"optional": true,
"os": [
"linux"
]
},
"node_modules/@msgpackr-extract/msgpackr-extract-linux-x64": {
"version": "3.0.4",
"resolved": "https://registry.npmjs.org/@msgpackr-extract/msgpackr-extract-linux-x64/-/msgpackr-extract-linux-x64-3.0.4.tgz",
"integrity": "sha512-8TNXMEjJc3QEy7R/x1INhgiU+XakDAFUzBhaz7+Rbrs8NH5UQeHQxxmzsSBJGyV6I1jW79undiQm8tOI+D+8FQ==",
"cpu": [
"x64"
],
"license": "MIT",
"optional": true,
"os": [
"linux"
]
},
"node_modules/@msgpackr-extract/msgpackr-extract-win32-x64": {
"version": "3.0.4",
"resolved": "https://registry.npmjs.org/@msgpackr-extract/msgpackr-extract-win32-x64/-/msgpackr-extract-win32-x64-3.0.4.tgz",
"integrity": "sha512-CmCXPQrkbwExx3j946/PtHWHbYJiCRBRDl4BlkRQcJB/YOwQxJRTpoo7aTsortjgoJ1x7opzTSxn7C+ASSLVjQ==",
"cpu": [
"x64"
],
"license": "MIT",
"optional": true,
"os": [
"win32"
]
},
"node_modules/@opencode-ai/plugin": {
"version": "1.15.13",
"resolved": "https://registry.npmjs.org/@opencode-ai/plugin/-/plugin-1.15.13.tgz",
"integrity": "sha512-NFwZGhmxIPijtfz9swPJXDmhOpq4UWP8WjEE7GEMr7FwtJrK/hv6v36nFimed5+OKk+pQCrTJn/vhRW7Io72IA==",
"license": "MIT",
"dependencies": {
"@opencode-ai/sdk": "1.15.13",
"effect": "4.0.0-beta.66",
"zod": "4.1.8"
},
"peerDependencies": {
"@opentui/core": ">=0.2.16",
"@opentui/keymap": ">=0.2.16",
"@opentui/solid": ">=0.2.16"
},
"peerDependenciesMeta": {
"@opentui/core": {
"optional": true
},
"@opentui/keymap": {
"optional": true
},
"@opentui/solid": {
"optional": true
}
}
},
"node_modules/@opencode-ai/sdk": {
"version": "1.15.13",
"resolved": "https://registry.npmjs.org/@opencode-ai/sdk/-/sdk-1.15.13.tgz",
"integrity": "sha512-4TwojIoQ8EG6/mVBuUVYZXiFcwNmiiytEnjnvyuvSJjGwFIlw2YIBFxtSVC3FbwwbwHT63teh1RHiQUUC4U5xw==",
"license": "MIT",
"dependencies": {
"cross-spawn": "7.0.6"
}
},
"node_modules/@standard-schema/spec": {
"version": "1.1.0",
"resolved": "https://registry.npmjs.org/@standard-schema/spec/-/spec-1.1.0.tgz",
"integrity": "sha512-l2aFy5jALhniG5HgqrD6jXLi/rUWrKvqN/qJx6yoJsgKhblVd+iqqU4RCXavm/jPityDo5TCvKMnpjKnOriy0w==",
"license": "MIT"
},
"node_modules/cross-spawn": {
"version": "7.0.6",
"resolved": "https://registry.npmjs.org/cross-spawn/-/cross-spawn-7.0.6.tgz",
"integrity": "sha512-uV2QOWP2nWzsy2aMp8aRibhi9dlzF5Hgh5SHaB9OiTGEyDTiJJyx0uy51QXdyWbtAHNua4XJzUKca3OzKUd3vA==",
"license": "MIT",
"dependencies": {
"path-key": "^3.1.0",
"shebang-command": "^2.0.0",
"which": "^2.0.1"
},
"engines": {
"node": ">= 8"
}
},
"node_modules/detect-libc": {
"version": "2.1.2",
"resolved": "https://registry.npmjs.org/detect-libc/-/detect-libc-2.1.2.tgz",
"integrity": "sha512-Btj2BOOO83o3WyH59e8MgXsxEQVcarkUOpEYrubB0urwnN10yQ364rsiByU11nZlqWYZm05i/of7io4mzihBtQ==",
"license": "Apache-2.0",
"optional": true,
"engines": {
"node": ">=8"
}
},
"node_modules/effect": {
"version": "4.0.0-beta.66",
"resolved": "https://registry.npmjs.org/effect/-/effect-4.0.0-beta.66.tgz",
"integrity": "sha512-4arEr62cziFa8BBVDUwJCJJmaVepXf/kRg7KtC0h8+bufngscrHbwWFhr9c+HonwOF+31U3iD3xUJmw9KzX7Dw==",
"license": "MIT",
"dependencies": {
"@standard-schema/spec": "^1.1.0",
"fast-check": "^4.6.0",
"find-my-way-ts": "^0.1.6",
"ini": "^6.0.0",
"kubernetes-types": "^1.30.0",
"msgpackr": "^1.11.9",
"multipasta": "^0.2.7",
"toml": "^4.1.1",
"uuid": "^13.0.0",
"yaml": "^2.8.3"
}
},
"node_modules/fast-check": {
"version": "4.8.0",
"resolved": "https://registry.npmjs.org/fast-check/-/fast-check-4.8.0.tgz",
"integrity": "sha512-GOJ158CUMnN6cSahsv4+ExARvIDuzzinFjkp0E9WtiBa5zcVeLozVkWaE4IzFcc+Y48Wp1EDlUZsXRyAztQcSg==",
"funding": [
{
"type": "individual",
"url": "https://github.com/sponsors/dubzzz"
},
{
"type": "opencollective",
"url": "https://opencollective.com/fast-check"
}
],
"license": "MIT",
"dependencies": {
"pure-rand": "^8.0.0"
},
"engines": {
"node": ">=12.17.0"
}
},
"node_modules/find-my-way-ts": {
"version": "0.1.6",
"resolved": "https://registry.npmjs.org/find-my-way-ts/-/find-my-way-ts-0.1.6.tgz",
"integrity": "sha512-a85L9ZoXtNAey3Y6Z+eBWW658kO/MwR7zIafkIUPUMf3isZG0NCs2pjW2wtjxAKuJPxMAsHUIP4ZPGv0o5gyTA==",
"license": "MIT"
},
"node_modules/ini": {
"version": "6.0.0",
"resolved": "https://registry.npmjs.org/ini/-/ini-6.0.0.tgz",
"integrity": "sha512-IBTdIkzZNOpqm7q3dRqJvMaldXjDHWkEDfrwGEQTs5eaQMWV+djAhR+wahyNNMAa+qpbDUhBMVt4ZKNwpPm7xQ==",
"license": "ISC",
"engines": {
"node": "^20.17.0 || >=22.9.0"
}
},
"node_modules/isexe": {
"version": "2.0.0",
"resolved": "https://registry.npmjs.org/isexe/-/isexe-2.0.0.tgz",
"integrity": "sha512-RHxMLp9lnKHGHRng9QFhRCMbYAcVpn69smSGcq3f36xjgVVWThj4qqLbTLlq7Ssj8B+fIQ1EuCEGI2lKsyQeIw==",
"license": "ISC"
},
"node_modules/kubernetes-types": {
"version": "1.30.0",
"resolved": "https://registry.npmjs.org/kubernetes-types/-/kubernetes-types-1.30.0.tgz",
"integrity": "sha512-Dew1okvhM/SQcIa2rcgujNndZwU8VnSapDgdxlYoB84ZlpAD43U6KLAFqYo17ykSFGHNPrg0qry0bP+GJd9v7Q==",
"license": "Apache-2.0"
},
"node_modules/msgpackr": {
"version": "1.11.12",
"resolved": "https://registry.npmjs.org/msgpackr/-/msgpackr-1.11.12.tgz",
"integrity": "sha512-RBdJ1Un7yGlXWajrkxcSa93nvQ0w4zBf60c0yYv7YtBelP8H2FA7XsfBbMHtXKXUMUxH7zV3Zuozh+kUQWhHvg==",
"license": "MIT",
"optionalDependencies": {
"msgpackr-extract": "^3.0.2"
}
},
"node_modules/msgpackr-extract": {
"version": "3.0.4",
"resolved": "https://registry.npmjs.org/msgpackr-extract/-/msgpackr-extract-3.0.4.tgz",
"integrity": "sha512-4kmO/MdyUIkLIvTPr8VHLil4AtoKIoniWPIEk5+CDy0xnWC84azhSFmuJ7PxZdsYtiP5kEeQsORAVIeMgxT+Hw==",
"hasInstallScript": true,
"license": "MIT",
"optional": true,
"dependencies": {
"node-gyp-build-optional-packages": "5.2.2"
},
"bin": {
"download-msgpackr-prebuilds": "bin/download-prebuilds.js"
},
"optionalDependencies": {
"@msgpackr-extract/msgpackr-extract-darwin-arm64": "3.0.4",
"@msgpackr-extract/msgpackr-extract-darwin-x64": "3.0.4",
"@msgpackr-extract/msgpackr-extract-linux-arm": "3.0.4",
"@msgpackr-extract/msgpackr-extract-linux-arm64": "3.0.4",
"@msgpackr-extract/msgpackr-extract-linux-x64": "3.0.4",
"@msgpackr-extract/msgpackr-extract-win32-x64": "3.0.4"
}
},
"node_modules/multipasta": {
"version": "0.2.7",
"resolved": "https://registry.npmjs.org/multipasta/-/multipasta-0.2.7.tgz",
"integrity": "sha512-KPA58d68KgGil15oDqXjkUBEBYc00XvbPj5/X+dyzeo/lWm9Nc25pQRlf1D+gv4OpK7NM0J1odrbu9JNNGvynA==",
"license": "MIT"
},
"node_modules/node-gyp-build-optional-packages": {
"version": "5.2.2",
"resolved": "https://registry.npmjs.org/node-gyp-build-optional-packages/-/node-gyp-build-optional-packages-5.2.2.tgz",
"integrity": "sha512-s+w+rBWnpTMwSFbaE0UXsRlg7hU4FjekKU4eyAih5T8nJuNZT1nNsskXpxmeqSK9UzkBl6UgRlnKc8hz8IEqOw==",
"license": "MIT",
"optional": true,
"dependencies": {
"detect-libc": "^2.0.1"
},
"bin": {
"node-gyp-build-optional-packages": "bin.js",
"node-gyp-build-optional-packages-optional": "optional.js",
"node-gyp-build-optional-packages-test": "build-test.js"
}
},
"node_modules/path-key": {
"version": "3.1.1",
"resolved": "https://registry.npmjs.org/path-key/-/path-key-3.1.1.tgz",
"integrity": "sha512-ojmeN0qd+y0jszEtoY48r0Peq5dwMEkIlCOu6Q5f41lfkswXuKtYrhgoTpLnyIcHm24Uhqx+5Tqm2InSwLhE6Q==",
"license": "MIT",
"engines": {
"node": ">=8"
}
},
"node_modules/pure-rand": {
"version": "8.4.0",
"resolved": "https://registry.npmjs.org/pure-rand/-/pure-rand-8.4.0.tgz",
"integrity": "sha512-IoM8YF/jY0hiugFo/wOWqfmarlE6J0wc6fDK1PhftMk7MGhVZl88sZimmqBBFomLOCSmcCCpsfj7wXASCpvK9A==",
"funding": [
{
"type": "individual",
"url": "https://github.com/sponsors/dubzzz"
},
{
"type": "opencollective",
"url": "https://opencollective.com/fast-check"
}
],
"license": "MIT"
},
"node_modules/shebang-command": {
"version": "2.0.0",
"resolved": "https://registry.npmjs.org/shebang-command/-/shebang-command-2.0.0.tgz",
"integrity": "sha512-kHxr2zZpYtdmrN1qDjrrX/Z1rR1kG8Dx+gkpK1G4eXmvXswmcE1hTWBWYUzlraYw1/yZp6YuDY77YtvbN0dmDA==",
"license": "MIT",
"dependencies": {
"shebang-regex": "^3.0.0"
},
"engines": {
"node": ">=8"
}
},
"node_modules/shebang-regex": {
"version": "3.0.0",
"resolved": "https://registry.npmjs.org/shebang-regex/-/shebang-regex-3.0.0.tgz",
"integrity": "sha512-7++dFhtcx3353uBaq8DDR4NuxBetBzC7ZQOhmTQInHEd6bSrXdiEyzCvG07Z44UYdLShWUyXt5M/yhz8ekcb1A==",
"license": "MIT",
"engines": {
"node": ">=8"
}
},
"node_modules/toml": {
"version": "4.1.1",
"resolved": "https://registry.npmjs.org/toml/-/toml-4.1.1.tgz",
"integrity": "sha512-EBJnVBr3dTXdA89WVFoAIPUqkBjxPMwRqsfuo1r240tKFHXv3zgca4+NJib/h6TyvGF7vOawz0jGuryJCdNHrw==",
"license": "MIT",
"engines": {
"node": ">=20"
}
},
"node_modules/uuid": {
"version": "13.0.2",
"resolved": "https://registry.npmjs.org/uuid/-/uuid-13.0.2.tgz",
"integrity": "sha512-vzi9uRZ926x4XV73S/4qQaTwPXM2JBj6/6lI/byHH1jOpCzb0zDbfytgA9LcN/hzb2l7WQSQnxITOVx5un/wGw==",
"funding": [
"https://github.com/sponsors/broofa",
"https://github.com/sponsors/ctavan"
],
"license": "MIT",
"bin": {
"uuid": "dist-node/bin/uuid"
}
},
"node_modules/which": {
"version": "2.0.2",
"resolved": "https://registry.npmjs.org/which/-/which-2.0.2.tgz",
"integrity": "sha512-BLI3Tl1TW3Pvl70l3yq3Y64i+awpwXqsGBYWkkqMtnbXgrMD+yj7rhW0kuEDxzJaYXGjEW5ogapKNMEKNMjibA==",
"license": "ISC",
"dependencies": {
"isexe": "^2.0.0"
},
"bin": {
"node-which": "bin/node-which"
},
"engines": {
"node": ">= 8"
}
},
"node_modules/yaml": {
"version": "2.9.0",
"resolved": "https://registry.npmjs.org/yaml/-/yaml-2.9.0.tgz",
"integrity": "sha512-2AvhNX3mb8zd6Zy7INTtSpl1F15HW6Wnqj0srWlkKLcpYl/gMIMJiyuGq2KeI2YFxUPjdlB+3Lc10seMLtL4cA==",
"license": "ISC",
"bin": {
"yaml": "bin.mjs"
},
"engines": {
"node": ">= 14.6"
},
"funding": {
"url": "https://github.com/sponsors/eemeli"
}
},
"node_modules/zod": {
"version": "4.1.8",
"license": "MIT",
"funding": {
"url": "https://github.com/sponsors/colinhacks"
}
}
}
}
+19 -2
View File
@@ -31,9 +31,26 @@
## Model Configuration
- Model `id` is **auto-injected** from filename (minus `.toml`) — never put `id` in TOML files
- Same model is duplicated across provider directories with no cross-referencing
- Provider models may reuse provider-agnostic facts from `models/` via `base_model`; otherwise the full provider model definition must be present in the file
- Schema uses `.strict()` — extra fields cause validation errors
### Model metadata and `base_model`
- Provider-agnostic model facts live under `models/<provider>/<model>.toml`
- Provider TOMLs can inherit those facts with:
```toml
base_model = "<provider-id>/<model-id>"
base_model_omit = ["limit.input"] # optional, dot-path strings
```
Example: `base_model = "anthropic/claude-opus-4-6"`
- Resolved at parse time in `generate()`; the final provider JSON output contains **no** `base_model` or `base_model_omit` fields
- Merge semantics:
- Plain objects from metadata and provider TOML (`[limit]`, `[modalities]`, …) are **deep-merged**
- Arrays (e.g. `modalities.input`) and primitives are **replaced** wholesale by the child
- Any provider field omitted is inherited verbatim from model metadata
- `cost`, `provider`, `experimental`, `reasoning_options`, `interleaved`, and `status` are provider-specific and must be declared in provider TOMLs when needed
- `base_model_omit` runs **after** the merge and deletes each dot-path from the result. Missing paths are ignored. Ancestor tables that become empty as a result are also pruned.
- The base model metadata file must exist; `base_model` pointing at a missing `models/` entry is an error
### Bedrock Naming Patterns
- Dated models: `-v1:0` suffix (`anthropic.claude-3-5-sonnet-20241022-v1:0.toml`)
- Latest/undated models: bare `-v1` (`anthropic.claude-opus-4-6-v1.toml`)
@@ -54,4 +71,4 @@
| `attachment`, `reasoning`, `tool_call`, `open_weights` | Yes | Boolean capabilities |
| `cost`, `limit`, `modalities` | Yes | Objects with their own required fields |
| `family`, `knowledge`, `temperature`, `structured_output` | No | Optional metadata |
| `status` | No | Use for `"alpha"`, `"beta"`, `"deprecated"` lifecycle |
| `status` | No | Use for `"alpha"`, `"beta"`, `"deprecated"` lifecycle |
+112 -2
View File
@@ -24,6 +24,18 @@ curl https://models.dev/api.json
Use the **Model ID** field to do a lookup on any model; it's the identifier used by [AI SDK](https://ai-sdk.dev/).
Provider-agnostic model metadata is available separately:
```bash
curl https://models.dev/models.json
```
Use this for facts about the model itself, independent of where it is served. If you need both provider endpoints and model-only metadata in one response:
```bash
curl https://models.dev/catalog.json
```
### Logos
Provider logos are available as SVG files:
@@ -40,7 +52,71 @@ The data is stored in the repo as TOML files; organized by provider and model. T
We need your help keeping the data up to date.
### Adding a New Model
### Adding Model Metadata
Model-only facts live in `models/`, using the same path-style IDs as provider models. For example, `models/openai/gpt-5.toml` defines metadata for the underlying GPT-5 model, while `providers/openai/models/gpt-5.toml` defines OpenAI-specific serving details such as pricing.
Use model metadata for provider-agnostic facts:
- `name`, `family`, `release_date`, `last_updated`, `knowledge`
- `attachment`, `reasoning`, `tool_call`, `structured_output`, `temperature`
- `[limit]` defaults like context, input, and output token limits
- `[modalities]` defaults
- `open_weights`, `license`, `links`, `weights`, and `benchmarks`
Example:
```toml
name = "GPT-5"
family = "gpt"
release_date = "2025-08-07"
last_updated = "2025-08-07"
attachment = true
reasoning = true
temperature = false
tool_call = true
structured_output = true
open_weights = false
[limit]
context = 400_000
input = 272_000
output = 128_000
[modalities]
input = ["text", "image"]
output = ["text"]
[[benchmarks]]
name = "Benchmark Name"
score = 72.5
metric = "accuracy"
source = "https://example.com/results"
[[weights]]
label = "Model weights"
url = "https://huggingface.co/example/model"
format = "safetensors"
```
Provider TOMLs can inherit these facts with `base_model` and then keep only provider-specific fields or overrides:
```toml
base_model = "openai/gpt-5"
[cost]
input = 1.25
output = 10.00
cache_read = 0.125
[limit]
context = 200_000 # optional provider override
output = 32_000
```
Provider fields win over model metadata during generation. Use this when the underlying model is the same but a provider serves it with different context limits, modalities, features, or pricing.
### Adding a New Provider Model
To add a new model, start by checking if the provider already exists in the `providers/` directory. If not, then:
@@ -120,6 +196,32 @@ output = ["text"] # Supported output modalities
field = "reasoning_content" # Name of the interleaved field "reasoning_content" or "reasoning_details"
```
#### 3a. Reuse Model Metadata with `base_model`
For wrapper providers that mirror an existing model, prefer referencing the model-only metadata instead of duplicating provider-agnostic fields.
Use `base_model` when the provider serves the same underlying model and only provider-specific fields differ.
```toml
base_model = "anthropic/claude-opus-4-6"
[cost]
input = 5.00
output = 25.00
```
Rules:
- `base_model` must point to a TOML file in `models/` using `<provider>/<model-id>`.
- You can override any top-level model field locally.
- If you override a nested table like `[cost]`, `[limit]`, or `[modalities]`, include the full values needed for that table.
- `base_model_omit` is optional and removes inherited model metadata fields after local overrides are merged. Use dot-path strings, for example `base_model_omit = ["limit.input"]`.
- `id` still comes from the filename; do not add it to the TOML.
Use `base_model` when the wrapper model is materially the same as the source model and only differs by provider-specific pricing, limits, modalities, provider request shape, or lifecycle flags.
Sync and generator scripts should preserve existing `base_model` / `base_model_omit` fields when updating provider TOMLs. Do not use legacy `[extends]` tables.
#### 4. Submit a Pull Request
1. Fork this repo
@@ -136,9 +238,17 @@ There's a GitHub Action that will automatically validate your submission against
- Values are within acceptable ranges
- TOML syntax is valid
When moving existing provider fields into model metadata, compare generated output before and after the change:
```bash
bun run compare:migrations
```
This prints a diff for each changed model TOML so you can confirm the generated JSON only changed where you intended.
### Schema Reference
Models must conform to the following schema, as defined in `app/schemas.ts`.
Models must conform to the following schema, as defined in `packages/core/src/schema.ts`.
**Provider Schema:**
+10 -12
View File
@@ -5,7 +5,7 @@
"": {
"name": "models.dev",
"dependencies": {
"@cloudflare/workers-types": "^4.20250801.0",
"@cloudflare/workers-types": "^4.20260424.1",
"sst": "3.17.23",
},
},
@@ -13,6 +13,7 @@
"name": "models.dev",
"version": "0.0.0",
"dependencies": {
"remeda": "^2.33.7",
"zod": "catalog:",
},
"devDependencies": {
@@ -31,6 +32,7 @@
"packages/web": {
"name": "@models.dev/web",
"dependencies": {
"@tanstack/virtual-core": "^3.14.0",
"hono": "^4.8.0",
"models.dev": "workspace:*",
},
@@ -48,7 +50,7 @@
"zod": "3.24.2",
},
"packages": {
"@cloudflare/workers-types": ["@cloudflare/workers-types@4.20250801.0", "", {}, "sha512-BQmMdoOGClY23TesgkR1PeGrPvPsSFD/zW7pDzWZHkOEsqkPk2A91h52bP8GbtKYTl1vdaYjQgJlGsP6Ih4G0w=="],
"@cloudflare/workers-types": ["@cloudflare/workers-types@4.20260424.1", "", {}, "sha512-0DLJ9yEk1KKzPbqop80Gw/P1wkKKzawmipULiJWdBXIBCoMvE0OVWms3IrL/Q/G7tfmPop9yF4XlZ69k9JLYng=="],
"@modelcontextprotocol/sdk": ["@modelcontextprotocol/sdk@1.6.1", "", { "dependencies": { "content-type": "^1.0.5", "cors": "^2.8.5", "eventsource": "^3.0.2", "express": "^5.0.1", "express-rate-limit": "^7.5.0", "pkce-challenge": "^4.1.0", "raw-body": "^3.0.0", "zod": "^3.23.8", "zod-to-json-schema": "^3.24.1" } }, "sha512-oxzMzYCkZHMntzuyerehK3fV6A2Kwh5BD6CGEJSVDU2QNEhfLOptf2X7esQgaHZXHZY0oHmMsOtIDLP71UJXgA=="],
@@ -56,9 +58,11 @@
"@models.dev/web": ["@models.dev/web@workspace:packages/web"],
"@tanstack/virtual-core": ["@tanstack/virtual-core@3.14.0", "", {}, "sha512-JLANqGy/D6k4Ujmh8Tr25lGimuOXNiaVyXaCAZS0W+1390sADdGnyUdSWNIfd49gebtIxGMij4IktRVzrdr12Q=="],
"@tsconfig/bun": ["@tsconfig/bun@1.0.8", "", {}, "sha512-JlJaRaS4hBTypxtFe8WhnwV8blf0R+3yehLk8XuyxUYNx6VXsKCjACSCvOYEFUiqlhlBWxtYCn/zRlOb8BzBQg=="],
"@types/bun": ["@types/bun@1.2.16", "", { "dependencies": { "bun-types": "1.2.16" } }, "sha512-1aCZJ/6nSiViw339RsaNhkNoEloLaPzZhxMOYEa7OzRzO41IGg5n/7I43/ZIAW/c+Q6cT12Vf7fOZOoVIzb5BQ=="],
"@types/bun": ["@types/bun@1.3.0", "", { "dependencies": { "bun-types": "1.3.0" } }, "sha512-+lAGCYjXjip2qY375xX/scJeVRmZ5cY0wyHYyCYxNcdEXrQ4AOe3gACgd4iQ8ksOslJtW4VNxBJ8llUwc3a6AA=="],
"@types/node": ["@types/node@22.13.9", "", { "dependencies": { "undici-types": "~6.20.0" } }, "sha512-acBjXdRJ3A6Pb3tqnw9HZmyR3Fiol3aGxRCK1x3d+6CDAMjl7I649wpSd+yNURCjbOUGu9tqtLKnTGxmK6CyGw=="],
@@ -78,7 +82,7 @@
"buffer": ["buffer@4.9.2", "", { "dependencies": { "base64-js": "^1.0.2", "ieee754": "^1.1.4", "isarray": "^1.0.0" } }, "sha512-xq+q3SRMOxGivLhBNaUdC64hDTQwejJ+H0T/NB1XMtTVEwNTrfFF3gAxiyW0Bu/xWEGhjVKgUcMhCrUy2+uCWg=="],
"bun-types": ["bun-types@1.2.16", "", { "dependencies": { "@types/node": "*" } }, "sha512-ciXLrHV4PXax9vHvUrkvun9VPVGOVwbbbBF/Ev1cXz12lyEZMoJpIJABOfPcN9gDJRaiKF9MVbSygLg4NXu3/A=="],
"bun-types": ["bun-types@1.3.0", "", { "dependencies": { "@types/node": "*" }, "peerDependencies": { "@types/react": "^19" } }, "sha512-u8X0thhx+yJ0KmkxuEo9HAtdfgCBaM/aI9K90VQcQioAmkVp3SG3FkwWGibUFz3WdXAdcsqOcbU40lK7tbHdkQ=="],
"bytes": ["bytes@3.1.2", "", {}, "sha512-/Nf7TyzTx6S3yRJObOAV7956r8cr2+Oj8AC5dt8wSP3BQAoeX58NoHyCU8P8zGkNXStjTSi6fzO6F0pBdcYbEg=="],
@@ -240,6 +244,8 @@
"raw-body": ["raw-body@3.0.0", "", { "dependencies": { "bytes": "3.1.2", "http-errors": "2.0.0", "iconv-lite": "0.6.3", "unpipe": "1.0.0" } }, "sha512-RmkhL8CAyCRPXCE28MMH0z2PNWQBNk2Q09ZdxM9IOOXwxwZbN+qbWaatPkdkWIKL2ZVDImrN/pK5HTRz2PcS4g=="],
"remeda": ["remeda@2.33.7", "", {}, "sha512-cXlyjevWx5AcslOUEETG4o8XYi9UkoCXcJmj7XhPFVbla+ITuOBxv6ijBrmbeg+ZhzmDThkNdO+iXKUfrJep1w=="],
"router": ["router@2.2.0", "", { "dependencies": { "debug": "^4.4.0", "depd": "^2.0.0", "is-promise": "^4.0.0", "parseurl": "^1.3.3", "path-to-regexp": "^8.0.0" } }, "sha512-nLTrUKm2UyiL7rlhapu/Zl45FwNgkZGaCpZbIHajDYgwlJCOzLSk+cIPAnsEqV955GjILJnKbdQC1nVPz+gAYQ=="],
"safe-buffer": ["safe-buffer@5.2.1", "", {}, "sha512-rp3So07KcdmmKbGvgaNxQSJr7bGVSVk5S9Eq1F+ppbRo70+YeaDxkw5Dd8NPN+GD6bjnYm2VuPuCXmpuYvmCXQ=="],
@@ -322,8 +328,6 @@
"http-errors/statuses": ["statuses@2.0.1", "", {}, "sha512-RwNA9Z/7PrK06rYLIzFMlaF+l73iwpzsqRIFgbMLbTcLD6cOao82TaWefPXQvB2fOC4AjuYSEndS7N/mTCbkdQ=="],
"models.dev/@types/bun": ["@types/bun@1.3.0", "", { "dependencies": { "bun-types": "1.3.0" } }, "sha512-+lAGCYjXjip2qY375xX/scJeVRmZ5cY0wyHYyCYxNcdEXrQ4AOe3gACgd4iQ8ksOslJtW4VNxBJ8llUwc3a6AA=="],
"opencontrol/@tsconfig/bun": ["@tsconfig/bun@1.0.7", "", {}, "sha512-udGrGJBNQdXGVulehc1aWT73wkR9wdaGBtB6yL70RJsqwW/yJhIg6ZbRlPOfIUiFNrnBuYLBi9CSmMKfDC7dvA=="],
"opencontrol/hono": ["hono@4.7.4", "", {}, "sha512-Pst8FuGqz3L7tFF+u9Pu70eI0xa5S3LPUmrNd5Jm8nTHze9FxLTK9Kaj5g/k4UcwuJSXTP65SyHOPLrffpcAJg=="],
@@ -331,11 +335,5 @@
"openid-client/jose": ["jose@4.15.9", "", {}, "sha512-1vUQX+IdDMVPj4k8kOxgUqlcK518yluMuGZwqlr44FS1ppZB/5GWh4rZG89erpOBOJjU/OBsnCVFfapsRz6nEA=="],
"bun-types/@types/node/undici-types": ["undici-types@7.8.0", "", {}, "sha512-9UJ2xGDvQ43tYyVMpuHlsgApydB8ZKfVYTsLDhXkFL/6gfkp+U8xTGdh8pMJv1SpZna0zxG1DwsKZsreLbXBxw=="],
"models.dev/@types/bun/bun-types": ["bun-types@1.3.0", "", { "dependencies": { "@types/node": "*" }, "peerDependencies": { "@types/react": "^19" } }, "sha512-u8X0thhx+yJ0KmkxuEo9HAtdfgCBaM/aI9K90VQcQioAmkVp3SG3FkwWGibUFz3WdXAdcsqOcbU40lK7tbHdkQ=="],
"models.dev/@types/bun/bun-types/@types/node": ["@types/node@24.0.3", "", { "dependencies": { "undici-types": "~7.8.0" } }, "sha512-R4I/kzCYAdRLzfiCabn9hxWfbuHS573x+r0dJMkkzThEa7pbrcDWK+9zu3e7aBOouf+rQAciqPFMnxwr0aWgKg=="],
"models.dev/@types/bun/bun-types/@types/node/undici-types": ["undici-types@7.8.0", "", {}, "sha512-9UJ2xGDvQ43tYyVMpuHlsgApydB8ZKfVYTsLDhXkFL/6gfkp+U8xTGdh8pMJv1SpZna0zxG1DwsKZsreLbXBxw=="],
}
}
+3
View File
@@ -0,0 +1,3 @@
<svg width="24" height="24" viewBox="0 0 40 40" xmlns="http://www.w3.org/2000/svg">
<path d="M37.9998 23.021C33.7998 25.2889 29.5698 27.3649 24.8614 28.3069C23.8114 28.5154 22.6474 28.5154 21.5809 28.3714C20.5639 28.2439 20.0554 27.3484 20.4169 26.4064C20.7619 25.5289 21.2209 24.635 21.8119 23.9C23.0899 22.3025 24.5329 20.849 25.8289 19.268C26.6203 18.2991 27.3335 17.2689 27.9618 16.187C28.4208 15.4205 28.2078 14.4935 27.4038 14.111C26.0584 13.4556 24.6154 12.9936 23.1889 12.4986C23.0239 12.4341 22.7779 12.6096 22.4509 12.7221C22.8604 13.0881 23.1559 13.3596 23.5654 13.727C19.3339 14.447 15.3305 15.467 11.4455 16.874C11.4275 16.9535 11.396 17.0165 11.411 17.0495C11.9855 17.927 11.723 18.5975 10.886 19.1405C10.5611 19.3531 10.2732 19.6176 10.034 19.9235C12.593 20.6735 14.873 20.243 17.0539 18.821C16.9234 18.6305 16.7914 18.455 16.6609 18.263C17.4799 18.407 17.9719 18.854 18.0379 19.556C18.0544 19.7165 17.9569 19.8755 17.9074 20.036C17.7919 19.907 17.6449 19.781 17.5474 19.6355C17.4799 19.5395 17.4634 19.4285 17.4154 19.268C14.8235 20.993 12.035 21.425 8.96751 20.531C8.96751 21.137 8.93451 21.6485 8.98401 22.1435C9.01701 22.574 8.83701 22.766 8.44401 22.9895C7.55752 23.5325 6.63803 24.092 5.90003 24.8105C5.01504 25.6879 5.34354 26.7589 6.54053 27.2059C7.90102 27.7159 9.329 27.7309 10.7555 27.5569C12.4445 27.3484 14.1005 27.0769 15.9394 26.8219C13.79 27.8269 11.6735 28.5319 9.4445 28.8169C7.88452 29.0269 6.32753 29.1379 4.78554 28.6909C2.57156 28.0684 1.58607 26.4394 2.16057 24.251C2.70206 22.2065 4.01455 20.5775 5.42454 19.076C10.133 14.078 16.0864 11.5401 22.9744 11.0286C24.5824 10.9176 26.2069 11.1246 27.7143 11.7951C29.8308 12.7536 30.7173 14.78 29.6838 16.826C29.0118 18.1835 28.0758 19.4285 27.1413 20.6585C26.2234 21.872 25.1899 22.9895 24.2224 24.155C23.9434 24.506 23.6809 24.875 23.4679 25.2724C23.0569 26.0224 23.3359 26.5174 24.2059 26.4394C26.0254 26.2624 27.8808 26.1199 29.6358 25.6729C32.2098 25.0174 34.7193 24.092 37.2618 23.2775C37.5243 23.213 37.7703 23.117 37.9998 23.0225V23.021Z" fill="currentColor"/>
</svg>

After

Width:  |  Height:  |  Size: 2.0 KiB

+3
View File
@@ -0,0 +1,3 @@
<svg width="24" height="24" viewBox="0 0 40 40" xmlns="http://www.w3.org/2000/svg">
<path d="M26.9568 9.88184H22.1265L30.7753 31.7848H35.4917L26.9568 9.88184ZM13.028 9.88184L4.4917 31.7848H9.32203L11.2305 27.1793H20.2166L22.0126 31.6724H26.8444L18.0832 9.88184H13.028ZM12.5783 23.1361L15.4987 15.3853L18.5315 23.1361H12.5783Z" fill="currentColor"/>
</svg>

After

Width:  |  Height:  |  Size: 355 B

+5
View File
@@ -0,0 +1,5 @@
<svg width="24" height="24" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg">
<path d="M9.14882 13.5552C9.58082 13.5552 10.4448 13.5336 11.6544 13.0368C13.0584 12.4536 15.8232 11.4168 17.832 10.3368C19.236 9.5808 19.8408 8.5872 19.8408 7.248C19.8408 5.412 18.3504 3.9 16.4928 3.9H8.71682C6.06002 3.9 3.90002 6.06 3.90002 8.7168C3.90002 11.3736 5.93042 13.5552 9.14882 13.5552Z" fill="currentColor"/>
<path d="M10.4664 16.86C10.4664 15.564 11.244 14.376 12.4536 13.8792L14.8944 12.864C17.3784 11.8488 20.1 13.6632 20.1 16.3416C20.1 18.4152 18.4152 20.1 16.3416 20.1H13.6848C11.9136 20.1 10.4664 18.6528 10.4664 16.86Z" fill="currentColor"/>
<path d="M6.68642 14.1816C5.15282 14.1816 3.90002 15.4344 3.90002 16.968V17.3352C3.90002 18.8472 5.15282 20.1 6.68642 20.1C8.22003 20.1 9.47283 18.8472 9.47283 17.3136V16.9464C9.45123 15.4344 8.22003 14.1816 6.68642 14.1816Z" fill="currentColor"/>
</svg>

After

Width:  |  Height:  |  Size: 913 B

+3
View File
@@ -0,0 +1,3 @@
<svg width="24" height="24" viewBox="0 0 40 40" xmlns="http://www.w3.org/2000/svg">
<path d="M35.6638 9.91965C35.3251 9.75432 35.1785 10.0703 34.9811 10.2316C34.9131 10.2836 34.8558 10.3516 34.7985 10.413C34.3025 10.9423 33.7238 11.289 32.9678 11.2476C31.8625 11.1863 30.9186 11.533 30.0839 12.3783C29.9066 11.3356 29.3173 10.7143 28.4213 10.3143C27.9519 10.1063 27.4773 9.89965 27.148 9.44766C26.9186 9.12633 26.856 8.76767 26.7413 8.41568C26.668 8.20235 26.5946 7.98502 26.3506 7.94902C26.084 7.90769 25.98 8.13035 25.876 8.31702C25.4587 9.07967 25.2973 9.91965 25.3133 10.7703C25.3493 12.6849 26.1573 14.2102 27.764 15.2942C27.9466 15.4182 27.9933 15.5435 27.9359 15.7249C27.8266 16.0982 27.696 16.4609 27.5813 16.8355C27.508 17.0742 27.3986 17.1248 27.1426 17.0222C26.2777 16.6504 25.4919 16.1164 24.828 15.4489C23.6854 14.3449 22.6534 13.1263 21.3654 12.1716C21.067 11.9511 20.7606 11.7416 20.4468 11.5436C19.1335 10.2676 20.6201 9.21967 20.9641 9.09567C21.3241 8.965 21.0881 8.51968 19.9254 8.52501C18.7628 8.53035 17.6988 8.91834 16.3428 9.43699C16.1413 9.51421 15.934 9.57529 15.7229 9.61966C14.4557 9.38091 13.1598 9.33506 11.8789 9.48366C9.36565 9.76365 7.35902 10.953 5.88305 12.9809C4.10975 15.4182 3.69243 18.1888 4.20308 21.0768C4.74041 24.122 6.29504 26.6433 8.683 28.6139C11.1603 30.6579 14.0122 31.6592 17.2668 31.4672C19.2428 31.3539 21.4441 31.0886 23.9254 28.9873C24.552 29.2993 25.208 29.4233 26.2986 29.5166C27.1386 29.5953 27.9466 29.4766 28.5719 29.3459C29.5519 29.1379 29.4839 28.23 29.1306 28.0646C26.2573 26.726 26.888 27.2713 26.3133 26.83C27.7746 25.102 29.9746 23.3074 30.8359 17.4928C30.9026 17.0302 30.8452 16.7395 30.8359 16.3662C30.8306 16.1395 30.8826 16.0502 31.1426 16.0249C31.8639 15.95 32.5637 15.7349 33.2025 15.3915C35.0638 14.3742 35.8158 12.7049 35.9931 10.7023C36.0198 10.3956 35.9878 10.081 35.6638 9.91965ZM19.4414 27.9433C16.6562 25.754 15.3055 25.0327 14.7482 25.0634C14.2256 25.0954 14.3202 25.6913 14.4349 26.0807C14.5549 26.4647 14.7109 26.7286 14.9295 27.066C15.0815 27.2886 15.1855 27.6206 14.7789 27.87C13.8816 28.4246 12.3229 27.6833 12.2496 27.6473C10.435 26.578 8.91632 25.1673 7.84834 23.2381C6.81637 21.3808 6.21638 19.3888 6.11771 17.2622C6.09105 16.7475 6.24171 16.5662 6.7537 16.4729C7.42583 16.3442 8.11451 16.3267 8.79233 16.4209C11.6349 16.8368 14.0536 18.1075 16.0828 20.1194C17.2402 21.2661 18.1161 22.6354 19.0188 23.974C19.9788 25.3953 21.0108 26.75 22.3254 27.8593C22.7894 28.2486 23.1587 28.5446 23.5134 28.7619C22.4441 28.8819 20.6601 28.9086 19.4414 27.9433ZM20.7748 19.3568C20.7745 19.2906 20.7904 19.2253 20.8211 19.1666C20.8517 19.1078 20.8962 19.0575 20.9507 19.0198C21.0052 18.9821 21.068 18.9583 21.1337 18.9503C21.1995 18.9424 21.2662 18.9505 21.3281 18.9741C21.407 19.0024 21.475 19.0546 21.5228 19.1235C21.5706 19.1923 21.5958 19.2743 21.5947 19.3581C21.5949 19.4123 21.5843 19.4659 21.5636 19.5159C21.5428 19.5659 21.5123 19.6113 21.4738 19.6494C21.4354 19.6875 21.3897 19.7176 21.3395 19.7378C21.2893 19.7581 21.2356 19.7682 21.1814 19.7675C21.1277 19.7676 21.0745 19.7571 21.0248 19.7365C20.9752 19.7158 20.9302 19.6855 20.8925 19.6473C20.8548 19.609 20.825 19.5636 20.805 19.5138C20.785 19.4639 20.7739 19.4105 20.7748 19.3568ZM24.9213 21.4848C24.6547 21.5928 24.3893 21.6861 24.1347 21.6981C23.7516 21.7114 23.3756 21.5918 23.0707 21.3594C22.7054 21.0528 22.4441 20.8821 22.3347 20.3488C22.297 20.0881 22.3042 19.823 22.3561 19.5648C22.4494 19.1288 22.3454 18.8488 22.0374 18.5955C21.7881 18.3875 21.4694 18.3302 21.1201 18.3302C21.0005 18.3232 20.8843 18.2875 20.7814 18.2262C20.6348 18.1542 20.5148 17.9728 20.6294 17.7488C20.6668 17.6768 20.8428 17.5008 20.8854 17.4688C21.3601 17.1995 21.9081 17.2875 22.4134 17.4902C22.8827 17.6822 23.2374 18.0342 23.748 18.5328C24.2694 19.1341 24.364 19.3008 24.6613 19.7515C24.896 20.1048 25.1093 20.4674 25.2547 20.8821C25.344 21.1421 25.2293 21.3541 24.9213 21.4848Z" fill="currentColor"/>
</svg>

After

Width:  |  Height:  |  Size: 3.8 KiB

+3
View File
@@ -0,0 +1,3 @@
<svg width="24" height="24" viewBox="0 0 40 40" xmlns="http://www.w3.org/2000/svg">
<path d="M37 20.034C27.8809 20.5837 20.5808 27.8809 20.0326 37H19.966C19.4163 27.8809 12.1177 20.5837 3 20.034V19.9674C12.1191 19.4163 19.4163 12.1191 19.966 3H20.0326C20.5822 12.1191 27.8809 19.4163 37 19.9674V20.034Z" fill="currentColor"/>
</svg>

After

Width:  |  Height:  |  Size: 333 B

+3
View File
@@ -0,0 +1,3 @@
<svg width="24" height="24" viewBox="0 0 40 40" xmlns="http://www.w3.org/2000/svg">
<path d="M27.1942 9.03509C24.4881 9.03509 22.3726 11.0731 20.4574 13.6623C17.8258 10.3114 15.6255 9.03509 12.9925 9.03509C7.62404 9.03509 3.51001 16.0234 3.51001 23.4181C3.51001 28.0453 5.74831 30.9649 9.49831 30.9649C12.1971 30.9649 14.1387 29.693 17.5904 23.6594C17.5904 23.6594 19.029 21.1199 20.0173 19.3699C20.3643 19.9293 20.7298 20.5327 21.1138 21.1798L22.7322 23.902C25.8843 29.1769 27.6416 30.9649 30.8229 30.9649C34.4778 30.9649 36.51 28.0058 36.51 23.2822C36.51 15.538 32.3039 9.03509 27.1942 9.03509ZM14.9574 22.0263C12.1606 26.4123 11.1928 27.3962 9.63574 27.3962C8.03194 27.3962 7.07872 25.9883 7.07872 23.4781C7.07872 18.1096 9.75562 12.6199 12.9471 12.6199C14.6752 12.6199 16.1197 13.617 18.3316 16.7836C16.2308 20.0058 14.9574 22.0263 14.9574 22.0263ZM25.5202 21.4751L23.5831 18.2456C23.0969 17.4514 22.5938 16.6676 22.0743 15.8947C23.8185 13.2032 25.2556 11.8611 26.9676 11.8611C30.5202 11.8611 33.3638 17.095 33.3638 23.5219C33.3638 25.9722 32.5612 27.3947 30.8989 27.3947C29.3053 27.3947 28.5451 26.3421 25.5188 21.4737" fill="currentColor"/>
</svg>

After

Width:  |  Height:  |  Size: 1.1 KiB

+3
View File
@@ -0,0 +1,3 @@
<svg width="24" height="24" viewBox="0 0 40 40" xmlns="http://www.w3.org/2000/svg">
<path d="M17.8758 9.20865C17.8758 8.59461 17.3777 8.09634 16.7663 8.09634C16.155 8.09634 15.6567 8.59575 15.6567 9.20865V27.6446C15.6567 29.0714 14.4985 30.2324 13.0755 30.2324C11.6523 30.2324 10.4941 29.0714 10.4941 27.6446V15.8167C10.4941 15.2027 9.99591 14.7044 9.38453 14.7044C8.77316 14.7044 8.275 15.2038 8.275 15.8167V20.8301C8.275 22.2567 7.11678 23.4179 5.69364 23.4179C4.2705 23.4179 3.1123 22.2567 3.1123 20.8301V19.0129C3.1123 18.6054 3.44177 18.2752 3.84822 18.2752C4.25467 18.2752 4.58413 18.6054 4.58413 19.0129V20.8301C4.58413 21.4441 5.08227 21.9424 5.69364 21.9424C6.30502 21.9424 6.80317 21.443 6.80317 20.8301V15.8167C6.80317 14.39 7.96139 13.2289 9.38453 13.2289C10.8077 13.2289 11.9659 14.39 11.9659 15.8167V27.6446C11.9659 28.2587 12.4641 28.7569 13.0755 28.7569C13.6868 28.7569 14.1849 28.2575 14.1849 27.6446V20.4123V9.20865C14.1849 7.78194 15.3431 6.62082 16.7663 6.62082C18.1894 6.62082 19.3476 7.78194 19.3476 9.20865V24.4746C19.3476 24.8821 19.0182 25.2123 18.6117 25.2123C18.2053 25.2123 17.8758 24.8821 17.8758 24.4746V9.20865ZM31.531 13.2289C30.1079 13.2289 28.9496 14.39 28.9496 15.8167V25.6969C28.9496 26.311 28.4515 26.8093 27.8401 26.8093C27.2287 26.8093 26.7306 26.3099 26.7306 25.6969V9.20865C26.7306 7.78194 25.5723 6.62082 24.1492 6.62082C22.7261 6.62082 21.5679 7.78194 21.5679 9.20865V30.1383C21.5679 30.7523 21.0697 31.2506 20.4583 31.2506C19.8469 31.2506 19.3488 30.7511 19.3488 30.1383V27.5471C19.3488 27.1396 19.0194 26.8093 18.6129 26.8093C18.2065 26.8093 17.877 27.1396 17.877 27.5471V30.1383C17.877 31.565 19.0352 32.7261 20.4583 32.7261C21.8815 32.7261 23.0397 31.565 23.0397 30.1383V9.20865C23.0397 8.59461 23.5378 8.09634 24.1492 8.09634C24.7605 8.09634 25.2587 8.59575 25.2587 9.20865V25.6969C25.2587 27.1237 26.417 28.2848 27.8401 28.2848C29.2632 28.2848 30.4215 27.1237 30.4215 25.6969V15.8167C30.4215 15.2027 30.9196 14.7044 31.531 14.7044C32.1424 14.7044 32.6405 15.2038 32.6405 15.8167V24.4746C32.6405 24.8821 32.97 25.2123 33.3764 25.2123C33.7829 25.2123 34.1123 24.8821 34.1123 24.4746V15.8167C34.1123 14.39 32.9541 13.2289 31.531 13.2289Z" fill="currentColor"/>
</svg>

After

Width:  |  Height:  |  Size: 2.2 KiB

+3
View File
@@ -0,0 +1,3 @@
<svg width="24" height="24" viewBox="0 0 40 40" xmlns="http://www.w3.org/2000/svg">
<path d="M8.92783 8.88101H13.357V13.3088H17.7861V17.738H17.7835H22.2152V13.3088H26.6418V8.88101H31.0722V26.5949H35.5V31.0241H22.2139V26.5962H17.7861V22.1671H13.3557V26.5949L17.7861 26.5962V31.0241H4.5V26.5949H8.92783V8.88101ZM22.2139 26.5962H26.6418V22.1671H22.2152V26.5962H22.2139Z" fill="currentColor"/>
</svg>

After

Width:  |  Height:  |  Size: 397 B

File diff suppressed because one or more lines are too long

After

Width:  |  Height:  |  Size: 6.7 KiB

+3
View File
@@ -0,0 +1,3 @@
<svg width="24" height="24" viewBox="0 0 40 40" xmlns="http://www.w3.org/2000/svg">
<path d="M16.1801 15.8791V14.0283C16.3472 14.0155 16.5271 14.0026 16.7199 14.0026C21.7966 13.8356 25.1254 18.3596 25.1254 18.3596C25.1254 18.3596 21.5267 23.3463 17.671 23.3463C17.1569 23.3463 16.6557 23.2692 16.1801 23.1021V17.4728C18.1465 17.7298 18.545 18.591 19.7274 20.5702L22.375 18.3468C22.375 18.3468 20.4343 15.8277 17.1955 15.8277C16.8356 15.8277 16.5014 15.8405 16.1801 15.8791ZM16.1801 9.75492V12.5246C16.3472 12.5118 16.5271 12.4989 16.7199 12.4861C23.763 12.2547 28.377 18.2696 28.377 18.2696C28.377 18.2696 23.0819 24.683 17.5939 24.683C17.0798 24.683 16.6171 24.6444 16.1801 24.5545V26.2767C16.5528 26.3152 16.9384 26.341 17.3625 26.341C22.4649 26.341 26.1664 23.7448 29.7523 20.6473C30.3435 21.1229 32.7597 22.2796 33.261 22.7937C29.8679 25.6341 21.9251 27.9346 17.4396 27.9346C17.0155 27.9346 16.5914 27.9089 16.1801 27.8704V30.2866H35.6001V9.75492H16.1801ZM16.1801 23.1021V24.5545C11.4376 23.7191 10.1266 18.7966 10.1266 18.7966C10.1266 18.7966 12.4015 16.2775 16.1801 15.8791V17.4728H16.1673C14.188 17.2414 12.6329 19.0922 12.6329 19.0922C12.6329 19.0922 13.5068 22.2025 16.1801 23.1021ZM7.77464 18.591C7.77464 18.591 10.5765 14.4525 16.1801 14.0283V12.5246C9.9724 13.0259 4.6001 18.2696 4.6001 18.2696C4.6001 18.2696 7.64612 27.0735 16.1801 27.8575V26.2767C9.90814 25.4798 7.77464 18.591 7.77464 18.591Z" fill="currentColor"/>
</svg>

After

Width:  |  Height:  |  Size: 1.4 KiB

+3
View File
@@ -0,0 +1,3 @@
<svg width="24" height="24" viewBox="0 0 40 40" xmlns="http://www.w3.org/2000/svg">
<path d="M32.8377 17.282C33.2127 16.25 33.3072 15.218 33.2127 14.1875C33.1197 13.1571 32.7447 12.1251 32.2752 11.1876C31.4322 9.78209 30.2127 8.6571 28.8072 8.0001C27.3072 7.34461 25.7127 7.15711 24.1197 7.53211C23.3698 6.78212 22.5253 6.12512 21.5878 5.65713C20.6503 5.18913 19.5253 5.00013 18.4948 5.00013C16.8851 4.99074 15.3125 5.48246 13.9948 6.40712C12.6824 7.34311 11.7449 8.6571 11.2754 10.1571C10.1504 10.4376 9.21289 10.9071 8.27539 11.4696C7.4324 12.1251 6.77541 12.9696 6.21291 13.8126C5.36992 15.2195 5.08792 16.8125 5.27542 18.407C5.46399 19.9968 6.11605 21.496 7.1504 22.718C6.79608 23.7086 6.66795 24.7659 6.77541 25.8124C6.86991 26.8444 7.2449 27.8749 7.7129 28.8124C8.55739 30.2194 9.77538 31.3444 11.1824 31.9999C12.6824 32.6569 14.2753 32.8444 15.8698 32.4694C16.6198 33.2194 17.4628 33.8749 18.4003 34.3444C19.3378 34.8139 20.4628 34.9999 21.4948 34.9999C23.1043 35.0097 24.6769 34.5185 25.9947 33.5944C27.3072 32.6569 28.2447 31.3444 28.7127 29.8444C29.7719 29.6432 30.7682 29.1934 31.6197 28.5319C32.4627 27.8749 33.2127 27.1249 33.6822 26.1874C34.5251 24.7819 34.8071 23.1875 34.6196 21.5945C34.4322 20 33.8697 18.5015 32.8377 17.282ZM21.5878 33.0304C20.0878 33.0304 18.9628 32.5609 17.9323 31.7179C17.9323 31.7179 18.0253 31.6234 18.1198 31.6234L24.1197 28.1554C24.2862 28.0803 24.4196 27.9469 24.4947 27.7804C24.5698 27.636 24.6021 27.4731 24.5877 27.3109V18.875L27.1197 20.375V27.3124C27.1455 28.0547 27.0215 28.7945 26.755 29.4878C26.4885 30.181 26.085 30.8134 25.5687 31.3473C25.0523 31.8811 24.4337 32.3054 23.7497 32.5949C23.0658 32.8843 22.3305 33.0314 21.5878 33.0304ZM9.49488 27.8749C8.83789 26.7499 8.55739 25.4374 8.83789 24.125C8.83789 24.125 8.93239 24.2195 9.02539 24.2195L15.0253 27.6874C15.1693 27.7638 15.3325 27.7966 15.4948 27.7819C15.6823 27.7819 15.8698 27.7819 15.9628 27.6874L23.2753 23.4695V26.3749L17.1823 29.9374C16.5506 30.3042 15.8527 30.5427 15.1287 30.6393C14.4046 30.7358 13.6686 30.6884 12.9629 30.4999C11.4629 30.1249 10.2449 29.1874 9.49488 27.8749ZM7.9004 14.8445C8.56239 13.7234 9.58826 12.8627 10.8074 12.4056V19.532C10.8074 19.718 10.8074 19.907 10.9004 20C10.9755 20.1665 11.1089 20.2998 11.2754 20.375L18.5878 24.5944L16.0573 26.0944L10.0574 22.625C9.41842 22.2639 8.85742 21.7797 8.40684 21.2004C7.95627 20.6211 7.62506 19.9582 7.4324 19.25C7.05741 17.8445 7.1504 16.157 7.9004 14.8445ZM28.6197 19.625L21.3073 15.407L23.8377 13.9071L29.8377 17.375C30.7752 17.9375 31.5252 18.6875 31.9947 19.625C32.4642 20.5625 32.7447 21.5945 32.6502 22.7195C32.5603 23.7755 32.1699 24.7837 31.5252 25.6249C30.8697 26.4694 30.0252 27.1249 28.9947 27.4999V20.375C28.9947 20.1875 28.9947 20 28.9002 19.907C28.9002 19.907 28.8072 19.718 28.6197 19.625ZM31.1502 15.875C31.1502 15.875 31.0572 15.782 30.9627 15.782L24.9627 12.3126C24.7752 12.2196 24.6822 12.2196 24.4947 12.2196C24.3072 12.2196 24.1197 12.2196 24.0252 12.3126L16.7128 16.532V13.6251L22.8073 10.0626C23.7448 9.50009 24.7752 9.31259 25.9002 9.31259C26.9322 9.31259 27.9627 9.68759 28.9002 10.3446C29.7447 11.0001 30.4947 11.8446 30.8697 12.7821C31.2447 13.7196 31.3377 14.8445 31.1502 15.875ZM15.4003 21.125L12.8699 19.625V12.5946C12.8699 11.5626 13.1503 10.4376 13.7128 9.59459C14.2753 8.6571 15.1198 8.0001 16.0573 7.53211C17.0127 7.05249 18.0956 6.88812 19.1503 7.06261C20.1823 7.15711 21.2128 7.62511 22.0573 8.2821C22.0573 8.2821 21.9628 8.3751 21.8698 8.3751L15.8698 11.8446C15.7033 11.9197 15.57 12.0531 15.4948 12.2196C15.4003 12.4071 15.4003 12.5001 15.4003 12.6876V21.125ZM16.7128 18.125L19.9948 16.25L23.2753 18.125V21.875L19.9948 23.75L16.7128 21.875V18.125Z" fill="currentColor"/>
</svg>

After

Width:  |  Height:  |  Size: 3.6 KiB

+3
View File
@@ -0,0 +1,3 @@
<svg width="24" height="24" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg">
<path d="M17.2642 2.8689L12.042 8.0961M17.2642 2.8689V8.0961H12.042M17.2642 2.8689V4.30027M12.042 8.0961L6.81809 2.8689V8.0961H12.042ZM12.042 8.0961L17.2642 13.3225V20.8159L12.042 15.5887M12.042 8.0961V15.5887M12.042 8.0961L6.81892 13.3225M12.0296 2.1V21.9M12.042 15.5887L6.81892 20.8159V13.3225M6.81892 13.3225L6.81809 15.559H4.57739V8.09527H12.0412L6.81892 13.3225ZM11.9859 8.09527L17.2081 13.3225V15.559H19.4497V8.09527H11.9859Z" stroke="currentColor" stroke-width="0.825" stroke-miterlimit="10"/>
</svg>

After

Width:  |  Height:  |  Size: 604 B

+3
View File
@@ -0,0 +1,3 @@
<svg width="24" height="24" viewBox="0 0 32 32" fill="none" xmlns="http://www.w3.org/2000/svg">
<path fill-rule="evenodd" clip-rule="evenodd" d="M18.0835 25.1541C19.5821 26.7684 21.1466 28.1292 22.6694 29.2117L21.5103 30.8416C19.8992 29.6963 18.2543 28.2675 16.6802 26.5808C17.1455 26.1486 17.6143 25.6722 18.0835 25.1541ZM9.99365 2.74979C11.7639 1.73255 13.8054 2.24897 15.6479 3.32304C17.52 4.41448 19.4573 6.22477 21.2603 8.33866L19.7378 9.63651C18.0045 7.60434 16.238 5.98161 14.6411 5.05058C13.0147 4.10247 11.8203 4.00682 10.9897 4.48417C10.0366 5.03255 9.41678 6.47496 9.78271 9.17167C9.86549 9.78127 9.99965 10.4345 10.1812 11.1277C11.6144 10.9497 13.0985 10.8513 14.6167 10.8543C17.7104 10.8604 20.4741 11.1506 22.7944 11.6805L22.7964 11.6814C23.2 11.7609 23.5914 11.858 23.9702 11.9656C23.9685 11.9703 23.9661 11.9746 23.9644 11.9793C24.661 12.1766 25.3101 12.3961 25.9067 12.6404C28.6066 13.7462 30.6077 15.4947 30.603 17.8855C30.599 19.9274 29.1314 21.4372 27.2798 22.4959C25.3986 23.5714 22.8625 24.344 20.1304 24.8484L19.7671 22.8807C22.3935 22.3957 24.6819 21.677 26.2866 20.7596C27.9209 19.8251 28.6011 18.8396 28.603 17.8816C28.6051 16.7818 27.6669 15.5237 25.1479 14.492C24.5672 14.2542 23.9208 14.0387 23.2134 13.8465C22.6517 15.1437 22.0035 16.4444 21.2612 17.7244C18.9392 21.7281 16.437 24.776 14.0688 26.6082C11.7614 28.3932 9.24631 29.2529 7.17822 28.0535C5.41209 27.0291 4.83828 25.0026 4.84717 22.8699C4.85632 20.7032 5.45524 18.1208 6.38428 15.5027L8.27002 16.1717C7.37685 18.6887 6.85497 21.0304 6.84717 22.8787C6.83939 24.7607 7.35367 25.8424 8.18213 26.323C9.13349 26.8747 10.6925 26.6915 12.8452 25.0262C13.3191 24.6595 13.8045 24.2295 14.3003 23.742C13.4493 22.6129 12.6395 21.4021 11.897 20.1101C9.59084 16.0976 8.20303 12.4071 7.80029 9.44022C7.40803 6.54936 7.92116 3.94134 9.99365 2.74979ZM14.6128 12.8543C13.3044 12.8518 12.0235 12.9291 10.7827 13.0701C11.4353 14.9013 12.3808 16.9381 13.6313 19.1141C14.2698 20.2249 14.9606 21.2715 15.6841 22.2537C16.9553 20.7654 18.2592 18.9138 19.5308 16.7215C20.1679 15.623 20.7315 14.5102 21.2271 13.4012C19.3246 13.0558 17.1033 12.8592 14.6128 12.8543ZM6.23193 11.8416C6.39799 12.459 6.59817 13.0982 6.83154 13.7566C4.8717 14.2207 3.07218 14.836 1.49854 15.5398L0.682129 13.7137C2.33167 12.9759 4.20224 12.3309 6.23193 11.8416ZM24.8901 3.62675L25.8853 3.70976C25.7206 5.68459 25.2981 7.84221 24.6128 10.0701C24.1572 9.9381 23.6801 9.8164 23.1831 9.71854C23.0101 9.6845 22.8337 9.6559 22.6567 9.62577C23.3278 7.47916 23.7373 5.41176 23.8931 3.54276L24.8901 3.62675Z" fill="currentColor"/>
</svg>

After

Width:  |  Height:  |  Size: 2.5 KiB

+3
View File
@@ -0,0 +1,3 @@
<svg width="24" height="24" viewBox="0 0 40 40" xmlns="http://www.w3.org/2000/svg">
<path d="M12.4579 15.6036L26.1529 35H20.0656L6.37059 15.6036H12.4579ZM12.4524 26.3764L15.4974 30.6909L12.4551 35H6.36377L12.4524 26.3764ZM33.6365 7.15727V35H28.647V14.2236L33.6365 7.15727ZM33.6365 5L20.0656 24.2205L17.0206 19.9073L27.5451 5H33.6365Z" fill="currentColor"/>
</svg>

After

Width:  |  Height:  |  Size: 364 B

+3
View File
@@ -0,0 +1,3 @@
<svg width="24" height="24" viewBox="0 0 40 40" xmlns="http://www.w3.org/2000/svg">
<path d="M17.3598 5.03522C13.6378 5.20577 11.3905 5.78765 9.47432 7.07179C8.10992 7.97471 7.10668 9.14849 6.38435 10.6935C5.59179 12.389 5.24066 14.255 5.09017 17.7262C4.90959 21.6087 5.17043 25.4812 5.75231 27.5378C6.27399 29.4039 7.10668 30.8285 8.38079 32.0223C9.95588 33.487 11.7216 34.2595 14.4604 34.6709C16.9685 35.0421 22.7773 35.0621 25.3154 34.711C28.4054 34.2896 30.3718 33.4168 31.987 31.7414C32.7896 30.9187 33.1608 30.377 33.6824 29.2835C34.4951 27.5679 34.8261 25.7922 34.9867 22.2407C35.107 19.7026 34.9867 16.0909 34.7358 14.4055C34.1439 10.4527 32.4585 7.88441 29.519 6.39962C27.964 5.62713 25.6766 5.17567 22.4963 5.02519C20.0986 4.91483 19.7776 4.91483 17.3598 5.03522ZM21.0617 14.3854C22.386 14.6964 23.0281 15.1378 23.4494 16.0407C23.8808 16.9637 23.951 17.7262 23.951 21.8896V25.8022L22.5264 25.7721L21.0918 25.742L21.0417 21.9297C20.9915 17.7663 20.9714 17.6359 20.3895 17.1844C19.8679 16.7731 19.4264 16.7229 16.5772 16.7129H13.8685L13.8183 21.2275L13.7682 25.742H10.9591L10.929 20.0336C10.909 15.5291 10.939 14.2951 11.0293 14.2349C11.0996 14.1847 13.2365 14.1647 15.7747 14.1847C19.4967 14.2249 20.52 14.265 21.0617 14.3854ZM28.9472 14.3252C29.0174 14.4657 29.0475 25.3708 28.9773 25.722C28.9773 25.7621 28.3252 25.7822 27.5426 25.7721L26.108 25.742L26.0779 20.0838C26.0679 15.9906 26.0879 14.3854 26.1682 14.2951C26.2585 14.1847 26.6096 14.1546 27.5727 14.1546C28.6964 14.1546 28.8669 14.1747 28.9472 14.3252ZM18.9349 22.2307V25.8022L17.4601 25.7721L15.9753 25.742L15.9452 22.331C15.9352 20.455 15.9452 18.8598 15.9753 18.7996C16.0054 18.6993 16.3967 18.6692 17.4802 18.6692H18.9349V22.2307Z" fill="currentColor"/>
</svg>

After

Width:  |  Height:  |  Size: 1.7 KiB

+3
View File
@@ -0,0 +1,3 @@
<svg width="24" height="24" viewBox="0 0 40 40" xmlns="http://www.w3.org/2000/svg">
<path d="M20.1312 7.50002L17.4088 11.1913H5.81625L8.5375 7.50002H20.1325H20.1312ZM34.0675 28.81L31.3475 32.5H19.795L22.5125 28.81H34.0675ZM35 7.50002L16.58 32.5H5L23.42 7.50002H35Z" fill="currentColor"/>
</svg>

After

Width:  |  Height:  |  Size: 295 B

+1
View File
File diff suppressed because one or more lines are too long
+18
View File
@@ -0,0 +1,18 @@
name = "Qwen Flash"
family = "qwen"
release_date = "2025-07-28"
last_updated = "2025-07-28"
attachment = false
reasoning = true
temperature = true
tool_call = true
knowledge = "2024-04"
open_weights = false
[limit]
context = 1_000_000
output = 32_768
[modalities]
input = ["text"]
output = ["text"]
+25
View File
@@ -0,0 +1,25 @@
name = "Qwen Max"
family = "qwen"
release_date = "2024-04-03"
last_updated = "2025-01-25"
attachment = false
reasoning = false
temperature = true
tool_call = true
knowledge = "2024-04"
open_weights = false
[limit]
context = 32_768
output = 8_192
[modalities]
input = ["text"]
output = ["text"]
[[benchmarks]]
name = "Aider Polyglot"
score = 21.8
metric = "percent correct"
source = "https://aider.chat/docs/leaderboards/"
date = "2025-01-28"
+18
View File
@@ -0,0 +1,18 @@
name = "Qwen-Omni Turbo"
family = "qwen"
release_date = "2025-01-19"
last_updated = "2025-03-26"
attachment = false
reasoning = false
temperature = true
tool_call = true
knowledge = "2024-04"
open_weights = false
[limit]
context = 32_768
output = 2_048
[modalities]
input = ["text", "image", "audio", "video"]
output = ["text", "audio"]
+18
View File
@@ -0,0 +1,18 @@
name = "Qwen Plus"
family = "qwen"
release_date = "2024-01-25"
last_updated = "2025-09-11"
attachment = false
reasoning = true
temperature = true
tool_call = true
knowledge = "2024-04"
open_weights = false
[limit]
context = 1_000_000
output = 32_768
[modalities]
input = ["text"]
output = ["text"]
+18
View File
@@ -0,0 +1,18 @@
name = "Qwen Turbo"
family = "qwen"
release_date = "2024-11-01"
last_updated = "2025-04-28"
attachment = false
reasoning = true
temperature = true
tool_call = true
knowledge = "2024-04"
open_weights = false
[limit]
context = 1_000_000
output = 16_384
[modalities]
input = ["text"]
output = ["text"]
+18
View File
@@ -0,0 +1,18 @@
name = "Qwen-VL Max"
family = "qwen"
release_date = "2024-04-08"
last_updated = "2025-08-13"
attachment = false
reasoning = false
temperature = true
tool_call = true
knowledge = "2024-04"
open_weights = false
[limit]
context = 131_072
output = 8_192
[modalities]
input = ["text", "image"]
output = ["text"]
+18
View File
@@ -0,0 +1,18 @@
name = "Qwen-VL Plus"
family = "qwen"
release_date = "2024-01-25"
last_updated = "2025-08-15"
attachment = false
reasoning = false
temperature = true
tool_call = true
knowledge = "2024-04"
open_weights = false
[limit]
context = 131_072
output = 8_192
[modalities]
input = ["text", "image"]
output = ["text"]
@@ -0,0 +1,22 @@
name = "Qwen2.5-VL 72B Instruct"
family = "qwen"
release_date = "2024-09"
last_updated = "2024-09"
attachment = false
reasoning = false
temperature = true
tool_call = true
knowledge = "2024-04"
open_weights = true
[limit]
context = 131_072
output = 8_192
[modalities]
input = ["text", "image"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct"
+36
View File
@@ -0,0 +1,36 @@
name = "Qwen3 235B-A22B"
family = "qwen"
release_date = "2025-04"
last_updated = "2025-04"
attachment = false
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-04"
open_weights = true
[limit]
context = 131_072
output = 16_384
[modalities]
input = ["text"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/Qwen/Qwen3-235B-A22B"
[[benchmarks]]
name = "Aider Polyglot"
score = 59.6
metric = "percent correct"
source = "https://aider.chat/docs/leaderboards/"
date = "2025-05-09"
[[benchmarks]]
name = "SWE-Bench Pro"
score = 21.41
metric = "resolve rate"
dataset = "public"
source = "https://labs.scale.com/leaderboard/swe_bench_pro_public"
+29
View File
@@ -0,0 +1,29 @@
name = "Qwen3 32B"
family = "qwen"
release_date = "2025-04"
last_updated = "2025-04"
attachment = false
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-04"
open_weights = true
[limit]
context = 131_072
output = 16_384
[modalities]
input = ["text"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/Qwen/Qwen3-32B"
[[benchmarks]]
name = "Aider Polyglot"
score = 40.0
metric = "percent correct"
source = "https://aider.chat/docs/leaderboards/"
date = "2025-05-08"
@@ -0,0 +1,43 @@
name = "Qwen3-Coder 30B-A3B Instruct"
family = "qwen"
release_date = "2025-04"
last_updated = "2025-04"
attachment = false
reasoning = false
temperature = true
tool_call = true
knowledge = "2025-04"
open_weights = true
[limit]
context = 262_144
output = 65_536
[modalities]
input = ["text"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct"
[[benchmarks]]
name = "Artificial Analysis Coding Index"
score = 19.4
metric = "index"
source = "https://openrouter.ai/qwen/qwen3-coder-30b-a3b-instruct/benchmarks"
date = "2026-06-02"
[[benchmarks]]
name = "SciCode"
score = 27.8
metric = "percent correct"
source = "https://openrouter.ai/qwen/qwen3-coder-30b-a3b-instruct/benchmarks"
date = "2026-06-02"
[[benchmarks]]
name = "Terminal-Bench Hard"
score = 15.2
metric = "success rate"
source = "https://openrouter.ai/qwen/qwen3-coder-30b-a3b-instruct/benchmarks"
date = "2026-06-02"
@@ -0,0 +1,29 @@
name = "Qwen3-Coder 480B-A35B Instruct"
family = "qwen"
release_date = "2025-04"
last_updated = "2025-04"
attachment = false
reasoning = false
temperature = true
tool_call = true
knowledge = "2025-04"
open_weights = true
[limit]
context = 262_144
output = 65_536
[modalities]
input = ["text"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct"
[[benchmarks]]
name = "SWE-Bench Pro"
score = 38.7
metric = "resolve rate"
dataset = "public"
source = "https://labs.scale.com/leaderboard/swe_bench_pro_public"
+18
View File
@@ -0,0 +1,18 @@
name = "Qwen3 Coder Flash"
family = "qwen"
release_date = "2025-07-28"
last_updated = "2025-07-28"
attachment = false
reasoning = false
temperature = true
tool_call = true
knowledge = "2025-04"
open_weights = false
[limit]
context = 1_000_000
output = 65_536
[modalities]
input = ["text"]
output = ["text"]
+18
View File
@@ -0,0 +1,18 @@
name = "Qwen3 Coder Plus"
family = "qwen"
release_date = "2025-07-23"
last_updated = "2025-07-23"
attachment = false
reasoning = false
temperature = true
tool_call = true
knowledge = "2025-04"
open_weights = false
[limit]
context = 1_048_576
output = 65_536
[modalities]
input = ["text"]
output = ["text"]
+39
View File
@@ -0,0 +1,39 @@
name = "Qwen3 Max"
family = "qwen"
release_date = "2025-09-23"
last_updated = "2025-09-23"
attachment = false
reasoning = false
temperature = true
tool_call = true
knowledge = "2025-04"
open_weights = false
[limit]
context = 262_144
output = 65_536
[modalities]
input = ["text"]
output = ["text"]
[[benchmarks]]
name = "Artificial Analysis Coding Index"
score = 26.4
metric = "index"
source = "https://openrouter.ai/qwen/qwen3-max/benchmarks"
date = "2026-05-30"
[[benchmarks]]
name = "SciCode"
score = 38.3
metric = "percent correct"
source = "https://openrouter.ai/qwen/qwen3-max/benchmarks"
date = "2026-05-30"
[[benchmarks]]
name = "Terminal-Bench Hard"
score = 20.5
metric = "success rate"
source = "https://openrouter.ai/qwen/qwen3-max/benchmarks"
date = "2026-05-30"
@@ -0,0 +1,22 @@
name = "Qwen3-Next 80B-A3B Instruct"
family = "qwen"
release_date = "2025-09"
last_updated = "2025-09"
attachment = false
reasoning = false
temperature = true
tool_call = true
knowledge = "2025-04"
open_weights = true
[limit]
context = 131_072
output = 32_768
[modalities]
input = ["text"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct"
@@ -0,0 +1,22 @@
name = "Qwen3-Next 80B-A3B (Thinking)"
family = "qwen"
release_date = "2025-09"
last_updated = "2025-09"
attachment = false
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-04"
open_weights = true
[limit]
context = 131_072
output = 32_768
[modalities]
input = ["text"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking"
+18
View File
@@ -0,0 +1,18 @@
name = "Qwen3-VL Plus"
family = "qwen"
release_date = "2025-09-23"
last_updated = "2025-09-23"
attachment = false
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-04"
open_weights = false
[limit]
context = 262_144
output = 32_768
[modalities]
input = ["text", "image"]
output = ["text"]
+28
View File
@@ -0,0 +1,28 @@
name = "Qwen3.5 122B-A10B"
family = "qwen"
release_date = "2026-02-23"
last_updated = "2026-02-23"
attachment = true
reasoning = true
temperature = true
tool_call = true
structured_output = true
open_weights = true
[limit]
context = 262_144
output = 65_536
[modalities]
input = ["text", "image", "video", "audio"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/Qwen/Qwen3.5-122B-A10B"
[[benchmarks]]
name = "SWE-Bench Verified"
score = 72
metric = "resolved"
source = "https://huggingface.co/Qwen/Qwen3.5-122B-A10B"
+28
View File
@@ -0,0 +1,28 @@
name = "Qwen3.5 27B"
family = "qwen"
release_date = "2026-02-23"
last_updated = "2026-02-23"
attachment = true
reasoning = true
temperature = true
tool_call = true
structured_output = true
open_weights = true
[limit]
context = 262_144
output = 65_536
[modalities]
input = ["text", "image", "video", "audio"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/Qwen/Qwen3.5-27B"
[[benchmarks]]
name = "SWE-Bench Verified"
score = 72.4
metric = "resolved"
source = "https://huggingface.co/Qwen/Qwen3.5-27B"
+22
View File
@@ -0,0 +1,22 @@
name = "Qwen3.5 35B-A3B"
family = "qwen"
release_date = "2026-02-23"
last_updated = "2026-02-23"
attachment = true
reasoning = true
temperature = true
tool_call = true
structured_output = true
open_weights = true
[limit]
context = 262_144
output = 65_536
[modalities]
input = ["text", "image", "video", "audio"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/Qwen/Qwen3.5-35B-A3B"
+28
View File
@@ -0,0 +1,28 @@
name = "Qwen3.5 397B-A17B"
family = "qwen"
release_date = "2026-02-15"
last_updated = "2026-02-15"
attachment = true
reasoning = true
temperature = true
tool_call = true
structured_output = true
open_weights = true
[limit]
context = 262_144
output = 65_536
[modalities]
input = ["text", "image", "video", "audio"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/Qwen/Qwen3.5-397B-A17B"
[[benchmarks]]
name = "SWE-Bench Verified"
score = 76.4
metric = "resolved"
source = "https://huggingface.co/Qwen/Qwen3.5-397B-A17B"
+18
View File
@@ -0,0 +1,18 @@
name = "Qwen3.5 Plus"
family = "qwen"
release_date = "2026-02-16"
last_updated = "2026-02-16"
attachment = false
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-04"
open_weights = false
[limit]
context = 1_000_000
output = 65_536
[modalities]
input = ["text", "image", "video"]
output = ["text"]
+28
View File
@@ -0,0 +1,28 @@
name = "Qwen3.6 27B"
family = "qwen"
release_date = "2026-04-22"
last_updated = "2026-04-22"
attachment = true
reasoning = true
temperature = true
tool_call = true
structured_output = true
open_weights = true
[limit]
context = 262_144
output = 65_536
[modalities]
input = ["text", "image", "video", "audio"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/Qwen/Qwen3.6-27B"
[[benchmarks]]
name = "SWE-Bench Verified"
score = 77.2
metric = "resolved"
source = "https://huggingface.co/Qwen/Qwen3.6-27B"
+28
View File
@@ -0,0 +1,28 @@
name = "Qwen3.6 35B-A3B"
family = "qwen"
release_date = "2026-04-17"
last_updated = "2026-04-17"
attachment = true
reasoning = true
temperature = true
tool_call = true
structured_output = true
open_weights = true
[limit]
context = 262_144
output = 65_536
[modalities]
input = ["text", "image", "video", "audio"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/Qwen/Qwen3.6-35B-A3B"
[[benchmarks]]
name = "SWE-Bench Verified"
score = 73.4
metric = "resolved"
source = "https://huggingface.co/Qwen/Qwen3.6-35B-A3B"
+18
View File
@@ -0,0 +1,18 @@
name = "Qwen3.6 Flash"
family = "qwen3.6"
release_date = "2026-04-27"
last_updated = "2026-04-27"
attachment = true
reasoning = true
temperature = true
tool_call = true
structured_output = true
open_weights = false
[limit]
context = 1_000_000
output = 65_536
[modalities]
input = ["text", "image", "video"]
output = ["text"]
+18
View File
@@ -0,0 +1,18 @@
name = "Qwen3.6 Max Preview"
family = "qwen"
release_date = "2026-04-20"
last_updated = "2026-04-20"
attachment = false
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-04"
open_weights = false
[limit]
context = 262_144
output = 65_536
[modalities]
input = ["text"]
output = ["text"]
+18
View File
@@ -0,0 +1,18 @@
name = "Qwen3.6 Plus"
family = "qwen"
release_date = "2026-04-02"
last_updated = "2026-04-02"
attachment = false
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-04"
open_weights = false
[limit]
context = 1_000_000
output = 65_536
[modalities]
input = ["text", "image", "video"]
output = ["text"]
+17
View File
@@ -0,0 +1,17 @@
name = "Qwen3.7 Max"
family = "qwen"
release_date = "2026-05-21"
last_updated = "2026-05-21"
attachment = false
reasoning = true
temperature = true
tool_call = true
open_weights = false
[limit]
context = 1_000_000
output = 65_536
[modalities]
input = ["text"]
output = ["text"]
+18
View File
@@ -0,0 +1,18 @@
name = "Qwen3.7 Plus"
family = "qwen"
release_date = "2026-06-02"
last_updated = "2026-06-02"
attachment = false
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-04"
open_weights = false
[limit]
context = 1_000_000
output = 64_000
[modalities]
input = ["text", "image"]
output = ["text"]
+18
View File
@@ -0,0 +1,18 @@
name = "QwQ Plus"
family = "qwen"
release_date = "2025-03-05"
last_updated = "2025-03-05"
attachment = false
reasoning = true
temperature = true
tool_call = true
knowledge = "2024-04"
open_weights = false
[limit]
context = 131_072
output = 8_192
[modalities]
input = ["text"]
output = ["text"]
@@ -0,0 +1,25 @@
name = "Claude Haiku 3.5"
family = "claude-haiku"
release_date = "2024-10-22"
last_updated = "2024-10-22"
attachment = true
reasoning = false
temperature = true
tool_call = true
knowledge = "2024-07-31"
open_weights = false
[limit]
context = 200_000
output = 8_192
[modalities]
input = ["text", "image", "pdf"]
output = ["text"]
[[benchmarks]]
name = "Aider Polyglot"
score = 28.0
metric = "percent correct"
source = "https://aider.chat/docs/leaderboards/"
date = "2024-12-21"
@@ -0,0 +1,25 @@
name = "Claude Sonnet 3.5 v2"
family = "claude-sonnet"
release_date = "2024-10-22"
last_updated = "2024-10-22"
attachment = true
reasoning = false
temperature = true
tool_call = true
knowledge = "2024-04-30"
open_weights = false
[limit]
context = 200_000
output = 8_192
[modalities]
input = ["text", "image", "pdf"]
output = ["text"]
[[benchmarks]]
name = "Aider Polyglot"
score = 51.6
metric = "percent correct"
source = "https://aider.chat/docs/leaderboards/"
date = "2025-01-17"
@@ -0,0 +1,25 @@
name = "Claude Sonnet 3.7"
family = "claude-sonnet"
release_date = "2025-02-19"
last_updated = "2025-02-19"
attachment = true
reasoning = true
temperature = true
tool_call = true
knowledge = "2024-10-31"
open_weights = false
[limit]
context = 200_000
output = 64_000
[modalities]
input = ["text", "image", "pdf"]
output = ["text"]
[[benchmarks]]
name = "Aider Polyglot"
score = 64.9
metric = "percent correct"
source = "https://aider.chat/docs/leaderboards/"
date = "2025-02-24"
+18
View File
@@ -0,0 +1,18 @@
name = "Claude Fable 5"
family = "claude-fable"
release_date = "2026-06-09"
last_updated = "2026-06-09"
attachment = true
reasoning = true
temperature = false
tool_call = true
open_weights = false
knowledge = "2026-01-31"
[limit]
context = 1_000_000
output = 128_000
[modalities]
input = ["text", "image", "pdf"]
output = ["text"]
@@ -0,0 +1,18 @@
name = "Claude Haiku 4.5"
family = "claude-haiku"
release_date = "2025-10-15"
last_updated = "2025-10-15"
attachment = true
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-02-28"
open_weights = false
[limit]
context = 200_000
output = 64_000
[modalities]
input = ["text", "image", "pdf"]
output = ["text"]
+25
View File
@@ -0,0 +1,25 @@
name = "Claude Haiku 4.5 (latest)"
family = "claude-haiku"
release_date = "2025-10-15"
last_updated = "2025-10-15"
attachment = true
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-02-28"
open_weights = false
[limit]
context = 200_000
output = 64_000
[modalities]
input = ["text", "image", "pdf"]
output = ["text"]
[[benchmarks]]
name = "SWE-Bench Pro"
score = 39.45
metric = "resolve rate"
dataset = "public"
source = "https://labs.scale.com/leaderboard/swe_bench_pro_public"
+25
View File
@@ -0,0 +1,25 @@
name = "Claude Opus 4 (latest)"
family = "claude-opus"
release_date = "2025-05-22"
last_updated = "2025-05-22"
attachment = true
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-03-31"
open_weights = false
[limit]
context = 200_000
output = 32_000
[modalities]
input = ["text", "image", "pdf"]
output = ["text"]
[[benchmarks]]
name = "Aider Polyglot"
score = 72.0
metric = "percent correct"
source = "https://aider.chat/docs/leaderboards/"
date = "2025-05-25"
@@ -0,0 +1,18 @@
name = "Claude Opus 4.1"
family = "claude-opus"
release_date = "2025-08-05"
last_updated = "2025-08-05"
attachment = true
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-03-31"
open_weights = false
[limit]
context = 200_000
output = 32_000
[modalities]
input = ["text", "image", "pdf"]
output = ["text"]
+18
View File
@@ -0,0 +1,18 @@
name = "Claude Opus 4.1 (latest)"
family = "claude-opus"
release_date = "2025-08-05"
last_updated = "2025-08-05"
attachment = true
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-03-31"
open_weights = false
[limit]
context = 200_000
output = 32_000
[modalities]
input = ["text", "image", "pdf"]
output = ["text"]
@@ -0,0 +1,25 @@
name = "Claude Opus 4"
family = "claude-opus"
release_date = "2025-05-22"
last_updated = "2025-05-22"
attachment = true
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-03-31"
open_weights = false
[limit]
context = 200_000
output = 32_000
[modalities]
input = ["text", "image", "pdf"]
output = ["text"]
[[benchmarks]]
name = "Aider Polyglot"
score = 72.0
metric = "percent correct"
source = "https://aider.chat/docs/leaderboards/"
date = "2025-05-25"
@@ -0,0 +1,25 @@
name = "Claude Opus 4.5"
family = "claude-opus"
release_date = "2025-11-01"
last_updated = "2025-11-01"
attachment = true
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-03-31"
open_weights = false
[limit]
context = 200_000
output = 64_000
[modalities]
input = ["text", "image", "pdf"]
output = ["text"]
[[benchmarks]]
name = "SWE-Bench Pro"
score = 45.89
metric = "resolve rate"
dataset = "public"
source = "https://labs.scale.com/leaderboard/swe_bench_pro_public"
+18
View File
@@ -0,0 +1,18 @@
name = "Claude Opus 4.5 (latest)"
family = "claude-opus"
release_date = "2025-11-24"
last_updated = "2025-11-24"
attachment = true
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-03-31"
open_weights = false
[limit]
context = 200_000
output = 64_000
[modalities]
input = ["text", "image", "pdf"]
output = ["text"]
+94
View File
@@ -0,0 +1,94 @@
name = "Claude Opus 4.6"
family = "claude-opus"
release_date = "2026-02-05"
last_updated = "2026-03-13"
attachment = true
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-05-31"
open_weights = false
[limit]
context = 1_000_000
output = 128_000
[modalities]
input = ["text", "image", "pdf"]
output = ["text"]
[[benchmarks]]
name = "SWE-Bench Pro"
score = 51.9
metric = "resolve rate"
dataset = "public"
source = "https://labs.scale.com/leaderboard/swe_bench_pro_public"
[[benchmarks]]
name = "SWE-Atlas Codebase QnA"
score = 33.3
metric = "score"
harness = "Claude Code"
source = "https://labs.scale.com/leaderboard/sweatlas-qna"
[[benchmarks]]
name = "SWE-Atlas Codebase QnA"
score = 30
metric = "score"
harness = "Mini-SWE-Agent"
source = "https://labs.scale.com/leaderboard/sweatlas-qna"
[[benchmarks]]
name = "SWE-Atlas Refactoring"
score = 35.58
metric = "score"
harness = "Claude Code"
source = "https://labs.scale.com/leaderboard/sweatlas-refactoring"
[[benchmarks]]
name = "SWE-Atlas Test Writing"
score = 36.67
metric = "score"
harness = "Claude Code"
source = "https://labs.scale.com/leaderboard/sweatlas-tw"
[[benchmarks]]
name = "SWE-Atlas Test Writing"
score = 36.08
metric = "score"
harness = "Mini-SWE-Agent"
source = "https://labs.scale.com/leaderboard/sweatlas-tw"
[[benchmarks]]
name = "Artificial Analysis Coding Agent Index"
score = 51.3
metric = "average pass@1"
harness = "Claude Code"
variant = "medium"
source = "https://artificialanalysis.ai/agents/coding-agents"
[[benchmarks]]
name = "SWE-Atlas Codebase QnA"
score = 71.9
metric = "pass@1"
harness = "Claude Code"
variant = "medium"
source = "https://artificialanalysis.ai/agents/coding-agents"
[[benchmarks]]
name = "SWE-Bench Pro"
score = 11.8
metric = "pass@1"
harness = "Claude Code"
variant = "medium"
dataset = "hard-aa"
source = "https://artificialanalysis.ai/agents/coding-agents"
[[benchmarks]]
name = "Terminal-Bench"
score = 70.2
metric = "pass@1"
harness = "Claude Code"
variant = "medium"
version = "2.1"
source = "https://artificialanalysis.ai/agents/coding-agents"
+143
View File
@@ -0,0 +1,143 @@
name = "Claude Opus 4.7"
family = "claude-opus"
release_date = "2026-04-16"
last_updated = "2026-04-16"
attachment = true
reasoning = true
temperature = false
tool_call = true
knowledge = "2026-01-31"
open_weights = false
[limit]
context = 1_000_000
output = 128_000
[modalities]
input = ["text", "image", "pdf"]
output = ["text"]
[[benchmarks]]
name = "SWE-Bench Pro"
score = 64.3
metric = "resolve rate"
source = "https://www.anthropic.com/news/claude-opus-4-8"
date = "2026-05-28"
[[benchmarks]]
name = "Terminal-Bench"
score = 66.1
metric = "success rate"
harness = "Terminus-2"
version = "2.1"
source = "https://www.anthropic.com/news/claude-opus-4-8"
date = "2026-05-28"
[[benchmarks]]
name = "SWE-Atlas Refactoring"
score = 48.57
metric = "score"
harness = "Claude Code"
source = "https://labs.scale.com/leaderboard/sweatlas-refactoring"
[[benchmarks]]
name = "Artificial Analysis Coding Agent Index"
score = 66.6
metric = "average pass@1"
harness = "Claude Code"
variant = "max"
source = "https://artificialanalysis.ai/agents/coding-agents"
[[benchmarks]]
name = "SWE-Atlas Codebase QnA"
score = 81
metric = "pass@1"
harness = "Claude Code"
variant = "max"
source = "https://artificialanalysis.ai/agents/coding-agents"
[[benchmarks]]
name = "SWE-Bench Pro"
score = 44.9
metric = "pass@1"
harness = "Claude Code"
variant = "max"
dataset = "hard-aa"
source = "https://artificialanalysis.ai/agents/coding-agents"
[[benchmarks]]
name = "Terminal-Bench"
score = 73.8
metric = "pass@1"
harness = "Claude Code"
variant = "max"
version = "2.1"
source = "https://artificialanalysis.ai/agents/coding-agents"
[[benchmarks]]
name = "Artificial Analysis Coding Agent Index"
score = 61.2
metric = "average pass@1"
harness = "Cursor CLI"
variant = "medium"
source = "https://artificialanalysis.ai/agents/coding-agents"
[[benchmarks]]
name = "SWE-Atlas Codebase QnA"
score = 78.4
metric = "pass@1"
harness = "Cursor CLI"
variant = "medium"
source = "https://artificialanalysis.ai/agents/coding-agents"
[[benchmarks]]
name = "SWE-Bench Pro"
score = 34.4
metric = "pass@1"
harness = "Cursor CLI"
variant = "medium"
dataset = "hard-aa"
source = "https://artificialanalysis.ai/agents/coding-agents"
[[benchmarks]]
name = "Terminal-Bench"
score = 70.6
metric = "pass@1"
harness = "Cursor CLI"
variant = "medium"
version = "2.1"
source = "https://artificialanalysis.ai/agents/coding-agents"
[[benchmarks]]
name = "Artificial Analysis Coding Agent Index"
score = 59.9
metric = "average pass@1"
harness = "Claude Code"
variant = "medium"
source = "https://artificialanalysis.ai/agents/coding-agents"
[[benchmarks]]
name = "SWE-Atlas Codebase QnA"
score = 71.7
metric = "pass@1"
harness = "Claude Code"
variant = "medium"
source = "https://artificialanalysis.ai/agents/coding-agents"
[[benchmarks]]
name = "SWE-Bench Pro"
score = 36.4
metric = "pass@1"
harness = "Claude Code"
variant = "medium"
dataset = "hard-aa"
source = "https://artificialanalysis.ai/agents/coding-agents"
[[benchmarks]]
name = "Terminal-Bench"
score = 71.4
metric = "pass@1"
harness = "Claude Code"
variant = "medium"
version = "2.1"
source = "https://artificialanalysis.ai/agents/coding-agents"
+33
View File
@@ -0,0 +1,33 @@
name = "Claude Opus 4.8"
family = "claude-opus"
release_date = "2026-05-28"
last_updated = "2026-05-28"
attachment = true
reasoning = true
temperature = false
tool_call = true
open_weights = false
[limit]
context = 1_000_000
output = 128_000
[modalities]
input = ["text", "image", "pdf"]
output = ["text"]
[[benchmarks]]
name = "SWE-Bench Pro"
score = 69.2
metric = "resolve rate"
source = "https://www.anthropic.com/news/claude-opus-4-8"
date = "2026-05-28"
[[benchmarks]]
name = "Terminal-Bench"
score = 74.6
metric = "success rate"
harness = "Terminus-2"
version = "2.1"
source = "https://www.anthropic.com/news/claude-opus-4-8"
date = "2026-05-28"
+32
View File
@@ -0,0 +1,32 @@
name = "Claude Sonnet 4 (latest)"
family = "claude-sonnet"
release_date = "2025-05-22"
last_updated = "2025-05-22"
attachment = true
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-03-31"
open_weights = false
[limit]
context = 200_000
output = 64_000
[modalities]
input = ["text", "image", "pdf"]
output = ["text"]
[[benchmarks]]
name = "Aider Polyglot"
score = 61.3
metric = "percent correct"
source = "https://aider.chat/docs/leaderboards/"
date = "2025-05-24"
[[benchmarks]]
name = "SWE-Bench Pro"
score = 42.7
metric = "resolve rate"
dataset = "public"
source = "https://labs.scale.com/leaderboard/swe_bench_pro_public"
@@ -0,0 +1,25 @@
name = "Claude Sonnet 4"
family = "claude-sonnet"
release_date = "2025-05-22"
last_updated = "2025-05-22"
attachment = true
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-03-31"
open_weights = false
[limit]
context = 200_000
output = 64_000
[modalities]
input = ["text", "image", "pdf"]
output = ["text"]
[[benchmarks]]
name = "Aider Polyglot"
score = 61.3
metric = "percent correct"
source = "https://aider.chat/docs/leaderboards/"
date = "2025-05-24"
@@ -0,0 +1,18 @@
name = "Claude Sonnet 4.5"
family = "claude-sonnet"
release_date = "2025-09-29"
last_updated = "2025-09-29"
attachment = true
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-07-31"
open_weights = false
[limit]
context = 200_000
output = 64_000
[modalities]
input = ["text", "image", "pdf"]
output = ["text"]
+25
View File
@@ -0,0 +1,25 @@
name = "Claude Sonnet 4.5 (latest)"
family = "claude-sonnet"
release_date = "2025-09-29"
last_updated = "2025-09-29"
attachment = true
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-07-31"
open_weights = false
[limit]
context = 200_000
output = 64_000
[modalities]
input = ["text", "image", "pdf"]
output = ["text"]
[[benchmarks]]
name = "SWE-Bench Pro"
score = 43.6
metric = "resolve rate"
dataset = "public"
source = "https://labs.scale.com/leaderboard/swe_bench_pro_public"
+73
View File
@@ -0,0 +1,73 @@
name = "Claude Sonnet 4.6"
family = "claude-sonnet"
release_date = "2026-02-17"
last_updated = "2026-03-13"
attachment = true
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-08-31"
open_weights = false
[limit]
context = 1_000_000
output = 64_000
[modalities]
input = ["text", "image", "pdf"]
output = ["text"]
[[benchmarks]]
name = "SWE-Atlas Codebase QnA"
score = 31.2
metric = "score"
harness = "Claude Code"
source = "https://labs.scale.com/leaderboard/sweatlas-qna"
[[benchmarks]]
name = "SWE-Atlas Refactoring"
score = 32.21
metric = "score"
harness = "Claude Code"
source = "https://labs.scale.com/leaderboard/sweatlas-refactoring"
[[benchmarks]]
name = "SWE-Atlas Test Writing"
score = 31.76
metric = "score"
harness = "Claude Code"
source = "https://labs.scale.com/leaderboard/sweatlas-tw"
[[benchmarks]]
name = "Artificial Analysis Coding Agent Index"
score = 49.4
metric = "average pass@1"
harness = "Claude Code"
variant = "medium"
source = "https://artificialanalysis.ai/agents/coding-agents"
[[benchmarks]]
name = "SWE-Atlas Codebase QnA"
score = 70.3
metric = "pass@1"
harness = "Claude Code"
variant = "medium"
source = "https://artificialanalysis.ai/agents/coding-agents"
[[benchmarks]]
name = "SWE-Bench Pro"
score = 14.9
metric = "pass@1"
harness = "Claude Code"
variant = "medium"
dataset = "hard-aa"
source = "https://artificialanalysis.ai/agents/coding-agents"
[[benchmarks]]
name = "Terminal-Bench"
score = 63.1
metric = "pass@1"
harness = "Claude Code"
variant = "medium"
version = "2.1"
source = "https://artificialanalysis.ai/agents/coding-agents"
+29
View File
@@ -0,0 +1,29 @@
name = "Command A"
family = "command-a"
release_date = "2025-03-13"
last_updated = "2025-03-13"
attachment = false
reasoning = false
temperature = true
tool_call = true
knowledge = "2024-06-01"
open_weights = true
[limit]
context = 256_000
output = 8_000
[modalities]
input = ["text"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/CohereLabs/c4ai-command-a-03-2025"
[[benchmarks]]
name = "Aider Polyglot"
score = 12.0
metric = "percent correct"
source = "https://aider.chat/docs/leaderboards/"
date = "2025-03-14"
+19
View File
@@ -0,0 +1,19 @@
name = "Command A Plus"
family = "command-a"
release_date = "2026-05-20"
last_updated = "2026-06-09"
attachment = true
reasoning = true
temperature = true
knowledge = "2025-04-01"
tool_call = true
open_weights = true
structured_output = true
[limit]
context = 128_000
output = 64_000
[modalities]
input = ["text", "image"]
output = ["text"]
+22
View File
@@ -0,0 +1,22 @@
name = "Command R"
family = "command-r"
release_date = "2024-08-30"
last_updated = "2024-08-30"
attachment = false
reasoning = false
temperature = true
tool_call = true
knowledge = "2024-06-01"
open_weights = true
[limit]
context = 128_000
output = 4_000
[modalities]
input = ["text"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/CohereLabs/c4ai-command-r-08-2024"
+22
View File
@@ -0,0 +1,22 @@
name = "Command R+"
family = "command-r"
release_date = "2024-08-30"
last_updated = "2024-08-30"
attachment = false
reasoning = false
temperature = true
tool_call = true
knowledge = "2024-06-01"
open_weights = true
[limit]
context = 128_000
output = 4_000
[modalities]
input = ["text"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/CohereLabs/c4ai-command-r-plus-08-2024"
+22
View File
@@ -0,0 +1,22 @@
name = "Command R7B"
family = "command-r"
release_date = "2024-02-27"
last_updated = "2024-02-27"
attachment = false
reasoning = false
temperature = true
tool_call = true
knowledge = "2024-06-01"
open_weights = true
[limit]
context = 128_000
output = 4_000
[modalities]
input = ["text"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/CohereLabs/c4ai-command-r7b-12-2024"
+19
View File
@@ -0,0 +1,19 @@
name = "North Mini Code"
family = "north"
release_date = "2026-06-09"
last_updated = "2026-06-09"
attachment = false
reasoning = true
temperature = true
structured_output = true
knowledge = "2025-09-23"
tool_call = true
open_weights = true
[limit]
context = 256_000
output = 64_000
[modalities]
input = ["text"]
output = ["text"]
+29
View File
@@ -0,0 +1,29 @@
name = "DeepSeek Chat"
family = "deepseek"
release_date = "2025-12-01"
last_updated = "2026-02-28"
attachment = true
reasoning = false
temperature = true
tool_call = true
knowledge = "2025-09"
open_weights = true
[limit]
context = 1_000_000
output = 384_000
[modalities]
input = ["text"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/deepseek-ai/DeepSeek-V3.2"
[[benchmarks]]
name = "Aider Polyglot"
score = 70.2
metric = "percent correct"
source = "https://aider.chat/docs/leaderboards/"
date = "2025-10-03"
+50
View File
@@ -0,0 +1,50 @@
name = "DeepSeek-R1"
family = "deepseek-thinking"
release_date = "2025-01-20"
last_updated = "2025-05-29"
attachment = false
reasoning = true
temperature = true
tool_call = true
knowledge = "2024-07"
open_weights = true
[limit]
context = 128_000
output = 32_768
[modalities]
input = ["text"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/deepseek-ai/DeepSeek-R1"
[[benchmarks]]
name = "Aider Polyglot"
score = 56.9
metric = "percent correct"
source = "https://aider.chat/docs/leaderboards/"
date = "2025-01-20"
[[benchmarks]]
name = "Artificial Analysis Coding Index"
score = 15.9
metric = "index"
source = "https://openrouter.ai/deepseek/deepseek-r1/benchmarks"
date = "2026-03-11"
[[benchmarks]]
name = "SciCode"
score = 35.7
metric = "percent correct"
source = "https://openrouter.ai/deepseek/deepseek-r1/benchmarks"
date = "2026-03-11"
[[benchmarks]]
name = "Terminal-Bench Hard"
score = 6.1
metric = "success rate"
source = "https://openrouter.ai/deepseek/deepseek-r1/benchmarks"
date = "2026-03-11"
+29
View File
@@ -0,0 +1,29 @@
name = "DeepSeek Reasoner"
family = "deepseek-thinking"
release_date = "2025-12-01"
last_updated = "2026-02-28"
attachment = true
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-09"
open_weights = true
[limit]
context = 1_000_000
output = 384_000
[modalities]
input = ["text"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/deepseek-ai/DeepSeek-V3.2"
[[benchmarks]]
name = "Aider Polyglot"
score = 74.2
metric = "percent correct"
source = "https://aider.chat/docs/leaderboards/"
date = "2025-10-03"
+29
View File
@@ -0,0 +1,29 @@
name = "DeepSeek V4 Flash"
family = "deepseek-flash"
release_date = "2026-04-24"
last_updated = "2026-04-24"
attachment = false
reasoning = true
temperature = true
tool_call = true
structured_output = true
knowledge = "2025-05"
open_weights = true
[limit]
context = 1_000_000
output = 384_000
[modalities]
input = ["text"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash"
[[benchmarks]]
name = "SWE-Bench Verified"
score = 79
metric = "resolved"
source = "https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash"
+63
View File
@@ -0,0 +1,63 @@
name = "DeepSeek V4 Pro"
family = "deepseek-thinking"
release_date = "2026-04-24"
last_updated = "2026-04-24"
attachment = false
reasoning = true
temperature = true
tool_call = true
structured_output = true
knowledge = "2025-05"
open_weights = true
[limit]
context = 1_000_000
output = 384_000
[modalities]
input = ["text"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro"
[[benchmarks]]
name = "SWE-Bench Verified"
score = 80.6
metric = "resolved"
source = "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro"
[[benchmarks]]
name = "Artificial Analysis Coding Agent Index"
score = 50.1
metric = "average pass@1"
harness = "Claude Code"
variant = "high"
source = "https://artificialanalysis.ai/agents/coding-agents"
[[benchmarks]]
name = "SWE-Atlas Codebase QnA"
score = 67.8
metric = "pass@1"
harness = "Claude Code"
variant = "high"
source = "https://artificialanalysis.ai/agents/coding-agents"
[[benchmarks]]
name = "SWE-Bench Pro"
score = 18
metric = "pass@1"
harness = "Claude Code"
variant = "high"
dataset = "hard-aa"
source = "https://artificialanalysis.ai/agents/coding-agents"
[[benchmarks]]
name = "Terminal-Bench"
score = 64.7
metric = "pass@1"
harness = "Claude Code"
variant = "high"
version = "2.1"
source = "https://artificialanalysis.ai/agents/coding-agents"
+19
View File
@@ -0,0 +1,19 @@
name = "Gemini 2.0 Flash-Lite"
family = "gemini-flash-lite"
release_date = "2024-12-11"
last_updated = "2024-12-11"
attachment = true
reasoning = false
temperature = true
tool_call = true
structured_output = true
knowledge = "2024-06"
open_weights = false
[limit]
context = 1_048_576
output = 8_192
[modalities]
input = ["text", "image", "audio", "video", "pdf"]
output = ["text"]
+19
View File
@@ -0,0 +1,19 @@
name = "Gemini 2.0 Flash"
family = "gemini-flash"
release_date = "2024-12-11"
last_updated = "2024-12-11"
attachment = true
reasoning = false
temperature = true
tool_call = true
structured_output = true
knowledge = "2024-06"
open_weights = false
[limit]
context = 1_048_576
output = 8_192
[modalities]
input = ["text", "image", "audio", "video", "pdf"]
output = ["text"]
+18
View File
@@ -0,0 +1,18 @@
name = "Nano Banana"
family = "gemini-flash"
release_date = "2025-08-26"
last_updated = "2025-08-26"
attachment = true
reasoning = true
temperature = true
tool_call = false
knowledge = "2025-06"
open_weights = false
[limit]
context = 32_768
output = 32_768
[modalities]
input = ["text", "image"]
output = ["text", "image"]
+40
View File
@@ -0,0 +1,40 @@
name = "Gemini 2.5 Flash-Lite"
family = "gemini-flash-lite"
release_date = "2025-06-17"
last_updated = "2025-06-17"
attachment = true
reasoning = true
temperature = true
tool_call = true
structured_output = true
knowledge = "2025-01"
open_weights = false
[limit]
context = 1_048_576
output = 65_536
[modalities]
input = ["text", "image", "audio", "video", "pdf"]
output = ["text"]
[[benchmarks]]
name = "Artificial Analysis Coding Index"
score = 9.5
metric = "index"
source = "https://openrouter.ai/google/gemini-2.5-flash-lite/benchmarks"
date = "2026-03-11"
[[benchmarks]]
name = "SciCode"
score = 19.3
metric = "percent correct"
source = "https://openrouter.ai/google/gemini-2.5-flash-lite/benchmarks"
date = "2026-03-11"
[[benchmarks]]
name = "Terminal-Bench Hard"
score = 4.5
metric = "success rate"
source = "https://openrouter.ai/google/gemini-2.5-flash-lite/benchmarks"
date = "2026-03-11"
+18
View File
@@ -0,0 +1,18 @@
name = "Gemini 2.5 Flash TTS"
family = "gemini-flash"
release_date = "2025-09-30"
last_updated = "2025-12-10"
attachment = false
reasoning = false
temperature = true
tool_call = false
knowledge = "2025-01"
open_weights = false
[limit]
context = 32_768
output = 16_384
[modalities]
input = ["text"]
output = ["audio"]
+47
View File
@@ -0,0 +1,47 @@
name = "Gemini 2.5 Flash"
family = "gemini-flash"
release_date = "2025-06-17"
last_updated = "2025-06-17"
attachment = true
reasoning = true
temperature = true
tool_call = true
structured_output = true
knowledge = "2025-01"
open_weights = false
[limit]
context = 1_048_576
output = 65_536
[modalities]
input = ["text", "image", "audio", "video", "pdf"]
output = ["text"]
[[benchmarks]]
name = "Aider Polyglot"
score = 55.1
metric = "percent correct"
source = "https://aider.chat/docs/leaderboards/"
date = "2025-05-25"
[[benchmarks]]
name = "Artificial Analysis Coding Index"
score = 22.2
metric = "index"
source = "https://openrouter.ai/google/gemini-2.5-flash/benchmarks"
date = "2026-06-02"
[[benchmarks]]
name = "SciCode"
score = 39.4
metric = "percent correct"
source = "https://openrouter.ai/google/gemini-2.5-flash/benchmarks"
date = "2026-06-02"
[[benchmarks]]
name = "Terminal-Bench Hard"
score = 13.6
metric = "success rate"
source = "https://openrouter.ai/google/gemini-2.5-flash/benchmarks"
date = "2026-06-02"
+18
View File
@@ -0,0 +1,18 @@
name = "Gemini 2.5 Pro TTS"
family = "gemini-pro"
release_date = "2025-09-30"
last_updated = "2025-12-10"
attachment = false
reasoning = false
temperature = false
tool_call = false
knowledge = "2025-01"
open_weights = false
[limit]
context = 32_768
output = 16_384
[modalities]
input = ["text"]
output = ["audio"]
+47
View File
@@ -0,0 +1,47 @@
name = "Gemini 2.5 Pro"
family = "gemini-pro"
release_date = "2025-06-17"
last_updated = "2025-06-17"
attachment = true
reasoning = true
temperature = true
tool_call = true
structured_output = true
knowledge = "2025-01"
open_weights = false
[limit]
context = 1_048_576
output = 65_536
[modalities]
input = ["text", "image", "audio", "video", "pdf"]
output = ["text"]
[[benchmarks]]
name = "Aider Polyglot"
score = 83.1
metric = "percent correct"
source = "https://aider.chat/docs/leaderboards/"
date = "2025-06-06"
[[benchmarks]]
name = "Artificial Analysis Coding Index"
score = 32
metric = "index"
source = "https://openrouter.ai/google/gemini-2.5-pro/benchmarks"
date = "2026-06-02"
[[benchmarks]]
name = "SciCode"
score = 42.8
metric = "percent correct"
source = "https://openrouter.ai/google/gemini-2.5-pro/benchmarks"
date = "2026-06-02"
[[benchmarks]]
name = "Terminal-Bench Hard"
score = 26.5
metric = "success rate"
source = "https://openrouter.ai/google/gemini-2.5-pro/benchmarks"
date = "2026-06-02"
+47
View File
@@ -0,0 +1,47 @@
name = "Gemini 3 Flash Preview"
family = "gemini-flash"
release_date = "2025-12-17"
last_updated = "2025-12-17"
attachment = true
reasoning = true
temperature = true
tool_call = true
structured_output = true
knowledge = "2025-01"
open_weights = false
[limit]
context = 1_048_576
output = 65_536
[modalities]
input = ["text", "image", "video", "audio", "pdf"]
output = ["text"]
[[benchmarks]]
name = "SWE-Bench Pro"
score = 34.63
metric = "resolve rate"
dataset = "public"
source = "https://labs.scale.com/leaderboard/swe_bench_pro_public"
[[benchmarks]]
name = "SWE-Atlas Codebase QnA"
score = 8.2
metric = "score"
harness = "Mini-SWE-Agent"
source = "https://labs.scale.com/leaderboard/sweatlas-qna"
[[benchmarks]]
name = "SWE-Atlas Refactoring"
score = 10
metric = "score"
harness = "Mini-SWE-Agent"
source = "https://labs.scale.com/leaderboard/sweatlas-refactoring"
[[benchmarks]]
name = "SWE-Atlas Test Writing"
score = 30.3
metric = "score"
harness = "Mini-SWE-Agent"
source = "https://labs.scale.com/leaderboard/sweatlas-tw"
@@ -0,0 +1,18 @@
name = "Nano Banana Pro"
family = "gemini-pro"
release_date = "2025-11-20"
last_updated = "2025-11-20"
attachment = true
reasoning = true
temperature = true
tool_call = false
knowledge = "2025-01"
open_weights = false
[limit]
context = 65_536
output = 32_768
[modalities]
input = ["text", "image"]
output = ["text", "image"]
+26
View File
@@ -0,0 +1,26 @@
name = "Gemini 3 Pro Preview"
family = "gemini-pro"
release_date = "2025-11-18"
last_updated = "2025-11-18"
attachment = true
reasoning = true
temperature = true
tool_call = true
structured_output = true
knowledge = "2025-01"
open_weights = false
[limit]
context = 1_048_576
output = 65_536
[modalities]
input = ["text", "image", "video", "audio", "pdf"]
output = ["text"]
[[benchmarks]]
name = "SWE-Bench Pro"
score = 43.3
metric = "resolve rate"
dataset = "public"
source = "https://labs.scale.com/leaderboard/swe_bench_pro_public"
@@ -0,0 +1,18 @@
name = "Nano Banana 2"
family = "gemini-flash"
release_date = "2026-02-26"
last_updated = "2026-02-26"
attachment = true
reasoning = true
temperature = true
tool_call = false
knowledge = "2025-01"
open_weights = false
[limit]
context = 65_536
output = 65_536
[modalities]
input = ["text", "image", "pdf"]
output = ["text", "image"]
@@ -0,0 +1,19 @@
name = "Gemini 3.1 Flash Lite Preview"
family = "gemini-flash-lite"
release_date = "2026-03-03"
last_updated = "2026-03-03"
attachment = true
reasoning = true
temperature = true
tool_call = true
structured_output = true
knowledge = "2025-01"
open_weights = false
[limit]
context = 1_048_576
output = 65_536
[modalities]
input = ["text", "image", "video", "audio", "pdf"]
output = ["text"]

Some files were not shown because too many files have changed in this diff Show More