opencode-agent[bot]
40bcce25de
Made api optional for @ai-sdk/openai
...
Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com >
2026-01-06 04:41:52 +00:00
Aiden Cline
840fe7fef6
Merge pull request #600 from xiaojiezj/zenmux_dev
...
feat: Update the model configuration file based on ZenMux’s model list
2026-01-04 23:27:39 -08:00
xiaojie.zj
8f070f49b3
fix: fix validate
2026-01-05 15:23:24 +08:00
Aiden Cline
fa61b458a0
Merge pull request #599 from billycao/billy/remove-Kimi-K2-Instruct
...
fix: Remove Kimi-K2-Instruct for provider Synthetic
2026-01-04 22:49:06 -08:00
xiaojie.zj
6ac98b8a8f
feat: Update the model configuration file based on ZenMux’s model list
2026-01-05 14:18:23 +08:00
Billy Cao
b643aa45b0
Remove Kimi-K2-Instruct for provider Synthetic
2026-01-04 20:06:15 -08:00
Aiden Cline
65b43b44c1
Merge pull request #598 from ishaksebsib/feat/groq-provider
...
Feat: update Groq provider with latest pricing, limits, and capabilities
2026-01-04 11:16:54 -08:00
ishaksebsib
7a7fe98987
groq: update structured output capability for models that support it
2026-01-04 20:48:46 +03:00
ishaksebsib
f94e0257c2
groq: update input and output cost/limit
2026-01-04 20:42:33 +03:00
ishaksebsib
0df9997e71
groq: update status for deprecated models
2026-01-04 20:41:21 +03:00
Aiden Cline
d1710b2b08
Merge pull request #597 from xinrui-z/aihubmix-add-minimax-m2.1-and-glm-4.7
...
aihubmix: add glm-4.7 and minimax-m2.1
2026-01-03 23:15:14 -08:00
Xinrui
b568ddd33d
aihubmix: add glm-4.7 and minimax-m2.1
2026-01-04 14:50:47 +08:00
Aiden Cline
4b96508663
Merge pull request #595 from dpuyosa/UpdateModel
...
Venice: Fixed modalities for grok-code-fast-1 and minimax-m21
2026-01-02 09:56:24 -08:00
Aiden Cline
4b02644ff9
Merge pull request #486 from xinrui-z/update/aihubmix
...
aihubmix: add models
2026-01-02 09:55:55 -08:00
Xinrui
c35f968adc
aihubmix: add models
2026-01-02 21:48:49 +08:00
dpuyosa
75957fb866
Update model configurations for grok-code-fast-1 and minimax-m21:
...
- Set attachment to false for both models
- Update last_updated to 2026-01-02 for both models
- Remove image input modality from grok-code-fast-1
- Remove image input modality from minimax-m21
- Add interleaved reasoning_content field to minimax-m21
- Add family field to minimax-m21
2026-01-02 02:59:42 +01:00
Aiden Cline
07da33848a
Merge pull request #582 from mark182es/fix/update-chutes-models-20251229
...
feat: add new Chutes TEE providers and fix model configuration fields
2026-01-01 16:05:23 -08:00
Aiden Cline
5d2d213aa4
Merge pull request #592 from janspoerer/provider-abacus
...
Added Abacus as a provider
2026-01-01 11:57:35 -08:00
Jan Spoerer
46728af37c
Transformed the Abacus logo into a matching format, color, size to the other logos
2026-01-01 20:52:26 +01:00
Jan Spoerer
8ce390ce26
Added Abacus svg
2026-01-01 20:48:26 +01:00
Aiden Cline
53a61d9e31
Merge pull request #593 from fhennerkes/dev
...
Poe: update 1/1/26
2026-01-01 10:46:49 -08:00
fhennerkes
4be86ce87f
Merge poe-pricing-sync into dev (selective)
...
Added new models:
- Cerebras: gpt-oss-120b-cs, zai-glm-4.6-cs
- Google: gemini-3-flash
- Novita: glm-4.6v, glm-4.7, kat-coder-pro, minimax-m2.1
- OpenAI: gpt-image-1.5
Updated pricing and configuration:
- Google Gemini 2.5 Flash/Pro cache pricing corrections
- Google Nano Banana models pricing updates
- xAI Grok models: added image input support
2026-01-01 10:34:26 -08:00
github-actions
989e70553e
chore: sync Poe pricing
2026-01-01 18:01:20 +00:00
fhennerkes
1b78419770
chore: restore Poe pricing sync automation
2026-01-01 09:59:25 -08:00
Jan Spoerer
3a7a4e9654
Added Abacus as a provider
2025-12-31 15:14:36 +01:00
Aiden Cline
7ea8fba795
Merge pull request #589 from dpuyosa/UpdateModel
...
Venice: Added new models Grok Code Fast 1 and Minimax M2.1
2025-12-30 14:40:21 -08:00
dpuyosa
3a61532edb
Updated model configurations and added new models:
...
- gemini-3-flash-preview: updated last_updated and added cache_read cost
- grok-code-fast-1: added new model configuration
- kimi-k2-thinking: updated release_date, last_updated, and cache_read cost
- minimax-m21: added new model configuration
2025-12-30 22:06:38 +01:00
Aiden Cline
f4069f92d3
Merge pull request #588 from jerome-benoit/fix/sap-ai-core-claude-haiku-4.5
...
fix(sap-ai-core): rename anthropic--claude-haiku-4.5 to anthropic--cl…
2025-12-30 11:34:55 -08:00
Jérôme Benoit
b9588df9ed
fix(sap-ai-core): rename anthropic--claude-haiku-4.5 to anthropic--claude-4.5-haiku
...
Signed-off-by: Jérôme Benoit <jerome.benoit@piment-noir.org >
2025-12-30 20:03:13 +01:00
Aiden Cline
a9aaa0f9ae
Merge pull request #587 from cravenceiling/refactor/siliconflow-model-ids
...
refactor siliconflow model ids
2025-12-30 10:31:34 -08:00
Aiden Cline
f5428a81a8
fix: some model dates
2025-12-30 12:23:25 -06:00
cravenceiling
0a55c3d1cd
refactor siliconflow model ids
...
* Change the model file structure to use foldes for ids containing `/`
* Update the models and file structure in the `providers/siliconflow-cn` directory
2025-12-30 09:57:37 -05:00
Aiden Cline
59ce57823c
Merge pull request #586 from mounta11n/patch-1
...
Fix typo from 4B to 8B
2025-12-29 20:03:53 -08:00
Yazan Agha-Schrader
eb85004c3e
Fix typo from 4B to 8B
2025-12-30 04:31:27 +01:00
Aiden Cline
53afc6aefb
Merge pull request #584 from jerome-benoit/feat/sap-ai-core-claude-updates
...
feat(sap-ai-core): add Claude Haiku 4.5 and cache pricing for Claude …
2025-12-29 14:57:14 -08:00
Frank
54d0d65ed5
update zen models
2025-12-29 16:56:56 -05:00
Aiden Cline
eaa25b5268
Merge pull request #579 from wojons/dev
...
Modify cost parameters in MiniMax-M2.1.toml
2025-12-29 13:17:06 -08:00
Aiden Cline
001367833d
Merge pull request #583 from dpuyosa/UpdateModel
...
Venice: Update/fix 'release_date' for many models
2025-12-29 13:16:40 -08:00
Jérôme Benoit
a24b564ee7
feat(sap-ai-core): add Claude Haiku 4.5 and cache pricing for Claude models
2025-12-29 22:01:37 +01:00
dpuyosa
d5d1b36cb8
Update/fix 'release_date' for many models
2025-12-29 20:26:17 +01:00
Marco
b1d82a1946
fix: add missing fields to all chutes models
...
Add structured_output field
2025-12-29 18:14:15 +01:00
Marco
b19dceffdd
feat: add new TEE providers, update context sizes and pricing
...
New TEE providers:
- MiniMaxAI: M2.1-TEE
- NousResearch: Hermes-4-405B-FP8-TEE
- Qwen: Qwen2.5-VL-72B-Instruct-TEE, Qwen3-235B-A22B-Instruct-2507-TEE, Qwen3-Coder-480B-A35B-Instruct-FP8-TEE
- deepseek-ai: DeepSeek-R1-0528-TEE, DeepSeek-R1-TEE, DeepSeek-V3-0324-TEE, DeepSeek-V3.1-TEE, DeepSeek-V3.1-Terminus-TEE, DeepSeek-V3.2-TEE
- moonshotai: Kimi-K2-Thinking-TEE
- openai: GPT-OSS-120B-TEE
- zai-org: GLM-4.5-TEE, GLM-4.7-TEE
Updates:
- Fixed context window sizes for multiple models
- Updated pricing for all affected providers
- Added NVIDIA Nemotron 3 Nano 30B model
2025-12-29 17:48:04 +01:00
Frank
057361ad5e
update zen models
2025-12-29 10:23:30 -05:00
Aiden Cline
d2939fa5ad
rm perplexity deprecated model
2025-12-28 17:57:11 -06:00
Alexis Okuwa
8952013668
Add interleaved section with reasoning_content field
2025-12-28 15:09:31 -08:00
Alexis Okuwa
e033fc186d
Modify cost parameters in MiniMax-M2.1.toml
...
Updated cost parameters for input and output.
2025-12-27 18:47:30 -08:00
Aiden Cline
9250fbe2bc
Merge pull request #567 from b3nw/feat/add-nano-gpt-models
...
Feat: Add Nano-GPT provider models
2025-12-26 22:49:12 -08:00
Ben
e6ab0814e2
Feat: Add Nano-GPT provider models
2025-12-27 05:25:59 +00:00
Aiden Cline
4bd8337131
Merge pull request #574 from friendliai/feat/add-friendli-provider
...
fix: correct friendli model file structure for API IDs with slashes
2025-12-26 20:54:00 -08:00
Aiden Cline
cb2c762dec
Merge pull request #575 from otterDeveloper/fireworks-pull-2
...
add Firework's MiniMax-M2.1
2025-12-26 20:53:40 -08:00
Miguel Medina
8bf3ff5fca
feat: add minimax 2.1
...
https://app.fireworks.ai/models/fireworks/minimax-m2p1
2025-12-26 22:34:05 -06:00
Miguel Medina
dfb7e0087a
fix: update context and pricing
...
obtained from https://app.fireworks.ai/models/fireworks/minimax-m2
2025-12-26 22:27:20 -06:00
minpeter
7a55ce44e7
fix: restructure friendli model files to match API IDs with slashes
...
- Change model file structure to use directories for IDs containing '/'
- Update generate-friendli.ts to create directory structure instead of replacing '/' with '-'
- Fixes 404 errors caused by model ID mismatch (e.g., Qwen/Qwen3-30B-A3B vs Qwen-Qwen3-30B-A3B)
2025-12-26 04:19:24 +09:00
Aiden Cline
006d0208f0
Merge pull request #558 from friendliai/feat/add-friendli-provider
...
Add Friendli serverless endpoints provider
2025-12-24 22:23:33 -08:00
Frank
7ac941d483
update zen mdoels
2025-12-24 14:34:23 -05:00
Aiden Cline
31ec6424b2
Merge pull request #570 from dpuyosa/UpdateModel
...
Venice: Update zai-org-glm-4.7
2025-12-24 09:15:49 -08:00
dpuyosa
0279094eff
Update glm 4.7 data
2025-12-24 17:41:52 +01:00
Aiden Cline
889dabce96
Merge pull request #569 from b3nw/feat/update-nvidia-models
...
Feat/update nvidia models
2025-12-24 07:33:12 -08:00
Aiden Cline
b68935b403
Merge pull request #566 from otterDeveloper/fireworks-pull-1
...
Add recent fireworks models
2025-12-24 07:32:55 -08:00
Aiden Cline
1ba3c3cc4a
Merge pull request #568 from M16X/deepinfra-glm-4.7
...
Rename glm-4.7.toml to GLM-4.7.toml
2025-12-24 07:32:23 -08:00
b3nw
31feccceda
Merge branch 'sst:dev' into feat/update-nvidia-models
2025-12-24 08:11:26 -06:00
Ben
ea4063510f
feat(nvidia): model update
2025-12-24 14:10:40 +00:00
minpeter
e5c683d830
Update Friendli logo to use currentColor in SVG
2025-12-24 15:07:05 +09:00
Nazar
07bbf78e9c
Rename glm-4.7.toml to GLM-4.7.toml
2025-12-24 11:32:41 +05:30
Miguel Medina
bc6981debc
fix: increase output token limit
...
16_384 seems to be the ui limit
2025-12-23 23:01:31 -06:00
Miguel Medina
4eb339327e
fix: document interleaved thinking
2025-12-23 22:58:13 -06:00
Aiden Cline
ef30eb2bca
Merge pull request #565 from M16X/deepinfra-glm-4.7
...
Add GLM-4.7 for DeepInfra
2025-12-23 20:26:16 -08:00
Nazar
9aa2515fd5
deepinfra: add interleaved reasoning for glm-4.7
2025-12-24 09:45:44 +05:30
Aiden Cline
02420741cf
Merge pull request #563 from dpuyosa/UpdateModel
...
Venice: Add cost.cache_read to kimi-k2-thinking
2025-12-23 20:11:57 -08:00
Aiden Cline
df4fa098b2
Merge pull request #564 from superhighfives/cgleason/fix-cloudflare-workers-pricing
...
Adds missing pricing information for Workers in Cloudflare AI Gateway
2025-12-23 20:11:47 -08:00
Miguel Medina
e5069994ba
feat: document fireworks.ai models
2025-12-23 22:03:53 -06:00
Nazar
067df451a5
[deepinfra] glm-4.7: update knowledge cut off time
2025-12-24 08:31:27 +05:30
Nazar
3c9f132359
deepinfra: remove cache_write for glm-4.7
2025-12-24 08:29:00 +05:30
Nazar
6fd63482ae
deepinfra: add docs on output limit
2025-12-24 08:24:54 +05:30
Nazar
c2a81337f5
deepinfra: deprecate glm-4.5
2025-12-24 08:20:09 +05:30
Nazar
450053341e
deepinfra: add glm-4.7
2025-12-24 08:12:50 +05:30
Charlie Gleason
1c4e1ec6b6
Adds missing pricing information
2025-12-23 18:20:48 -08:00
dpuyosa
e4a102b68f
Add cost.cache_read to kimi-k2-thinking
2025-12-24 03:15:58 +01:00
Aiden Cline
336e4583ba
fix: filename
2025-12-23 18:54:03 -06:00
Frank
2abd51895b
update zen models
2025-12-23 19:18:53 -05:00
Aiden Cline
3a9d8af6a5
Merge pull request #562 from dsingal0/dev
...
add GLM 4.7 for baseten provider
2025-12-23 15:34:45 -08:00
Dhruv Singal
a66d418cfa
Rename glm-4.7.toml to GLM-4.7.toml
2025-12-23 14:48:38 -08:00
Dhruv Singal
cc6079297c
add glm 4.7
2025-12-23 14:48:06 -08:00
Aiden Cline
09d5d80a8a
Merge pull request #561 from KevinPoorDeveloper/dev
...
Add GLM 4.7 for Provider Venice.ai
2025-12-23 14:17:14 -08:00
Kevin
cb4a5843c5
Add GLM 4.7 for Provider Venice.ai
...
New model toml
2025-12-23 13:41:02 -08:00
Aiden Cline
d54bc052eb
Merge pull request #560 from superhighfives/cgleason/fix-workers-model-ids
...
Fix Workers AI models in Cloudflare AI Gateway
2025-12-23 12:17:22 -08:00
Aiden Cline
e174f5400f
fix: properly set interleaved setting for glm 4.7
2025-12-23 14:09:20 -06:00
Charlie Gleason
821f350e9a
Add model families
2025-12-23 10:58:08 -08:00
Aiden Cline
663b10c8b3
Merge pull request #557 from no1wudi/mini
...
feat: add MiniMax-M2.1 model configuration
2025-12-23 10:43:10 -08:00
Charlie Gleason
f6ff799d21
Update models
2025-12-23 10:22:16 -08:00
Charlie Gleason
a15c161d2d
Fix Workers AI model references and model names
2025-12-23 10:18:43 -08:00
minpeter
6a97400dd7
Update reasoning and open_weights for Friendli models
2025-12-23 19:46:11 +09:00
minpeter
506ab5646c
Add Friendli provider with 11 models
2025-12-23 19:17:00 +09:00
minpeter
0c4b20a7ad
Refactor API key argument parsing to remove redundant null checks
2025-12-23 19:15:14 +09:00
minpeter
e47641da01
Fix TypeScript type errors in generator scripts
...
- Fix possible undefined array access in generate-friendli.ts
- Fix undefined type assignments in generate-venice.ts
- Use safe array access with .at() and nullish coalescing operators
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com >
2025-12-23 19:06:40 +09:00
minpeter
6d6743331c
Add Friendli serverless endpoints provider
...
- Add provider configuration for Friendli serverless endpoints
- Implement auto-generation script (generate-friendli.ts)
- Add 11 models: Llama, Qwen, DeepSeek-R1, EXAONE, GLM
- Handle TOKEN-based pricing (4 models) and SECOND-based pricing (7 models)
- Auto-infer model families and open_weights status
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com >
2025-12-23 19:02:25 +09:00
Huang Qi
88471de736
feat: add MiniMax-M2.1 model configuration
...
Add new MiniMax-M2.1 reasoning model to both global and Chinese providers
* Supports reasoning capabilities, temperature settings, and tool calls
* Includes open weights support with context limit of 196,608 tokens
* Pricing: $0.30/input and $1.20/output per million tokens
2025-12-23 14:44:41 +08:00
Aiden Cline
a090e9a69a
Merge pull request #556 from InduwaraSMPN/dev-copy
...
Adds configuration for Openrouter/MiniMax M2.1 model
2025-12-22 22:10:19 -08:00
InduwaraSMPN
63b1f5e6a9
Adds configuration for MiniMax M2.1 model
...
Introduces support for MiniMax M2.1 with detailed model parameters,
cost estimates, and modality specifications to enable integration and
usage with the provider ecosystem.
2025-12-23 11:37:45 +05:30
Aiden Cline
0abcb5b3cf
Merge pull request #554 from dpuyosa/VeniceUpdate
...
Venice: Update Autogenerate Script
2025-12-22 20:49:09 -08:00
Aiden Cline
f0ae336593
Merge pull request #555 from no1wudi/glm
...
fix: set costs to 0 for zai-coding-plan provider
2025-12-22 20:48:41 -08:00
Huang Qi
f4b3e08d2a
fix: set costs to 0 for zai-coding-plan provider
...
Updated cost configuration for GLM-4.7 model to reflect subscription-based
billing rather than token-based pricing. Since zai-coding-plan uses a
subscription model, all per-token costs should be zero.
- Changed input cost from 0.6 to 0
- Changed output cost from 2.2 to 0
- Changed cache_read cost from 0.11 to 0
2025-12-23 12:38:18 +08:00
Frank
87ccab8807
update zen models
2025-12-22 19:43:48 -05:00
dpuyosa
e571d678ac
Update cost.cache_read for models that support cache
2025-12-23 01:30:24 +01:00
dpuyosa
d6650a05df
Update generate-venice.ts to include new cache feature (cache_read cost)
2025-12-23 01:28:41 +01:00
Frank
4be4bea336
update zen models
2025-12-22 19:11:48 -05:00
Aiden Cline
840be0e2b8
Merge pull request #551 from reissbaker/glm-4.7
...
Add Synthetic's GLM-4.7 hosting
2025-12-22 15:54:53 -08:00
Matt Baker
484a603366
Add interleaved thinking setting
2025-12-22 15:45:40 -08:00
Frank
b604eabecf
update zen models
2025-12-22 18:13:41 -05:00
Frank
fb4abefa68
update zen models
2025-12-22 17:49:12 -05:00
Aiden Cline
e3e89e4fbf
Merge pull request #552 from titouv/dev
...
Add OpenRouter Z.AI GLM 4.7
2025-12-22 14:33:28 -08:00
Aiden Cline
e7bc32be6b
fix
2025-12-22 16:31:59 -06:00
Aiden Cline
e469476732
Merge pull request #553 from superhighfives/cgleason/fix-model-mapping
...
Fix model mapping for Cloudflare AI Gateway.
2025-12-22 14:24:35 -08:00
Charlie Gleason
0d448bf0a2
Updated Cloudflare AI Gateway models
2025-12-22 14:11:24 -08:00
Titouan V
d408d60f49
openrouter glm 4.7 add interleaved reasoning_content
2025-12-22 21:54:21 +00:00
Titouan V
ea0250433c
feat: add openrouter z.ai glm 4.7
2025-12-22 21:32:24 +00:00
Matt Baker
e22dd2f3de
Add Synthetic's GLM-4.7 hosting
2025-12-22 13:27:22 -08:00
Frank
39e5930b3b
update zen models
2025-12-22 12:02:12 -05:00
Aiden Cline
a6093eafe6
Merge pull request #548 from no1wudi/glm
...
feat: add glm-4.7 model with interleaved thinking
2025-12-22 08:07:41 -08:00
Huang Qi
26778bd4cf
feat: add glm-4.7 model with interleaved thinking
...
Add GLM-4.7 model configuration to zai, zai-coding-plan, zhipuai,
and zhipuai-coding-plan providers. The model features interleaved
reasoning capability with reasoning_content field.
* Created glm-4.7.toml in zai and zai-coding-plan providers
* Added symlinks in zhipuai and zhipuai-coding-plan providers
* Configured with same pricing and limits as glm-4.6
* Supports reasoning, tool_call, and temperature settings
2025-12-22 23:12:48 +08:00
Aiden Cline
970c13f8d7
Merge pull request #546 from dpuyosa/RemoveDeprecated
...
Venice: Remove deprecated model devstral-2-2512
2025-12-21 20:00:38 -08:00
Aaron Iker
4654d1f039
Merge pull request #547 from sst/visually-align-logo-weights
...
fix: Visually align provider logos
2025-12-21 23:14:01 +01:00
Aaron Iker
b2b7f7e99a
fix: align colors, subtle fills
2025-12-21 23:09:03 +01:00
Aaron Iker
9a19c74ef9
fix: remaining provider logos
2025-12-21 22:42:41 +01:00
Aaron Iker
6fafd70000
fix: reorder some provider logos
2025-12-21 22:38:00 +01:00
dpuyosa
1e64e546cc
Remove deprecated model devstral-2-2512
2025-12-21 22:25:02 +01:00
Aaron Iker
d35af033d0
fix: visually align provider logos
2025-12-21 22:08:18 +01:00
Aiden Cline
9264f8bead
deepinfra: add minimax m2 & kimi k2 thinking
2025-12-20 23:39:17 -06:00
Aiden Cline
cf2c8aecd3
Merge pull request #545 from JaviMaligno/oss-agent/issue-528-add-nvidia-nemotron-3-nano
...
fix: Add Nvidia Nemotron 3 Nano
2025-12-20 19:14:43 -08:00
Aiden Cline
469026c193
Delete validation_output.json
2025-12-20 17:30:42 -06:00
Javier
13f09f8b90
fix: Add Nvidia Nemotron 3 Nano ( #528 )
...
Fixes #528
---
Changes prepared with assistance from OSS-Agent
2025-12-21 00:05:05 +01:00
Aiden Cline
620c92a5ed
Merge pull request #544 from dpuyosa/RemoveDeprecated
...
Venice: Remove deprecated model qwen3-235b
2025-12-20 12:35:39 -08:00
Aiden Cline
6b6e733a72
Revert "tweak: update ollama logo, add ollama local"
...
This reverts commit 8ff1ca4747 .
2025-12-20 14:28:03 -06:00
Aiden Cline
be1f2f9bc8
Revert "fix: validation err"
...
This reverts commit 91e7dac265 .
2025-12-20 14:27:59 -06:00
Aiden Cline
bf6f1ac1c9
Revert "fix: env"
...
This reverts commit 4105e28730 .
2025-12-20 14:27:57 -06:00
Aiden Cline
b01ccb1504
Revert "fix: handle empty dir"
...
This reverts commit 62ff421d08 .
2025-12-20 14:27:54 -06:00
Aiden Cline
b07097c62b
Revert "fix: dir check"
...
This reverts commit 4e69c0f724 .
2025-12-20 14:27:53 -06:00
Aiden Cline
4e69c0f724
fix: dir check
2025-12-20 14:01:01 -06:00
Aiden Cline
62ff421d08
fix: handle empty dir
2025-12-20 13:57:27 -06:00
dpuyosa
d9f270fe31
Remove deprecated model qwen3-235b
2025-12-20 20:52:31 +01:00
Aiden Cline
4105e28730
fix: env
2025-12-20 13:03:11 -06:00
Aiden Cline
91e7dac265
fix: validation err
2025-12-20 12:42:39 -06:00
Aiden Cline
8ff1ca4747
tweak: update ollama logo, add ollama local
2025-12-20 12:40:47 -06:00
Aiden Cline
3f4d29af7b
revert venice ai npm change
2025-12-20 12:07:18 -06:00
Aiden Cline
7a9c0a9591
Revert "Merge pull request #543 from sst/revert-536-VeniceUpdate"
...
This reverts commit 16f9f608de , reversing
changes made to 9b0ae67d59 .
2025-12-20 12:06:09 -06:00
Aiden Cline
16f9f608de
Merge pull request #543 from sst/revert-536-VeniceUpdate
...
Revert "Venice Autogenerate Script"
2025-12-20 08:50:00 -08:00
Aiden Cline
6a8adee790
Revert "Venice Autogenerate Script"
2025-12-20 10:49:49 -06:00
Frank
9b0ae67d59
update zen models
2025-12-20 02:37:04 -05:00
Frank
42275ae674
update zen model
2025-12-20 01:26:13 -05:00
Aiden Cline
1c4ec77b81
moonshot: add interleaved setting
2025-12-19 17:01:40 -06:00
Aiden Cline
94028fdbdb
Merge pull request #536 from dpuyosa/VeniceUpdate
...
Venice Autogenerate Script
2025-12-19 14:27:50 -08:00
Aiden Cline
321a4fb35b
Merge pull request #542 from ParthSareen/parth/update-ollama-deps-and-api
...
providers: fix ollama api url
2025-12-19 14:26:42 -08:00
Aiden Cline
4cea7b5651
Merge branch 'dev' into parth/update-ollama-deps-and-api
2025-12-19 16:26:01 -06:00
Aiden Cline
68385a4efa
ci: fix validation
2025-12-19 16:25:38 -06:00
ParthSareen
bf449e0a9f
providers: fix ollama api url
2025-12-19 14:19:35 -08:00
Aiden Cline
5526d7f615
switch venice ai to use openrouter aisdk pkg, fix deepseek v3.2 on openrouter
2025-12-19 16:07:14 -06:00
Aiden Cline
5feaf08c52
Merge pull request #541 from ParthSareen/parth/update-ollama-deps-and-api
...
provider: update ollama cloud, and use openai compat
2025-12-19 12:32:58 -08:00
ParthSareen
3a6c747433
provider: update ollama cloud, and use openai compat
2025-12-19 12:29:56 -08:00
David Hill
22f0d939e3
fix: update zen logo
2025-12-19 15:06:51 +00:00
Aiden Cline
25a49727b1
Merge pull request #538 from no1wudi/dev
...
feat: add xiaomi provider with mimo-v2-flash model
2025-12-18 21:14:22 -08:00
Huang Qi
b8d9ded7d3
feat: add xiaomi provider with mimo-v2-flash model
...
Integrate Xiaomi AI services into the models.dev ecosystem by adding
support for their MiMo-V2-Flash model through OpenAI-compatible API.
* Add xiaomi provider configuration with api.xiaomimimo.com endpoint
* Configure environment variable XIAOMI_API_KEY for authentication
* Add mimo-v2-flash model with 256k context window and reasoning support
* Set pricing at /usr/bin/zsh.07 input / /usr/bin/zsh.21 output per 1M tokens
* Enable tool calling and interleaved reasoning capabilities
* Configure as open weights model for transparency
This addition follows the existing provider pattern and maintains
compatibility with the OpenAI SDK through @ai-sdk/openai-compatible.
2025-12-19 12:59:59 +08:00
Aiden Cline
f21fef4c5d
fix: oepnrouter gemini 3 flash
2025-12-18 19:43:55 -06:00
Frank
45a6ccce32
update zen models
2025-12-18 13:36:49 -05:00
Aiden Cline
0836bb84e5
Merge pull request #537 from s-scheck/feat/add-two-free-mistral-models
...
add two free mistral models
2025-12-18 08:32:05 -08:00
Sinan Scheck
f357887fd4
add two free mistral models
2025-12-18 17:14:44 +01:00
Aiden Cline
afde8f6b81
Merge pull request #535 from davidcharbonnier/dev
...
Google VertexAI - Add gemini-3-flash-preview model
2025-12-18 07:42:42 -08:00
David Charbonnier
142435d232
vertex: add gemini-3-flash-preview model
2025-12-18 10:21:38 -05:00
dpuyosa
f646fadeb4
Merge branch 'sst:dev' into VeniceUpdate
2025-12-18 16:21:11 +01:00
dpuyosa
07fcc36057
Update README.md
2025-12-18 16:16:23 +01:00
Aiden Cline
ffbe6dc6b6
Merge pull request #533 from no1wudi/dev
...
feat: add Xiaomi MiMo-V2-Flash model configuration
2025-12-18 07:03:19 -08:00
dpuyosa
ac1a717bf3
Update Venice models with Generate Script
2025-12-18 15:40:06 +01:00
dpuyosa
22404d19f6
Add readme
2025-12-18 15:32:32 +01:00
dpuyosa
5034aacb9b
Add Venice autogenerate script.
...
Add Venice logo.
2025-12-18 15:16:46 +01:00
Aiden Cline
d20f4c3309
Merge pull request #534 from requestyai/requesty/gemini-3-flash
...
requesty: gemini 3 flash
2025-12-18 05:42:10 -08:00
John Costa
2b1d1e73c4
requesty: gemini 3 flash
2025-12-18 10:31:53 +00:00
Huang Qi
f30fecfdc0
feat: add Xiaomi MiMo-V2-Flash model configuration
...
Add new Xiaomi MiMo-V2-Flash model to Zenmux provider with complete
specification including capabilities, pricing, limits, and modalities.
* Configured reasoning and tool calling capabilities
* Set knowledge cutoff date to 2024-12-01
* Defined cost structure (input: $0.07, output: $0.21)
* Established context limits (256K input, 32K output)
* Text-only modality support
2025-12-18 16:58:49 +08:00
Aiden Cline
12eeb32b60
Merge pull request #532 from DanRioDev/patch-2
...
hotfix: correct Copilot Gemini 3 model naming
2025-12-17 16:57:54 -08:00
Dan (Danilo) Rio (Ribeiro)
992d354085
hotfix: correct model naming
2025-12-17 20:49:42 -03:00
Aiden Cline
22a09c2506
Merge pull request #531 from KevinPoorDeveloper/dev
...
Add Gemini 3 Flash Preview model configuration
2025-12-17 15:15:10 -08:00
Aiden Cline
2c973f6be7
Merge pull request #530 from DanRioDev/patch-1
...
Add Gemini 3 Flash to Copilot
2025-12-17 15:00:54 -08:00
Kevin
0a6e9046d7
Add Gemini 3 Flash Preview model configuration
2025-12-17 14:59:56 -08:00
Dan (Danilo) Rio (Ribeiro)
f24f850e22
Update Gemini model details in TOML file
2025-12-17 19:57:08 -03:00
Aiden Cline
5ff7fad6c3
Merge pull request #529 from markusylisiurunen/fix-gemini-3-flash-preview-pricing
...
Fix Gemini 3 Flash Preview pricing
2025-12-17 12:39:42 -08:00
Markus Ylisiurunen
cee38f160d
fix OpenRouter as well
2025-12-17 22:29:08 +02:00
Markus Ylisiurunen
8cbe01b9fc
use the correct Gemini 3 Flash prices
2025-12-17 22:15:41 +02:00
Aiden Cline
f16290906a
Merge pull request #523 from sst/opencode/issue521-20251217020621
...
Created siliconflow-cn provider with CN API
2025-12-17 10:06:04 -08:00
Aiden Cline
9a3789408f
Merge pull request #527 from mvarrieur/add-opus-4.5
...
Bedrock: Add Opus 4.5
2025-12-17 09:29:39 -08:00
Michael Varrieur
f5894edf77
Add new fields
2025-12-17 12:25:09 -05:00
Michael Varrieur
ece7021c2c
Add back Bedrock 4.5 provider
2025-12-17 12:23:09 -05:00
Aiden Cline
c8c8e31920
Revert "Fixed broken symlink in vercel/cerebras"
...
This reverts commit df62e66cb7 .
2025-12-17 10:31:12 -06:00
Aiden Cline
a54e4d580c
Merge pull request #525 from shkumbinhasani/add-gemini-3-flash-preview
...
Add Gemini 3 Flash Preview model
2025-12-17 08:19:09 -08:00
Aiden Cline
ff2c7bb84a
Merge pull request #526 from shkumbinhasani/add-gemini-3-flash-preview-openrouter
...
Add Gemini 3 Flash Preview to OpenRouter
2025-12-17 08:18:56 -08:00
shkumbinhasani
866f9673aa
Add Gemini 3 Flash Preview to OpenRouter
2025-12-17 17:16:12 +01:00
shkumbinhasani
ee2b9d8a30
Add Gemini 3 Flash Preview model
2025-12-17 17:12:47 +01:00
Frank
4bb140ab53
update zen models
2025-12-17 11:09:12 -05:00
opencode-agent[bot]
df62e66cb7
Fixed broken symlink in vercel/cerebras
...
Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com >
2025-12-17 02:11:52 +00:00
opencode-agent[bot]
3a457d5c96
Created siliconflow-cn provider with CN API
...
Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com >
2025-12-17 02:08:23 +00:00
Charlie Gleason
eb31887b3d
Fix model mapping
2025-12-15 16:14:58 -08:00
Frank
14c7777ca5
update zen models
2025-12-15 15:52:34 -05:00
Aiden Cline
ec7e706fcd
Merge pull request #516 from fhennerkes/dev
...
poe: add 7 new models
2025-12-15 12:38:48 -08:00
fhennerkes
c963c1ef4d
Poe: remove deepseek-v3.2
2025-12-15 12:24:04 -08:00
fhennerkes
81ae5e3bab
Merge branch 'sst:dev' into dev
2025-12-15 12:17:56 -08:00
Aiden Cline
29e0135d9a
Merge pull request #520 from shelvick/add-azure-models-dec-2025
...
Add new Azure models: GPT-5.2 Chat, DeepSeek-V3.2, Kimi K2 Thinking
2025-12-15 11:59:58 -08:00
Scott Helvick
8ec1d1477c
add new azure models: gpt-5.2-chat, deepseek-v3.2, deepseek-v3.2-speciale, kimi-k2-thinking
...
- GPT-5.2 Chat: multimodal chat model (128K context, 16K output)
- DeepSeek-V3.2: reasoning model with tool calling (128K context/output)
- DeepSeek-V3.2-Speciale: specialized variant without tool calling
- Kimi K2 Thinking: agentic reasoning model with interleaved thinking (262K context/output)
All models symlinked to Azure Cognitive Services.
2025-12-15 18:47:48 +00:00
Aiden Cline
ccb453d05d
add glm 4.6v
2025-12-15 10:35:39 -06:00
Aiden Cline
952d7f8990
Merge pull request #519 from helmifraser/add-bedrock-kimi-k2-thinking
...
Adds Kimi K2 Thinking model config to Amazon Bedrock provider
2025-12-15 08:21:38 -08:00
Aiden Cline
51fe45b82f
Add interleaved option to moonshot model config
2025-12-15 10:21:06 -06:00
Helmi Fraser
31e86578d2
Adds Kimi K2 Thinking model config to Amazon Bedrock provider
2025-12-15 13:01:57 +00:00
Aiden Cline
deb1a65df6
Merge pull request #501 from ASMAE20/feat/add_new_supported_model_to_cortecs
...
feat: add new supported models
2025-12-14 23:44:08 -08:00
ASMAE20
df0101cf2d
fix: validation issue
2025-12-15 08:26:27 +01:00
ASMAE20
f84d599fd1
fix: add interleaved parameter
2025-12-15 08:08:50 +01:00
Aiden Cline
943cc7dcce
Merge pull request #517 from shamil2/add-sherlock-models
...
Add OpenRouter Sherlock models
2025-12-14 15:55:41 -08:00
Shamil GHASEETA
b270d8149b
Add OpenRouter Sherlock models: Think Alpha and Dash Alpha
...
- Sherlock Think Alpha: Reasoning-focused model with 1.8M context
- Sherlock Dash Alpha: Speed-focused model with 1.8M context
- Both are free during alpha, multimodal, excel at tool calling
2025-12-14 23:30:16 +01:00
Adam
154d9edb53
feat: model family
2025-12-14 04:07:47 -06:00
Adam
8de746edab
feat: model family
2025-12-14 03:41:22 -06:00
fhennerkes
a80bec3776
poe: add 7 new models
...
Add new Poe models:
- gemini-deep-research (Google)
- deepseek-v3.2 (Novita)
- gpt-5.1-codex-max (OpenAI)
- gpt-5.2 (OpenAI)
- gpt-5.2-instant (OpenAI)
- gpt-5.2-pro (OpenAI)
- claude-code (Poe Tools)
2025-12-13 23:46:42 -08:00
Aiden Cline
2380542c68
Merge pull request #515 from helmifraser/update-bedrock-models
...
Amazon Bedrock: updates available models
2025-12-13 11:05:23 -08:00
Aiden Cline
287e00198d
Merge pull request #514 from superhighfives/cloudflare-ai-gateway-updates
...
Update Cloudflare AI Gateway model configurations
2025-12-13 08:58:53 -08:00
Helmi Fraser
d64d6cefbb
Add Qwen Bedrock models: Qwen3 Next and Qwen3 VL
2025-12-13 12:09:41 +00:00
Helmi Fraser
53b4d3d6ca
Add OpenAI Bedrock models: GPT OSS (20B, 120B with and without safeguard)
2025-12-13 12:06:38 +00:00
Helmi Fraser
222d9442ba
Add NVIDIA Bedrock models: Nemotron Nano (9B and 12B variants)
2025-12-13 12:06:38 +00:00
Helmi Fraser
08bd1c04d0
Add Mistral AI Bedrock models: Ministral, Mistral Large, Mixtral, Voxtral
2025-12-13 12:06:38 +00:00
Helmi Fraser
820357141f
Add Google Bedrock models: Gemma 3 (4B, 12B, 27B variants)
2025-12-13 12:06:38 +00:00
Helmi Fraser
b47069079a
Add Amazon Bedrock models: Nova 2 Lite and Titan Text Express
2025-12-13 12:06:38 +00:00
Frank
9972fed6a5
update zen model
2025-12-13 00:14:21 -05:00
Charlie Gleason
b417cb6f26
Update Cloudflare AI Gateway model configurations
...
- Update model TOML files for anthropic, openai, replicate, and workers-ai providers
- Add new generation scripts (generate_model_names.sh, generate_model_toml.sh, utils.sh)
- Add model_names.json and API response data
- Remove duplicate/deprecated model files
- Standardize model configuration format
2025-12-12 17:06:09 -08:00
Frank
f7a4d0f3c5
update zen models
2025-12-12 13:55:30 -05:00
Helmi Fraser
a52d5318be
Adds MiniMax M2 model config for Amazon Bedrock
2025-12-12 15:44:01 +00:00
Frank
19f27546d8
update zen models
2025-12-11 23:55:18 -05:00
Aiden Cline
6624336d0b
Merge pull request #513 from ai13f/patch-7
...
Update GPT model version to 5.2 with new settings
2025-12-11 19:10:12 -08:00
Aiden Cline
39883b120f
Merge pull request #512 from no1wudi/dev
...
Unify GLM model names to GLM-x.y pattern
2025-12-11 19:09:45 -08:00
ai13f
44851914d8
Update GPT model version to 5.2 with new settings
2025-12-11 22:09:20 -05:00
Huang Qi
93b50c296c
Unify GLM model names to GLM-x.y pattern
...
- Update GLM 4.5V to GLM-4.5V in zai and zai-coding-plan providers
- Ensures consistent naming convention across GLM serial models
2025-12-12 11:02:53 +08:00
Aiden Cline
4bf5a8a71d
Merge pull request #498 from riccardogiorato/dev
...
feat: updating together ai models with newer ones up to December 2025
2025-12-11 17:48:41 -08:00
Aiden Cline
1709d6e5b7
Add interleaved option to Kimi-K2-Thinking model
2025-12-11 19:47:18 -06:00
Aiden Cline
5db0bf3bb4
Merge pull request #510 from KevinPoorDeveloper/dev
...
Add GPT 5.2 for Venice.ai provider
2025-12-11 17:24:39 -08:00
Kevin
3a9778785e
Merge pull request #1 from KevinPoorDeveloper/Add-GPT-5.2-for-Venice
...
Add configuration for OpenAI GPT-5.2 model for Venice.ai
2025-12-11 17:15:22 -08:00
Kevin
2aa6914767
Add configuration for OpenAI GPT-5.2 model for Venice.ai
2025-12-11 17:00:34 -08:00
David Hill
e8fbabf47a
fix: update ollama logo
2025-12-12 00:42:26 +00:00
David Hill
dbbc7e3fbb
fix: update zen logo
2025-12-12 00:09:49 +00:00
David Hill
9101e7f5fc
fix: update zen logo
2025-12-11 23:01:16 +00:00
Aiden Cline
2fe1240277
Merge pull request #509 from Mickael-Roger/typo-in-devstal-name
...
There is a Typo in the paid Devstral Name on openrouter (Indicate Free)
2025-12-11 13:42:36 -08:00
MickaelRoger
f80b415e45
There is a Typo in the paid Devstral Name on openrouter (It indicates Free)
2025-12-11 22:21:10 +01:00
Aiden Cline
8536e0c69b
Merge pull request #508 from Mickael-Roger/add-mistral-devstral-2
...
Add MistralAI Devstral 2 (Free and Paid) infered on Openrouter
2025-12-11 13:15:29 -08:00
MickaelRoger
bca891d82e
Add MistralAI Devstral 2 (Free and Paid) infered on Openrouter
2025-12-11 21:40:16 +01:00
Aiden Cline
c3bf224da9
Merge pull request #507 from Reusek/dev
...
Add OpenRouter GPT-5.2 models
2025-12-11 12:32:44 -08:00
Aiden Cline
c773a4d651
Merge pull request #506 from AleksanderBondar/dev
...
Copilot - GPT 5.2
2025-12-11 12:31:46 -08:00
Albert Klinkovský
ce032da6e2
Add OpenRouter GPT-5.2 models
2025-12-11 21:27:23 +01:00
Aleksander Bondar
60fdf0ea38
Copilot - GPT 5.2
2025-12-11 21:22:45 +01:00
Aiden Cline
d959c9415c
Merge pull request #505 from shkumbinhasani/fix-gpt-5.2-models
...
Fix GPT-5.2 models to match GPT-5.1 structure
2025-12-11 11:17:34 -08:00
shkumbinhasani
3705c15a39
Fix GPT-5.2 models to match GPT-5.1 structure
2025-12-11 20:15:21 +01:00
Aiden Cline
22cc1a5a27
Merge pull request #504 from shkumbinhasani/add-gpt-5.2-models
...
Add OpenAI GPT-5.2 model family
2025-12-11 11:12:41 -08:00
shkumbinhasani
e3815e2698
Add OpenAI GPT-5.2 model family
2025-12-11 20:09:49 +01:00
Aiden Cline
3675e0654c
Merge pull request #502 from s-scheck/add-two-mistral-models
...
feat: add mistral-small-2506 and mistral-embed
2025-12-11 07:57:47 -08:00
Aiden Cline
947e18adb8
Merge pull request #503 from matthusby/dev
...
Update the Chutes models from the api output
2025-12-11 07:57:29 -08:00
Matt Husby
b468fca6a7
Update the Chutes models from the api output
2025-12-11 08:47:45 -05:00
Sinan Scheck
3ff33acb1b
add mistral small 2506 model
2025-12-11 12:23:18 +01:00
Sinan Scheck
eca4a579de
add mistrals embedding model
2025-12-11 12:22:48 +01:00
ASMAE20
ec418b3d5c
feat: add new supported models
2025-12-11 08:49:07 +01:00
Aiden Cline
0c66fc84a2
fix: copilot pdf
2025-12-10 23:06:36 -06:00
Riccardo Giorato
0c76289971
Update GLM-4.6.toml
2025-12-10 22:15:40 +01:00
Riccardo Giorato
af87011435
Update Kimi-K2-Thinking.toml
2025-12-10 22:13:55 +01:00
Riccardo Giorato
32d4d0dce5
Update gpt-oss-120b.toml
2025-12-10 22:12:29 +01:00
Riccardo Giorato
68ec7759d4
Add new model configurations for DeepSeek-V3-1, Rnj-1-Instruct, Kimi-K2-
2025-12-10 22:08:33 +01:00
Dax Raad
2ef3dd0d2d
add family to UI
2025-12-10 14:35:14 -05:00
Aiden Cline
207947d310
Merge pull request #494 from FrancoStino/patch-4
...
Create kimi-k2-thinking.toml
2025-12-10 11:34:46 -08:00
Dax Raad
8698310f77
add models.dev family
2025-12-10 14:29:36 -05:00
Aiden Cline
b32ec1eb29
tweak openrouter deepseek v3.2
2025-12-10 13:11:02 -06:00
Aiden Cline
247c315077
tweak: baseten deepseekv3.2
2025-12-10 11:23:44 -06:00
Aiden Cline
10d232abb9
fix: deepseek
2025-12-10 11:17:09 -06:00
Davide Ladisa
38b9d89fd7
Update kimi-k2-thinking.toml
2025-12-10 17:36:27 +01:00
Aiden Cline
68309a87db
Merge pull request #493 from FrancoStino/patch-3
...
Create devstral-2-123b-instruct-2512.toml
2025-12-10 07:13:27 -08:00
Aiden Cline
06b00f24f7
Merge pull request #495 from no1wudi/dev
...
feat: add GLM-4.6V model to ZAI providers
2025-12-10 07:13:08 -08:00
Aiden Cline
aecf1d3e15
Merge pull request #492 from FrancoStino/patch-2
...
Create ministral-14b-instruct-2512.toml
2025-12-10 07:12:46 -08:00
Aiden Cline
174d0b1513
Merge pull request #496 from s-scheck/labs-devstral-small-2512
...
add labs-devstral-small-2512
2025-12-10 07:11:39 -08:00
Sinan Scheck
db4d06b32a
add labs-devstral-small-2512
2025-12-10 15:37:12 +01:00
Huang Qi
3a9c0633fe
feat: add GLM-4.6V model to ZAI providers
...
- Add GLM-4.6V model to ZAI provider with official pricing (/usr/bin/zsh.3//usr/bin/zsh.9 per 1M tokens)
- Add GLM-4.6V model to ZAI Coding Plan provider with free pricing (0/0)
- Create symlinks for zhipuai and zhipuai-coding-plan providers
- Based on official Z.AI documentation (Dec 8, 2025)
- Features: 128K context, native tool calling, multimodal support
- Modalities: text, image, video input → text output
- Open source model with MIT license
- Add proper formatting with trailing newlines
2025-12-10 21:26:15 +08:00
Davide Ladisa
51e58ec2fc
Create kimi-k2-thinking.toml
2025-12-10 11:00:40 +01:00
Davide Ladisa
aeee4cd3eb
Create devstral-2-123b-instruct-2512.toml
2025-12-10 10:45:57 +01:00
Davide Ladisa
80c693345d
Update ministral-14b-instruct-2512.toml
2025-12-10 10:26:13 +01:00
Davide Ladisa
3a8a4eca79
Create ministral-14b-instruct-2512.toml
2025-12-10 10:24:25 +01:00
Aiden Cline
f49b0f8828
openrouter gemini interleaved
2025-12-09 15:35:09 -06:00
Frank
9792d9bc0e
Update interleaved field name
2025-12-09 21:22:42 +00:00
Aiden Cline
8a762009c4
name -> field
2025-12-09 15:06:58 -06:00
Aiden Cline
255960f1d1
interleaved thinking tweaks
2025-12-09 14:44:08 -06:00
Aiden Cline
8bc49fece7
Merge pull request #491 from sst/cursor/update-schema-add-interleaved-146b
...
Update schema add interleaved
2025-12-09 12:33:44 -08:00
Cursor Agent
8ad9873ac0
Refactor: Move interleaved to its own section
...
Co-authored-by: frank <frank@anomalyinnovations.com >
2025-12-09 18:56:56 +00:00
Cursor Agent
656973307d
feat: Add interleaved support for Claude Sonnet and Kimi K2
...
Co-authored-by: frank <frank@anomalyinnovations.com >
2025-12-09 18:56:16 +00:00
Cursor Agent
afcffa357f
feat: Add interleaved support to model configuration
...
Co-authored-by: frank <frank@anomalyinnovations.com >
2025-12-09 18:50:39 +00:00
Cursor Agent
5321a3d5fd
feat: Add interleaved option to Model schema
...
Co-authored-by: frank <frank@anomalyinnovations.com >
2025-12-09 18:49:05 +00:00
Aiden Cline
98d27c6268
Merge pull request #485 from fhennerkes/dev
...
Poe: price and model update 25/12/8
2025-12-09 10:19:11 -08:00
fhennerkes
6092e00b87
poe: ree-add pdf as input modality for anthropic models
2025-12-09 10:16:38 -08:00
fhennerkes
b794ee9bd9
Merge branch 'sst:dev' into dev
2025-12-09 10:05:42 -08:00
Aiden Cline
597350692c
Merge pull request #487 from ProlowN/dev
...
feat/Removed deprecated models and added new models for Venice
2025-12-09 09:52:11 -08:00
Aiden Cline
f4280b9793
Merge pull request #490 from ThomsenDrake/add-devstral-2-latest
...
feat: add Devstral 2 model configuration
2025-12-09 09:51:48 -08:00
Drake Thomsen
c9db39c5d2
feat: add Devstral 2 model configuration
...
Adds devstral-medium-latest.toml with the new Devstral 2 123B Instruct model
specifications including 256k context window and updated capabilities.
Generated by Mistral Vibe.
Co-Authored-By: Mistral Vibe <vibe@mistral.ai >
2025-12-09 12:42:32 -05:00
Aiden Cline
36cf6c178f
Merge pull request #488 from onlylonly/dev
...
add GPT OSS 120B and GPT OSS 20B model configuration files for VertexAI
2025-12-09 07:52:09 -08:00
Aiden Cline
10d3a81f45
Merge pull request #489 from jerome-benoit/fix/sap-ai-core-env
...
fix: update env variable name for SAP AI Core provider
2025-12-09 07:49:37 -08:00
Jérôme Benoit
0be9b2ed3b
fix: update env variable name for SAP AI Core provider
...
Signed-off-by: Jérôme Benoit <jerome.benoit@piment-noir.org >
2025-12-09 16:42:43 +01:00
onlylonly
9428a93e37
add GPT OSS 120B and GPT OSS 20B model configuration files for VertexAI
2025-12-09 12:43:52 +00:00
Magnus
cf659278af
feat/Removed deprecated models and added new models
2025-12-09 12:46:49 +01:00
Xinrui
a6b28915fe
aihubmix: add models claude-opus-4.5, gpt-5.1-codex-max, coding-glm-4.6-free
2025-12-09 19:18:08 +08:00
fhennerkes
4cbcd96c1f
Merge poe-pricing-sync into dev (selective)
...
Includes:
- Unify openai folder naming (openAi -> openai) - 35 files
- Update pricing for existing Poe models (Anthropic, Google, xAI, OpenAI)
- Add 4 new Poe models with tool support:
- claude-opus-4.5
- nano-banana-pro
- kimi-k2-thinking
- grok-4.1-fast-reasoning
66 files changed, 125 insertions(+), 93 deletions(-)
2025-12-08 21:19:49 -08:00
fhennerkes
285778e4f7
poe: add pricing sync script and update 12/8
2025-12-08 21:06:36 -08:00
fhennerkes
93a614b748
poe: unify openai folder naming
2025-12-08 21:06:36 -08:00
fhennerkes
94dd76937a
Merge branch 'sst:dev' into poe-pricing-sync
2025-12-08 19:18:18 -08:00
Aiden Cline
cda8c3087b
Merge pull request #484 from dogmatic69/azure/gpt-5.1-codex-max
...
add azure gpt-5.1-codex-max model
2025-12-08 14:03:25 -08:00
Carl Sutton (dogmatic69)
12eb654e40
add azure gpt-5.1-codex-max model
2025-12-08 22:47:43 +01:00
Aiden Cline
6f58b8baac
Merge pull request #325 from H2Shami/helicone-models
...
add helicone models + helicone model generation script
2025-12-08 13:17:03 -08:00
Hammad Shami
2388b6d188
update helicone svg + add more helicone models
2025-12-08 13:04:21 -08:00
Aiden Cline
644cf45916
Merge pull request #483 from djmaze/update_mistral_large
...
Update mistral-large for 2512 and separate model versions
2025-12-08 08:32:37 -08:00
djmaze
5d50a962ff
Update mistral-large for 2512 and separate model versions
2025-12-08 16:43:06 +01:00
Aiden Cline
0c37a91efc
Merge pull request #480 from crankycoder/vng/deepseek-3.2
...
add deepseek/Deepseek 3.2
2025-12-07 20:30:03 -08:00
Victor Ng
5b8cb39265
add deepseek/Deepseek 3.2
2025-12-07 23:27:47 -05:00
Aiden Cline
d7a539e5ea
fix: anthropic models so they properly list pdf as valid modality
2025-12-07 22:08:14 -06:00
Aiden Cline
28caae468e
Merge pull request #478 from elithrar/cf-aig-naming
...
fix: cloudflare-ai-gateway naming
2025-12-07 14:56:46 -08:00
Matt Silverlock
fbe0ea0088
cloudflare: fix model gen
2025-12-07 16:54:53 -05:00
Matt Silverlock
d2b7ba3957
cloudflare: update models
2025-12-07 16:29:38 -05:00
Matt Silverlock
474273e07d
cloudflare: update models
2025-12-07 16:00:58 -05:00
Matt Silverlock
92bbedc98c
--amend
2025-12-07 15:37:51 -05:00
Matt Silverlock
84e5977791
cloudflare: fix @cf -> workers-ai/ model naming + update provider.toml
2025-12-07 15:37:41 -05:00
Aiden Cline
cb75588156
Merge pull request #475 from georgeglarson/add-claude-opus-4-5
...
Add Claude Opus 4.5 model to Venice provider (claude-opus-45)
2025-12-06 11:09:39 -08:00
Aiden Cline
214db72999
Merge pull request #476 from elithrar/cloudflare-ai-gateway
...
add provider: Cloudflare AI Gateway
2025-12-06 11:02:51 -08:00
george larson
fc96c36f78
Remove unsupported beta field
2025-12-06 19:02:37 +00:00
Matt Silverlock
9b0a01d0ea
fix: use ai-gateway-provider npm pkg
2025-12-06 12:55:58 -05:00
Matt Silverlock
e86098c536
add provider: Cloudflare AI Gateway
2025-12-06 12:49:51 -05:00
george larson
e63f152a63
Add Claude Opus 4.5 model as claude-opus-45.toml
2025-12-06 12:16:27 +00:00
george larson
c7a8e153c9
Rename model file to match Venice API naming convention
2025-12-06 12:16:26 +00:00
george larson
8792dd616b
Update knowledge cutoff to 2025-03
2025-12-06 12:08:32 +00:00
george larson
f94eecdc22
Update providers/venice/models/claude-opus-4-5.toml
...
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
2025-12-05 21:17:52 -05:00
george larson
5ee1a42976
Add Claude Opus 4.5 model to Venice provider
2025-12-05 23:52:18 +00:00
Aiden Cline
17fc6274bd
Merge pull request #474 from nicolasgere/dev
...
Add baseten deepseek 3.2
2025-12-05 12:40:00 -08:00
Nicolas Gere-lamaysouette
5b4bc2b49b
add baseten deepseek 3.2
2025-12-05 12:05:40 -08:00
Aiden Cline
496d7cf3c7
Merge pull request #396 from sst/opencode/issue395-20251118055255
...
Added GPT-5 Pro to Azure Cognitive Services
2025-12-05 09:18:45 -08:00
Aiden Cline
b36a5d14a7
Merge pull request #473 from FrancoStino/patch-1
...
Create mistral-large-3-675b-instruct-2512.toml
2025-12-05 09:12:10 -08:00
Davide Ladisa
07beb4bc47
Update mistral-large-3-675b-instruct-2512.toml
2025-12-05 18:06:48 +01:00
Davide Ladisa
be0749a120
Update mistral-large-3-675b-instruct-2512.toml
2025-12-05 18:05:17 +01:00
Aiden Cline
ad66a95921
Merge pull request #472 from AleksanderBondar/dev
...
Copilot - GPT 5.1 Codex Max
2025-12-05 08:52:10 -08:00
Davide Ladisa
c0c8477742
Create mistral-large-3-675b-instruct-2512.toml
2025-12-05 17:46:26 +01:00
Frank
2015955f8c
fix codex model output modalities
2025-12-05 09:08:36 -05:00
Frank
a30bb0a8c1
Update zen models
2025-12-05 09:06:30 -05:00
Aleksander Bondar
95c0cf00a3
Copilot - GPT 5.1 Codex Max
2025-12-05 11:14:15 +01:00
Aiden Cline
a9963d76a8
Merge pull request #471 from teeverc/openai-5.1-codex-make
...
feat(openai): add OpenAI 5.1 Codex Max
2025-12-04 19:47:48 -08:00
teeverc
51af74ccb4
Fix OpenAI GPT-5.1 Codex Max display name
2025-12-04 19:25:52 -08:00
teeverc
098fd5a7c8
Add OpenAI GPT-5.1-Codex-Max model
2025-12-04 19:22:50 -08:00
Aiden Cline
ab11eb9675
Merge pull request #470 from jerome-benoit/feat/add-sap-ai-core-provider
...
feat: add SAP AI Core provider models
2025-12-04 18:13:01 -08:00
Jérôme Benoit
609623c5fc
fix: address valid review comments
...
Signed-off-by: Jérôme Benoit <jerome.benoit@piment-noir.org >
2025-12-05 01:57:08 +01:00
Jérôme Benoit
f4942b8147
refactor: remove deprecated SAP AI Core models
...
Signed-off-by: Jérôme Benoit <jerome.benoit@piment-noir.org >
2025-12-05 01:49:35 +01:00
Jérôme Benoit
c91f50d974
Revert "fix: mismerge SAP AI Core models"
...
This reverts commit ee18b6096d .
2025-12-05 01:48:40 +01:00
Jérôme Benoit
ee18b6096d
fix: mismerge SAP AI Core models
...
Signed-off-by: Jérôme Benoit <jerome.benoit@piment-noir.org >
2025-12-05 01:44:39 +01:00
Jérôme Benoit
f26b68b8a8
feat: add SAP AI Core provider models
...
Signed-off-by: Jérôme Benoit <jerome.benoit@piment-noir.org >
2025-12-05 01:44:39 +01:00
Aiden Cline
876cd26ee8
Merge pull request #469 from Cyber-Ice/dev
...
Added hf:deepseek-ai/DeepSeek-V3.2 to synthetic
2025-12-04 12:59:32 -08:00
Aiden Cline
6b30a0be14
kill agentrouter
2025-12-04 14:55:11 -06:00
Cyber-Ice
5c09ced055
Create DS-V3.2 for synthetic
2025-12-04 20:48:13 +00:00
Aiden Cline
632739e71a
Merge pull request #468 from ProlowN/dev
...
Added Grok 4.1 Fast to Venice
2025-12-04 09:52:10 -08:00
Magnus
234b0feaf4
Merge branch 'dev' of https://github.com/prolowN/models.dev into dev
2025-12-04 13:16:11 +01:00
Magnus
4bc2362b9e
feat/Added Grok 4.1 Fast to Venice
2025-12-04 13:16:03 +01:00
Aiden Cline
4a0805d71e
Merge pull request #467 from snadeau123/feat/add-deepseek-v3.2-speciale
...
feat: add DeepSeek V3.2 Speciale model
2025-12-03 14:31:16 -08:00
Sebastien Nadeau
8f01616d74
feat: add DeepSeek V3.2 Speciale model
2025-12-03 17:18:46 -05:00
Aiden Cline
51c376c666
Merge pull request #466 from jerome-benoit/feat/add-sap-ai-core-provider
...
feat: Add SAP AI Core provider
2025-12-03 13:51:11 -08:00
Jérôme Benoit
ee22cc4888
fix: add missing last_updated and open_weights fields to SAP AI Core models
2025-12-03 22:43:18 +01:00
Jérôme Benoit
a7fc4aba20
Apply suggestion from @Copilot
...
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
2025-12-03 22:08:09 +01:00
Jérôme Benoit
804a89b62f
Apply suggestion from @Copilot
...
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
2025-12-03 22:07:21 +01:00
OpenCode Bot
54dec2f61b
feat: add SAP AI Core provider
...
Add SAP AI Core provider with support for:
- GPT-4o
- Claude 3.5 Sonnet
- Gemini 1.5 Pro
SAP AI Core provides access to 40+ models from OpenAI, Anthropic, Google,
Amazon, Meta, Mistral, and AI21 through a unified platform.
Provider uses @mymediset/sap-ai-provider npm package and authenticates
via SAP_AI_SERVICE_KEY environment variable (SAP BTP service key JSON).
2025-12-03 21:56:32 +01:00
Aiden Cline
d24dc115fc
fix: ollama cloud model name
2025-12-03 14:44:53 -06:00
Aiden Cline
2b0f0ccc42
Merge pull request #465 from InduwaraSMPN/dev
...
Add DeepSeek-V3.2 and Kimi-K2-Thinking model configurations to the iflowcn provider
2025-12-03 08:26:36 -08:00
InduwaraSMPN
1bb65943e8
Refactor model names for consistency in DeepSeek-V3, Kimi-K2, and MiniMax-M2 configurations
2025-12-03 21:35:01 +05:30
InduwaraSMPN
a8bde6c08c
Add DeepSeek-V3.2 and Kimi-K2-Thinking model configurations to the iflowcn provider
2025-12-03 21:28:56 +05:30
Aiden Cline
364914c501
Merge pull request #464 from ProlowN/dev
...
Add Venice models: Gemini 3 Pro Preview and Kimi K2 Thinking
2025-12-03 07:37:21 -08:00
Magnus
b42b72b6d5
Add Venice models: Gemini 3 Pro Preview and Kimi K2 Thinking
2025-12-03 13:36:16 +01:00
Aiden Cline
0bc8f23411
Merge pull request #462 from briansakal/dev
...
add openrouter/deepseek-v3.2
2025-12-02 21:01:42 -08:00
Aiden Cline
adcea4c7f9
Merge pull request #463 from matthusby/dev
...
Update Chutes models based on the api output.
2025-12-02 20:57:32 -08:00
Matt Husby
92e85a7e14
Update Chutes models based on the api output.
2025-12-02 20:28:39 -05:00
Brian Sakal
e7b215e8be
add openrouter/deepseek-v3.2
2025-12-02 19:51:10 -05:00
Aiden Cline
f2419e88bf
Merge pull request #460 from ghostdevv/update-cf-models
...
chore: update cloudflare workers ai models
2025-12-02 11:50:04 -08:00
Aiden Cline
7f7bd5af92
Merge pull request #461 from ghostdevv/update-docs-schema-status
...
docs: fix schema status info
2025-12-02 11:43:25 -08:00
Willow (GHOST)
c035249f96
docs: fix schema status info
2025-12-02 19:24:22 +00:00
Willow (GHOST)
e180854216
chore: update cloudflare workers ai models
2025-12-02 19:20:00 +00:00
Aiden Cline
dd10de3aa8
Merge pull request #458 from EasyDevv/edit
...
feat: add DeepSeek-V3.2 models and update Kimi-K2-Thinking pricing
2025-12-02 09:21:52 -08:00
Aiden Cline
8bd2b3595f
Merge pull request #459 from briansunter/add-kimi-for-coding-provider
...
Add Kimi For Coding provider
2025-12-01 23:38:42 -08:00
Brian Sunter
87fc6287b3
Add Kimi For Coding provider
...
- Add kimi-for-coding provider with Kimi K2 Thinking model
- Uses @ai-sdk/anthropic with custom API endpoint
- 262K context, 32K output, supports reasoning/tool_call/structured_output
2025-12-01 20:26:09 -10:00
EasyDev
39c74282af
Merge branch 'dev' into edit
2025-12-02 10:52:04 +09:00
easydev
654fb92653
feat: update Kimi-K2-Thinking pricing and add DeepSeek-V3.2 models
...
- Update Kimi-K2-Thinking costs
- Add DeepSeek-V3.2 and DeepSeek-V3.2-Speciale models to chutes provider
2025-12-02 10:17:37 +09:00
Aiden Cline
7241e658bb
Merge pull request #457 from shelvick/fix-azure-tool-call-settings
...
fix tool_call settings for azure deepseek-r1-0528 and mai-ds-r1
2025-12-01 14:21:04 -08:00
Scott Helvick
f84f37a508
fix tool_call settings for azure deepseek-r1-0528 and mai-ds-r1
...
- Enable tool_call for deepseek-r1-0528 (supports function calling)
- Disable tool_call for mai-ds-r1 (does not support function calling)
2025-12-01 22:13:33 +00:00
Aiden Cline
fc67863d7a
Merge pull request #454 from shelvick/add-azure-llama-models
...
Add Meta Llama models to Azure and Azure Cognitive Services
2025-11-29 19:04:29 -08:00
Aiden Cline
0d5e78e407
Merge pull request #455 from shelvick/add-azure-microsoft-models
...
Add Microsoft Phi and MAI models to Azure providers
2025-11-29 19:04:14 -08:00
Aiden Cline
303f668568
Merge pull request #456 from shelvick/add-azure-mistral-models
...
add mistral models to azure and azure cognitive services
2025-11-29 16:01:01 -08:00
Aiden Cline
ac8b56ab57
Merge pull request #449 from shelvick/add-azure-embedding-models-and-router
...
Add embedding models and model-router to Azure providers
2025-11-29 15:59:48 -08:00
Scott Helvick
70e6b9c506
add mistral models to azure and azure cognitive services
...
Add 6 Mistral models to Azure and Azure Cognitive Services providers:
- Mistral Nemo
- Mistral Small 3.1 (mistral-small-2503)
- Mistral Medium 3 (mistral-medium-2505)
- Mistral Large 24.11 (mistral-large-2411)
- Ministral 3B
- Codestral 25.01
Azure Cognitive Services files are symlinks to Azure equivalents.
2025-11-29 23:08:42 +00:00
Scott Helvick
4dd70ef24a
add microsoft phi and mai models to azure providers
...
Add 15 Microsoft models to Azure and Azure Cognitive Services:
- Phi-4 series: Phi-4, Phi-4-mini, Phi-4-multimodal, Phi-4-reasoning,
Phi-4-mini-reasoning, Phi-4-reasoning-plus
- Phi-3.5 series: Phi-3.5-mini-instruct, Phi-3.5-MoE-instruct
- Phi-3 series: mini/small/medium variants (4k/8k/128k context)
- MAI-DS-R1 (Microsoft's DeepSeek R1 distillation)
Pricing from Azure AI Foundry. Tool calling only enabled for
Phi-4-mini, Phi-4-mini-reasoning, and MAI-DS-R1 (officially supported).
Reasoning mode only for Phi-4-reasoning variants and MAI-DS-R1.
2025-11-29 22:24:12 +00:00
Scott Helvick
8f9b00fbae
add Meta Llama models to Azure and Azure Cognitive Services
...
Adds 10 Meta Llama models to Azure with Azure-specific pricing:
- Llama 4 Maverick 17B 128E Instruct FP8
- Llama 4 Scout 17B 16E Instruct
- Llama 3.3 70B Instruct
- Llama 3.2 90B Vision Instruct
- Llama 3.2 11B Vision Instruct
- Meta Llama 3.1 405B Instruct
- Meta Llama 3.1 70B Instruct
- Meta Llama 3.1 8B Instruct
- Meta Llama 3 70B Instruct
- Meta Llama 3 8B Instruct
Azure Cognitive Services models are symlinked to Azure equivalents.
2025-11-29 21:46:17 +00:00
Aiden Cline
372190649d
Merge pull request #451 from shelvick/add-azure-cohere-models
...
add Cohere models to Azure providers
2025-11-29 13:22:30 -08:00
Aiden Cline
6ee919b10a
Merge pull request #452 from shelvick/fix-deepseek-symlinks
...
convert ACS DeepSeek files to symlinks
2025-11-29 13:22:17 -08:00
Aiden Cline
ce3adc2062
Merge pull request #453 from shelvick/add-azure-xai-models
...
add xAI Grok models to Azure providers
2025-11-29 13:22:01 -08:00
Scott Helvick
983e390391
add xAI Grok models to Azure providers
...
Adds 6 xAI Grok models to Azure and Azure Cognitive Services:
- grok-3
- grok-3-mini
- grok-4
- grok-4-fast-reasoning
- grok-4-fast-non-reasoning
- grok-code-fast-1
2025-11-29 21:04:45 +00:00
Scott Helvick
56c5af723c
convert ACS DeepSeek files to symlinks
2025-11-29 20:50:25 +00:00
Scott Helvick
cd63d80bb8
convert ACS embedding/router files to symlinks
2025-11-29 20:49:26 +00:00
Scott Helvick
b36c116166
add Cohere models to Azure providers
...
Command models:
- Command A
- Command R (08-2024)
- Command R+ (08-2024)
Embed models:
- Embed v3 English
- Embed v3 Multilingual
- Embed v4 (multimodal)
2025-11-29 20:47:49 +00:00
Scott Helvick
78b299bc77
add model-router pricing ($0.14/1M input tokens)
2025-11-29 20:42:40 +00:00
Aiden Cline
c3e0370e99
Merge pull request #450 from shelvick/add-azure-deepseek-models
...
add DeepSeek models to Azure providers
2025-11-29 12:14:19 -08:00
Scott Helvick
0a27b3ee73
add DeepSeek models to Azure providers
...
Adds 4 DeepSeek models to both Azure and Azure Cognitive Services:
- DeepSeek-R1
- DeepSeek-R1-0528
- DeepSeek-V3-0324
- DeepSeek-V3.1
2025-11-29 20:02:41 +00:00
Scott Helvick
d6a4db8bf1
add embedding models and model-router to azure providers
2025-11-29 19:30:08 +00:00
Aiden Cline
826a781aa9
add claude opus 4.5 to google vertex
2025-11-29 11:29:01 -06:00
Aiden Cline
1bd182a227
Merge pull request #448 from yug49/add-io-intelligence-provider
...
fix: resolve "Bad Request" issue when using IO.NET provider
2025-11-29 09:24:55 -08:00
yug49
a4bdad02d5
refactor: rename provider folder from io-intelligence to io-net
2025-11-29 21:09:46 +05:30
Yug Agarwal
5fe017495f
Merge branch 'sst:dev' into add-io-intelligence-provider
2025-11-29 20:21:01 +05:30
yug49
8966ec1760
fix: resolve 'bad request' error when using IO.NET models
2025-11-29 20:18:27 +05:30
Aiden Cline
f4a4b89d52
Merge pull request #444 from InduwaraSMPN/dev
...
fix(models): correct model name in gpt-5 configuration
2025-11-28 13:40:02 -08:00
Aiden Cline
9311540505
Merge pull request #446 from no1wudi/dev
...
feat: add minimax-cn provider with China region endpoints
2025-11-28 08:20:46 -08:00
Huang Qi
a056753dfe
style: make MiniMax logos square with centered content
...
Update logo dimensions from 35x28 to 35x35 for both MiniMax and
MiniMax-cn providers to create square logos with centered original content.
Changes:
- Changed width="35" height="28" to width="35" height="35"
- Updated viewBox from "0 0 35 28" to "0 0 35 35"
- Wrapped path in <g transform="translate(0, 3.5)> to vertically center content
This ensures visual consistency across provider logos while maintaining
the original logo appearance within the new square dimensions.
2025-11-29 00:04:24 +08:00
Huang Qi
b6ed422e36
chore: fix MiniMax capitalization consistency
...
Correct the capitalization of Minimax to MiniMax across all provider and model configuration files to maintain consistent branding.
* Updated provider.toml files for both minimax and minimax-cn
* Updated MiniMax-M2 model configuration files
* Updated synthetic model reference for hf:MiniMaxAI/MiniMax-M2
2025-11-28 18:32:41 +08:00
Huang Qi
49b4d5f489
feat: add minimax-cn provider with China region endpoints
...
Create new minimax-cn provider supporting Chinese region with
updated API and documentation URLs, following naming convention
for -cn providers.
Changes:
- Created provider directory structure
- Updated API URL: api.minimaxi.com (vs api.minimax.io)
- Updated docs URL: platform.minimaxi.com (vs platform.minimax.io)
- Set provider name: 'Minimax (China)' (matches -cn convention)
- Linked existing MiniMax-M2 model to avoid duplication
- Copied provider logo for consistency
Files added:
- providers/minimax-cn/provider.toml
- providers/minimax-cn/logo.svg
- providers/minimax-cn/models/MiniMax-M2.toml (symbolic link)
This enables Chinese region access while maintaining
configuration consistency with the main minimax provider.
2025-11-28 18:14:42 +08:00
Jay V
48358b91b7
Update TogetherAI logo to use currentColor for dynamic theming
2025-11-27 19:45:54 -05:00
Jay V
772b9a19b5
Update IO Intelligence logo to use currentColor for dynamic theming
2025-11-27 19:44:25 -05:00
Jay V
f0de2acb12
Update Cohere logo to use currentColor for dynamic theming
2025-11-27 19:43:48 -05:00
Frank
911de6a5be
update zen models
2025-11-27 09:58:30 -05:00
Frank
efbe043093
Merge pull request #443 from mdrxy/mdrxy/add-opus-4.5-alias
...
Add missing Opus 4.5 ID entry
2025-11-27 09:26:46 -05:00
InduwaraSMPN
9c49209afc
fix(models): correct model name in gpt-5 configuration
2025-11-27 14:01:20 +05:30
Mason Daugherty
876ff875af
Add missing Opus 4.5 alias entry
2025-11-27 00:21:32 -05:00
Aiden Cline
37254145ef
Merge pull request #441 from InduwaraSMPN/dev
...
feat(providers): add agentrouter provider files and model configs
2025-11-26 20:43:43 -08:00
InduwaraSMPN
fa52c7c431
style: add trailing newline to agentrouter logo and model config files
2025-11-27 09:10:21 +05:30
InduwaraSMPN
4f701f3ba5
feat(providers): add agentrouter provider files and model configs
2025-11-27 09:07:15 +05:30
Aiden Cline
f24a719ec7
Merge pull request #432 from yug49/add-io-intelligence-provider
...
Add IO Intelligence (io.net) provider with 17 models
2025-11-26 16:38:55 -08:00
Aiden Cline
3671b16d97
Change logo.svg fill color to currentColor
2025-11-26 18:38:00 -06:00
Frank
3634c492f5
update zen models
2025-11-26 14:01:52 -05:00
Aiden Cline
03aa3bdfee
Merge pull request #440 from markjaquith/fix/remove-non-global-bedrock-opus-4.5--PR
...
fix: remove non-global prefixed amazon-bedrock opus 4.5 model
2025-11-26 09:26:22 -08:00
Mark Jaquith
50db5cc1c4
fix: remove non-global prefixed amazon-bedrock opus 4.5 model
...
Opus 4.5 is currently ONLY available via global inference and requires
the global prefix.
https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-support.html
2025-11-26 12:17:28 -05:00
Aiden Cline
aa43b2a47b
Merge pull request #436 from codegrandpa/dev
...
add Bailing in provider options
2025-11-26 08:48:21 -08:00
Aiden Cline
6ff4f5de06
Merge pull request #437 from requestyai/feat/requesty-models
...
requesty: opus 4.5 + gemini 3
2025-11-26 08:00:25 -08:00
Aiden Cline
654b0bfc07
Merge pull request #438 from gapeleon/dev
...
fix: correct input types for qwen3-omni-30b-a3b-captioner
2025-11-26 07:59:30 -08:00
Aiden Cline
c9867f10b9
Merge pull request #439 from badlogic/fix-claude-opus-4-5-cache-pricing
...
Fix Claude Opus 4.5 cache pricing
2025-11-26 07:57:56 -08:00
Mario Zechner
b195943be1
Fix Claude Opus 4.5 cache pricing
...
The cache pricing was 3x too high:
- cache_read should be sh.50/MTok (was .50/MTok)
- cache_write should be .25/MTok (was 8.75/MTok)
Source: https://www.anthropic.com/pricing#anthropic-api
2025-11-26 16:32:26 +01:00
Gapeleon
5544c44b3e
fix: correct input types for qwen3-omni-30b-a3b-captioner
...
The model was listed as accepting audio+text inputs
But actually supports audio-only.
Updated the model configuration to reflect the correct input types.
2025-11-26 23:09:43 +11:00
谨谕
7234fb989f
update logo
2025-11-26 17:58:45 +08:00
John Costa
f43c1aefe1
requesty: opus 4.5 + gemini 3
2025-11-26 08:19:51 +00:00
Aiden Cline
e9e3edb880
Merge pull request #435 from guillaumeboehm/feat/openrouter_opus_4.5
...
Add openrouter Opus 4.5
2025-11-25 23:10:48 -08:00
谨谕
eb565e4b48
Merge remote-tracking branch 'origin/dev' into dev
2025-11-26 15:03:23 +08:00
谨谕
78de69502e
change logo
2025-11-26 15:03:10 +08:00
Guillaume BOEHM
7c4a238877
feat: Add openrouter Opus 4.5
2025-11-26 07:57:19 +01:00
codegrandpa
323b1635cb
Merge branch 'sst:dev' into dev
2025-11-26 14:42:47 +08:00
谨谕
b626d5c7cf
Merge remote-tracking branch 'origin/dev' into dev
2025-11-26 14:38:25 +08:00
谨谕
ab41c7dcf0
add log
2025-11-26 14:28:51 +08:00
Aiden Cline
038850ae84
Merge pull request #434 from crankycoder/add-qwen3-coder-flash
...
feat: Add Qwen3 Coder Flash model to OpenRouter provider
2025-11-25 20:07:51 -08:00
codegrandpa
35541e89e3
Merge branch 'sst:dev' into dev
2025-11-26 10:39:06 +08:00
谨谕
e596f72954
Add new provider: bailing
2025-11-26 10:32:57 +08:00
yug49
edbd13d4dc
Update IO.NET logo
2025-11-26 07:31:14 +05:30
Aiden Cline
e7d02c0b1e
Merge pull request #433 from cevr/dev
...
Global Amazon Bedrock Opus 4.5
2025-11-25 17:21:02 -08:00
yug49
d8223a85a1
Add IO Intelligence provider with 17 models
...
- Add OpenAI-compatible provider configuration
- Include 17 production-ready AI models:
* 3 reasoning models (DeepSeek R1, Kimi K2 Thinking, Qwen 3 235B)
* 4 vision models (Llama 3.2 90B, Llama 4 Maverick, Qwen 2.5 VL, Mistral Large)
* Flagship model: Llama 4 Maverick with 430K context window
* Specialized coding models: Qwen 3 Coder 480B, Devstral Small
- All models include complete pricing, context limits, and capabilities
- Verified against live API endpoint
- Includes cache pricing for prompt caching support
2025-11-26 05:38:37 +05:30
Aiden Cline
1d4e501333
Merge pull request #429 from InduwaraSMPN/dev
...
Add siliconflow provider
2025-11-25 14:08:22 -08:00
InduwaraSMPN
1c47dbd2a4
refactor(svg): update SiliconFlow logo to use viewBox and currentColor
2025-11-25 23:20:14 +05:30
Aiden Cline
09ac80dc03
Merge pull request #430 from wantpinow/add-opus-4.5-vercel
...
Add Claude 4.5 Opus to Vercel provider
2025-11-25 09:02:41 -08:00
cevr
6ffbcc19ec
fix
2025-11-25 11:54:38 -05:00
cevr
a050c466df
add global
2025-11-25 08:06:10 -05:00
Patrick Frenett
8969051007
feat: add opus to vercel
2025-11-25 10:51:03 +00:00
InduwaraSMPN
851c76579d
Add Qwen/Qwen2.5-72B-Instruct model configuration
2025-11-25 14:12:14 +05:30
InduwaraSMPN
c15acd175d
Add siliconflow provider assets (logo + models)
...
Add model configuration files for multiple models (e.g., BAIDU ERNIE-4.5-300B-A47B, DeepSeek R1 Distill Qwen 14B/32B, ByteDance Seed-OSS 36B, Tencent Hunyuan A13B/MT-7B, stepfun-ai/step3) with metadata (release dates, cost, limits, modalities) and the provider logo.svg asset.
2025-11-25 14:00:45 +05:30
Frank
3d2e4cebc3
update zen models
2025-11-24 23:18:29 -05:00
Aiden Cline
7ad32ff36a
Merge pull request #428 from kavhnr/fix/anthropic-opus-latest-flag
...
fix(anthropic): add (latest) flag and correct last_updated for Opus 4.5
2025-11-24 15:50:10 -08:00
kavhnr
a1a807ebf2
fix(anthropic): corrected the name and last_updated fields in the claude-opus-4-5.toml file
2025-11-24 16:44:46 -07:00
Frank
3af5ce08ae
add input token limit
2025-11-24 18:29:34 -05:00
Aiden Cline
4866af45db
Merge pull request #427 from cau1k/feat/azure-opus-4-5
...
Add Claude Opus 4.5 to Azure providers
2025-11-24 15:14:52 -08:00
cau1k
202c2c32fc
Add Claude Opus 4.5 to Azure providers
2025-11-24 18:12:50 -05:00
Aiden Cline
923f032621
Merge pull request #426 from djmaze/patch-3
...
Correct output cost for kimi-k2-thinking on Fireworks.ai
2025-11-24 14:48:49 -08:00
Martin Honermeyer
6b1ec0d344
Correct output cost for kimi-k2-thinking on Fireworks.ai
...
It has been corrected on their info page: https://app.fireworks.ai/models/fireworks/kimi-k2-thinking
2025-11-24 23:47:29 +01:00
Aiden Cline
cbaccdc0d0
Merge pull request #425 from markjaquith/feat/amazon-bedrock/opus-4.5--PR
...
add claude opus 4.5 to amazon bedrock provider
2025-11-24 14:26:08 -08:00
Mark Jaquith
1ea18acbda
add claude opus 4.5 to amazon bedrock provider
2025-11-24 17:14:09 -05:00
Aiden Cline
2c1689b2ab
use openrouter sdk for the models that need it
2025-11-24 15:50:31 -06:00
Aiden Cline
5e4933ea4a
fix: copilot opus 4.5
2025-11-24 15:22:36 -06:00
Frank
87e4f0506a
Update zen models
2025-11-24 15:23:55 -05:00
Aiden Cline
f68ad8e452
Merge pull request #424 from shkumbinhasani/add-opus-4-5-copilot
...
Add Claude Opus 4.5 to GitHub Copilot provider
2025-11-24 12:15:38 -08:00
opencode-agent[bot]
ed685fb812
Updated limits: 128k context, 16k output
...
Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com >
2025-11-24 20:04:03 +00:00
shkumbinhasani
dfcd8d9b6e
add claude-opus-4-5 to github-copilot provider
2025-11-24 20:42:33 +01:00
Aiden Cline
5e41716f12
add opus 4.5
2025-11-24 13:15:58 -06:00
fhennerkes
d84c0950ad
poe: update 11/24/25
2025-11-24 11:07:39 -08:00
fhennerkes
b40004d3e5
Merge branch 'sst:dev' into poe-pricing-sync
2025-11-24 10:36:58 -08:00
Frank
06c3d9ff71
update zen models
2025-11-24 11:58:16 -05:00
Victor Ng
6c4c957945
feat: Add Qwen3 Coder Flash model to OpenRouter provider
2025-11-24 08:36:21 -05:00
Aiden Cline
d845c921e9
Merge pull request #423 from sebastiand-cerebras/cerebras-models-update-251123
...
chore: remove deprecated qwen-3-coder-480b model
2025-11-23 18:00:50 -08:00
Seb Duerr
073001d5b7
remove deprecated qwen-3-coder-480b model
2025-11-23 16:55:01 -08:00
Frank
c8162a6f67
update zen models
2025-11-23 17:50:07 -05:00
Aiden Cline
b4120dacfd
Merge pull request #422 from fifthfrankie/update-ollama-cloud
...
fix: update ollama-cloud model naming convention with cloud suffix
2025-11-23 14:19:17 -08:00
Frankie Seabrook
99791a4cae
Update ollama-cloud model naming convention with cloud suffix
2025-11-23 22:06:17 +00:00
Aiden Cline
b461476ca3
Merge pull request #421 from djmaze/patch-2
...
Add kimi-k2-thinking model to Fireworks.ai provider
2025-11-23 12:59:27 -08:00
djmaze
edd46d7718
Add kimi-k2-thinking model to Fireworks.ai provider
...
Source: https://app.fireworks.ai/models/fireworks/kimi-k2-thinking
2025-11-23 21:56:27 +01:00
Aiden Cline
66ef0ed411
Merge pull request #420 from fifthfrankie/fix-invalid-dates
...
fix: correct invalid dates
2025-11-23 12:22:38 -08:00
Frankie Seabrook
409556596b
fix: correct invalid dates
2025-11-23 20:15:15 +00:00
Aiden Cline
a5354243e6
Merge pull request #419 from fifthfrankie/add-ollama-cloud
...
Add ollama-cloud provider
2025-11-22 09:04:45 -08:00
Frankie Seabrook
b3c3eeed66
Add remaining Ollama Cloud models
2025-11-22 14:48:40 +00:00
Frankie Seabrook
2b86b91c85
Add ollama-cloud provider with GPT-OSS, Qwen3 Coder, and Qwen-VL models
2025-11-22 14:24:52 +00:00
github-actions
38088350d0
chore: sync Poe pricing
2025-11-22 02:59:48 +00:00
Aiden Cline
d8af587642
Merge pull request #418 from yharaskrik/jaybell/fix-command-a-reasoning-toml-file-name
...
fix(cohere): remove space missed in file name
2025-11-21 16:21:16 -08:00
jaybell
107258833a
fix(cohere): remove space missed in file name
2025-11-21 16:20:13 -08:00
Aiden Cline
32184a0b3e
Merge pull request #415 from yharaskrik/jaybell/fix-output-tokens-for-cohere-command-a
...
fix(cohere): switch output tokens for a and a reasoning
2025-11-21 16:14:54 -08:00
jaybell
94802d0abf
fix(cohere): switch output tokens for a and a reasoning
2025-11-21 16:12:25 -08:00
Frank
9729e841b1
Update zen models
2025-11-21 15:49:24 -05:00
Aiden Cline
178c0dd5f3
Merge pull request #414 from yharaskrik/jaybell/add-cohere-models
...
feat(cohere): add cohere models
2025-11-21 12:27:09 -08:00
jaybell
f0d721e83d
fix: strip colors of cohere svg
2025-11-21 11:55:19 -08:00
jaybell
87b695b30c
feat(cohere): add cohere models
2025-11-21 11:34:09 -08:00
Aiden Cline
416ca63afd
Merge pull request #410 from cau1k/fix/foundry-ai-sdk-anthropic
...
Fixes Azure/Azure Cognitive Services to use @ai-sdk/anthropic
2025-11-21 11:03:32 -08:00
Aiden Cline
b69d548c3c
Merge pull request #413 from DanielSLew/add-gpt-oss-safeguard-20b
...
feat: add OpenRouter GPT OSS Safeguard 20B model
2025-11-21 08:22:16 -08:00
Daniel Lew
9d7c0401a4
feat: add OpenRouter GPT OSS Safeguard 20B model
...
Add support for OpenAI's GPT OSS Safeguard 20B model via OpenRouter. This is a safety reasoning model optimized for content classification, LLM filtering, and trust & safety labeling tasks.
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com >
2025-11-21 10:52:26 -05:00
Aiden Cline
184cb483a0
Merge pull request #412 from ariane-emory/chore/bury-sherlock
...
chore: remove dead 'Sherlock'cloaked OR models
2025-11-20 21:43:02 -08:00
Ariane Emory
c0cc5635b6
chore: the cloaked models Sherlock Dash Alpha and Sherlock Think Alpha models on OpenRouter are no longer available, remove them.
2025-11-21 00:12:30 -05:00
Aiden Cline
9fbba7ab27
Merge pull request #411 from InduwaraSMPN/dev
...
Fix release and last updated dates in GLM-4.6.toml
2025-11-20 19:18:24 -08:00
github-actions
660a648755
chore: sync Poe pricing
2025-11-21 03:06:33 +00:00
S.M. Pasindu Nadun Induwara
1c32fc3cc4
Fix release and last updated dates in GLM-4.6.toml
2025-11-21 08:20:29 +05:30
cau1k
1acf083ef5
fix: @ai-sdk/anthropic
2025-11-20 19:21:29 -05:00
Aiden Cline
69526507d8
Revert "tweak: make zai-coding plan use anthropic endpoint"
...
This reverts commit f41d957b75 .
2025-11-20 14:17:56 -06:00
Aiden Cline
3a6da3e379
Revert "fix: typo"
...
This reverts commit 400c7b1f03 .
2025-11-20 14:17:54 -06:00
Aiden Cline
400c7b1f03
fix: typo
2025-11-20 13:49:08 -06:00
Aiden Cline
f41d957b75
tweak: make zai-coding plan use anthropic endpoint
2025-11-20 13:46:49 -06:00
Aiden Cline
0ca213481f
Merge pull request #374 from fhennerkes/dev
...
Add Poe.com as provider
2025-11-20 11:01:10 -08:00
Aiden Cline
bb9cb8ff78
fix: hiphen xai models
2025-11-20 10:05:25 -06:00
github-actions
243736847c
chore: sync Poe pricing
2025-11-20 03:05:25 +00:00
Aiden Cline
5389818cb7
Merge pull request #409 from cau1k/fix/azure-anthropic
...
Fixes @anthropic-ai/foundry-sdk providers for azure claude models
2025-11-19 18:19:55 -08:00
fhennerkes
f99734c4a0
Poe: remove models without tool support
2025-11-19 18:11:39 -08:00
fhennerkes
e76beef925
Merge poe-pricing-sync into dev
2025-11-19 18:08:58 -08:00
fhennerkes
ca9770f550
Merge branch 'sst:dev' into dev
2025-11-19 18:04:42 -08:00
fhennerkes
0a6a797332
Merge branch 'sst:dev' into poe-pricing-sync
2025-11-19 18:04:23 -08:00
cau1k
8f6f2847f3
fix: add @anthropic-ai/foundry-sdk providers to azure claude models
2025-11-19 20:54:11 -05:00
Frank
6b7f85410f
Update Zen models
2025-11-19 20:46:01 -05:00
Aiden Cline
de0b10f9e8
Merge pull request #408 from shariqriazz/add-xai-grok-4.1-fast-models
...
Add grok-4.1-fast models to xAI provider
2025-11-19 17:32:27 -08:00
Shariq Riaz
166622d802
Add grok-4.1-fast models to xAI provider
2025-11-20 06:29:17 +05:00
Aiden Cline
2228b82414
Merge pull request #407 from shariqriazz/add-grok-4.1-fast-model
...
Add grok-4.1-fast model
2025-11-19 17:25:31 -08:00
Shariq Riaz
6a3977b808
Add grok-4.1-fast model - Free for 2 weeks then prices apply
2025-11-20 06:21:32 +05:00
Aiden Cline
0c74df28c1
Merge pull request #406 from ariane-emory/chore/remove-dead-or-models
...
chore: remove dead cloaked models from the OpenRouter provider.
2025-11-19 16:55:41 -08:00
Ariane Emory
ce7986f7f5
tidy: save Opencode users some unnecessary keystrokes by removing the obsolete cloaked models from the OpenRouter provider to so that its section of the list doesn't become a graveyard of dead models.
2025-11-19 19:42:07 -05:00
fhennerkes
388d06110a
Merge branch 'sst:dev' into poe-pricing-sync
2025-11-19 16:38:44 -08:00
fhennerkes
7b951012a6
poe: sonic 3, Gemini 3, qwen3
2025-11-19 16:38:09 -08:00
Aiden Cline
3c5c66b366
Merge pull request #405 from cau1k/feat/azure-cs-anthropic-support
...
adds claude models to azure and azure cognitive services
2025-11-19 14:23:25 -08:00
cau1k
357fa48559
feat: add claude models to azure and symlinks to azure cognitive services
2025-11-19 16:57:51 -05:00
Aiden Cline
8c316ca33e
Merge pull request #403 from wantpinow/add-gemini-3-pro-preview
...
Add Google Gemini 3 Pro Preview model to Vercel provider
2025-11-19 09:32:27 -08:00
Patrick Frenett
d0c998e4b9
Add Google Gemini 3 Pro Preview model to Vercel provider
2025-11-19 17:22:00 +00:00
Aiden Cline
7412c88501
Merge pull request #401 from akakenle/add-aihubmix-provider
...
Updated the aihubmix provider model, added Gemini 3 and GPT 5.1
2025-11-19 07:38:05 -08:00
Aiden Cline
fe8fcaf53a
Merge pull request #402 from Atomzwieback/add-openrouter-gemini-3-pro-preview
...
Add Google Gemini 3 Pro Preview for OpenRouter
2025-11-19 07:36:31 -08:00
Atomzwieback
1d2a99a313
Add Google Gemini 3 Pro Preview for OpenRouter
...
Add google/gemini-3-pro-preview model to OpenRouter provider with specifications:
- Input: $2/M tokens, Output: $12/M tokens
- Context window: 1,050,000 tokens
- Max output: 66,000 tokens
- Supports reasoning, tool calling, and multimodal inputs (text, image, audio, video, pdf)
- Knowledge cutoff: January 2025
- Released: November 18, 2025
2025-11-19 15:46:36 +01:00
akakenle
4a055a8bbf
Create gemini-3-pro-preview.toml
2025-11-19 17:27:35 +08:00
akakenle
2702bab5a7
add new model Gemini3、gpt5.1
2025-11-19 17:27:28 +08:00
github-actions
2b85c75b3b
chore: sync Poe pricing
2025-11-19 03:07:25 +00:00
Frank
3de62ded10
update zen models
2025-11-18 14:45:09 -05:00
Aiden Cline
217070ed90
fix: copilot gemini
2025-11-18 13:42:50 -06:00
Frank
e7c089158d
Update zen models
2025-11-18 14:42:29 -05:00
Aiden Cline
15ed8c0b1a
Merge pull request #400 from iljod/dev
...
Add Gemini 3 Pro Preview to GitHub Copilot provider
2025-11-18 10:43:05 -08:00
iljod
8e1c4db1a5
Add Gemini 3 Pro Preview model for copilot
2025-11-18 19:27:21 +01:00
ai13f
e2e6876174
Add gemini 3 pro preview ( #399 )
2025-11-18 12:19:35 -05:00
Aiden Cline
e8d76a1018
Merge pull request #398 from TylerBarnes/add-gemini-3-pro-preview
...
Add Gemini 3 Pro Preview model
2025-11-18 08:59:37 -08:00
Tyler Barnes
8754585b75
Merge origin/dev into add-gemini-3-pro-preview
...
Resolved conflict in gemini-3-pro-preview.toml by keeping our more accurate version:
- Correct release date: 2025-11-18 (not 2025-01-01)
- Correct context window: 1M tokens (not 200k)
- Correct output limit: 64k tokens (not 65.5k)
- Includes context_over_200k pricing tier from official docs
2025-11-18 08:47:14 -08:00
Tyler Barnes
0c449f8f96
Add Gemini 3 Pro Preview model
...
- Model ID: gemini-3-pro-preview
- 1M token context window, 64k output
- Native multimodal support (text, image, video, audio, pdf)
- Reasoning capabilities with thinking levels
- Pricing: $2/$12 per 1M tokens (<=200k), $4/$18 (>200k)
- Knowledge cutoff: January 2025
2025-11-18 08:37:03 -08:00
Dax Raad
1ffae7c905
add: Gemini 3 Pro Preview model from Google
2025-11-18 11:33:03 -05:00
opencode-agent[bot]
5f101d1644
Added GPT-5 Pro to Azure Cognitive Services
...
Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com >
2025-11-18 05:54:49 +00:00
Aiden Cline
0cb3e3498b
fix: minimax api
2025-11-17 10:32:45 -06:00
Aiden Cline
b99f043b71
Merge pull request #394 from mlazuardy/update-deepseek
...
Update DeepSeek model costs and last_updated
2025-11-17 08:05:41 -08:00
mlazuardy
0a345c9fd7
Update DeepSeek model costs and last_updated
2025-11-17 22:53:39 +07:00
Aiden Cline
38e6bd10e0
update minimax
2025-11-17 01:15:59 -06:00
Aiden Cline
6300eccf7d
Merge pull request #393 from PanAchy/feature/add-azure-cognitive-services-support
...
add support for azure cognitive services provider
2025-11-16 19:52:15 -08:00
github-actions
698acde9d8
chore: sync Poe pricing
2025-11-17 03:11:30 +00:00
Youssef Achy
5fc6a44227
added azure cognitive services with symlinks to azure models to minimize maintenance
2025-11-16 20:57:38 -06:00
Aiden Cline
812f6c4af7
Merge pull request #392 from teeverc/5.1-family
...
feat(openai): add 5.1 family
2025-11-16 18:24:14 -08:00
teeverc
596bc43e89
✨ feat: add 5.1 family
2025-11-16 17:38:07 -08:00
Aiden Cline
bf930b2424
fix
2025-11-16 00:34:58 -06:00
Aiden Cline
c9d0bcc1f7
Merge pull request #390 from kcrommett/dev
...
Adding Sherlock Alpha models for Openrouter
2025-11-15 21:41:12 -08:00
Kyle Crommett
bf3c9cc5ee
Merge branch 'dev' of github.com:kcrommett/models.dev into dev
2025-11-15 21:28:01 -08:00
Kyle Crommett
e1e3f813bb
Adding Sherlock Alpha modesl for Openrouter
2025-11-15 21:27:37 -08:00
Aiden Cline
c922eedcc5
fix: copilot limits
2025-11-15 20:39:20 -06:00
Aiden Cline
5c5ffa75de
Merge pull request #389 from Mickael-Roger/update-openrouter-minimax-m2
...
Update the minimax M2 model for openrouter
2025-11-15 10:51:42 -08:00
MickaelRoger
ba7845cd52
Update the minimax M2 model for openrouter: Remove Minimax M2 Free that no longer exists and add the priced Minimax M2
2025-11-15 16:23:11 +01:00
github-actions
995fa74d56
chore: sync Poe pricing
2025-11-15 03:02:22 +00:00
Jay
4f499c750b
Modify logo.svg to use currentColor for fills
...
Updated logo.svg to change fill colors to 'currentColor'.
2025-11-14 19:05:23 -05:00
Frank
c6c2107fa4
experimental tiered cost structure
2025-11-14 18:47:57 -05:00
Aiden Cline
5493d62012
Merge pull request #388 from thebongy/add-azure-gpt-5.1-models
...
Add Azure OpenAI GPT-5.1 series models
2025-11-14 12:44:35 -08:00
Rishit Bansal
92a4c21765
Add Azure OpenAI GPT-5.1 series models
...
Added cost data and model configurations for the GPT-5.1 series announced on November 14, 2025:
- GPT-5.1: Adaptive reasoning model with multimodal support
- GPT-5.1 Chat: Interactive chat with chain-of-thought
- GPT-5.1 Codex: Advanced coding with enhanced tool handling
- GPT-5.1 Codex Mini: Compact, cost-effective coding variant
Pricing based on Standard Global deployment tier from Azure AI Foundry announcement.
2025-11-15 02:08:45 +05:30
Aiden Cline
fe4fbb9e1c
Merge pull request #387 from eliasto/add-ovhcloud-reasoning-models
...
Add OVHcloud AI Endpoints reasoning models
2025-11-14 12:32:21 -08:00
Elias TOURNEUX
3b52def3fc
Add OVHcloud AI Endpoints reasoning models
2025-11-14 15:28:25 -05:00
fhennerkes
e9d0e35f28
Poe: update GPT-5.1 models
2025-11-14 10:17:20 -08:00
Aiden Cline
619dbe3b4c
Merge pull request #372 from wojons/dev
...
Adding Minimax as a provodier with the M2 model
2025-11-14 09:55:50 -08:00
Aiden Cline
0b195f495a
Merge pull request #386 from seaweeduk/add-openrouter-gpt-5.1-models
...
Add GPT 5.1 models to openrouter provider
2025-11-14 07:36:01 -08:00
seaweeduk
0c1f109a24
Fix pricing for gpt-5.1-codex-mini
2025-11-14 14:25:52 +00:00
Aiden Cline
d70936ad17
Merge pull request #385 from xiaojiezj/zenmux_dev
...
add: add new models to ZenMux provider
2025-11-14 04:44:23 -08:00
seaweeduk
756a859e7e
Add OpenRouter GPT-5.1 models (gpt-5.1, gpt-5.1-chat, gpt-5.1-codex, gpt-5.1-codex-mini)
2025-11-14 11:30:27 +00:00
xiaojie.zj
93c1e74e4c
add: add new models to ZenMux provider
2025-11-14 16:05:25 +08:00
Frank
b2e5463e04
Update zen models
2025-11-14 01:00:16 -05:00
Frank
5203a00e16
update zen models
2025-11-13 23:48:06 -05:00
github-actions
dde87d62e2
chore: sync Poe pricing
2025-11-14 03:08:36 +00:00
Aiden Cline
83a038148a
Merge pull request #384 from AleksanderBondar/dev
...
Add GPT 5.1-Codex and GPT 5.1-Codex-mini to github-copilot
2025-11-13 16:08:46 -08:00
Aleksander Bondar
ebfd29c368
Add GPT 5.1-Codex and GPT 5.1-Codex-mini to github-copilot
2025-11-14 00:01:57 +01:00
Aiden Cline
9876997dc1
Merge pull request #383 from AleksanderBondar/dev
...
Add GPT 5.1 for github-copilot
2025-11-13 14:52:48 -08:00
Aleksander Bondar
51e4890bfc
Add GPT 5.1 for github-copilot
2025-11-13 23:50:31 +01:00
Aiden Cline
484adb805e
Merge pull request #381 from matthusby/dev
...
Kimi K2 pricing update for chutes
2025-11-13 14:33:58 -08:00
Matt Husby
6edc462966
Kimi K2 pricing update for chutes
2025-11-13 17:21:35 -05:00
Aiden Cline
9b4c1cbf0f
update deprecated groq models
2025-11-13 16:00:27 -06:00
Aiden Cline
715e45d2cc
Merge pull request #380 from monotykamary/add-gpt-5.1
...
feat(openai): add gpt-5.1 model
2025-11-13 13:52:47 -08:00
Tom X Nguyen
88a5722dfa
feat(openai): add gpt-5.1 model
2025-11-14 04:12:17 +07:00
Aiden Cline
94c28944c8
Merge pull request #379 from redzrush101/add-minimax-m2-and-enable-glm-reasoning
...
Add MiniMax M2 model and enable reasoning for GLM-4.6
2025-11-13 10:03:24 -08:00
yassin
d8add53e7a
Add MiniMax M2 model and enable reasoning for GLM-4.6
2025-11-13 18:54:43 +01:00
fhennerkes
8c2bbb7338
Merge branch 'sst:dev' into poe-pricing-sync
2025-11-13 09:49:02 -08:00
Aiden Cline
d97dcdb2e5
Merge pull request #378 from requestyai/feat/requesty-models
...
requesty: adding new models and fixing names of previous ones
2025-11-13 09:19:17 -08:00
John Costa
36c7bd261e
feat: adding new models
2025-11-13 17:07:40 +00:00
John Costa
e98e716fc7
fix: correcting model names
2025-11-13 17:01:35 +00:00
Frank
7c298c3ae3
update zen model
2025-11-13 11:22:18 -05:00
Aiden Cline
2fbe983cb0
Merge pull request #377 from eliasto/add-ovhcloud-ai-endpoints-provider
...
Update of OVHcloud AI Endpoints prices
2025-11-13 07:36:25 -08:00
Elias TOURNEUX
8b98367b8b
Update of OVHcloud AI Endpoints prices
2025-11-13 09:34:53 -05:00
Aiden Cline
a3875fb69d
Merge pull request #376 from sst/opencode/issue375-20251113055408
...
Updated GitHub Copilot model limits
2025-11-12 22:02:25 -08:00
opencode-agent[bot]
638e7f7809
Updated GitHub Copilot model limits
...
Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com >
2025-11-13 05:56:15 +00:00
fhennerkes
6be5cd4bfd
Update poe/novita/qwen3-max-n.toml
2025-11-12 19:47:59 -08:00
github-actions
1041784528
chore: sync Poe pricing
2025-11-13 03:10:16 +00:00
Alexis Okuwa
402f517655
Refine API validation logic in schema.ts
...
Refactor API validation logic for OpenAI and Anthropic compatibility.
2025-11-12 16:53:14 -08:00
Alexis Okuwa
c5d5eabcbb
Refactor Provider validation logic for clarity
2025-11-12 16:39:33 -08:00
fhennerkes
a70972d8ab
Merge branch 'sst:dev' into dev
2025-11-12 11:37:56 -08:00
fhennerkes
627562d5d2
remove update script
2025-11-12 11:24:11 -08:00
fhennerkes
7ab18a4a7b
Merge branch 'poe-pricing-sync' into dev
2025-11-12 11:22:04 -08:00
fhennerkes
6a36627e84
Merge branch 'sst:dev' into poe-pricing-sync
2025-11-12 11:19:30 -08:00
fhennerkes
9c25701d6f
add context_length to update script and add missing new lines
2025-11-12 11:16:00 -08:00
Aiden Cline
29d0799fab
Merge pull request #373 from eliasto/add-ovhcloud-ai-endpoints-provider
...
Add OVHcloud AI Endpoints provider
2025-11-12 10:53:03 -08:00
Elias TOURNEUX
6623724f21
Add OVHcloud AI Endpoints provider
2025-11-12 13:36:04 -05:00
Alexis Okuwa
f6bc9bfbef
Update schema validation for API field requirements
2025-11-12 09:08:06 -08:00
Aiden Cline
8aac965baf
update perplexity npm pacjage
2025-11-12 10:34:24 -06:00
Alexis Okuwa
fe41132d75
Change npm package from openai-compatible to anthropic
2025-11-11 21:05:09 -08:00
Alexis Okuwa
968657ad28
Merge branch 'sst:dev' into dev
2025-11-11 21:03:38 -08:00
Alexis Okuwa
79dd151b3d
Rename minimax-m2.toml to MiniMax-M2.toml
2025-11-11 21:01:03 -08:00
Alexis Okuwa
69c3bbc841
Add logo.svg for minimax provider
2025-11-11 21:00:06 -08:00
Alexis Okuwa
6b70c368c9
Add files via upload
2025-11-11 20:56:59 -08:00
Alexis Okuwa
b323fa280b
Add Minimax-M2 model configuration
2025-11-11 20:56:14 -08:00
Alexis Okuwa
f089d775bf
Update output limit in MiniMax-M2 configuration
2025-11-11 20:32:41 -08:00
Aiden Cline
7da99658b0
add gh copilot raptor mini
2025-11-11 22:20:42 -06:00
Aiden Cline
cd6e6079db
mark copilot sonnet 3.5 as deprecated
2025-11-11 21:57:25 -06:00
Aiden Cline
abc01d0d6e
Merge pull request #370 from teeverc/baseten-kimi-k2-thinking
...
Add Kimi K2 Thinking for Baseten Provider
2025-11-11 19:22:39 -08:00
teeverc
0b8ac4035d
fix knowledge date
2025-11-11 18:49:53 -08:00
teeverc
f5133c98f1
Add Baseten Kimi K2 Thinking model
2025-11-11 18:42:47 -08:00
Alexis Okuwa
511a95c128
Merge branch 'sst:dev' into dev
2025-11-11 18:25:24 -08:00
Alexis Okuwa
6c67cd105c
Create minimax-m2.toml
2025-11-11 10:53:08 -08:00
Alexis Okuwa
2fa751911a
Add Minimax provider configuration file
2025-11-11 10:52:46 -08:00
Aiden Cline
4de4665f66
Merge pull request #368 from DanRioDev/kwaipilot-kat-coder-pro-free
...
Add Kwaipilot Kat Coder Pro (free) model from OpenRouter provider
2025-11-11 09:04:21 -08:00
Aiden Cline
2273498a2d
Merge pull request #367 from nicognaW/update-vercel-minimax-m2-cost
...
Update vercel minimax m2 cost
2025-11-11 08:20:09 -08:00
Dan Rio
70e920cc8c
Add Kwaipilot Kat Coder Pro (free) model to OpenRouter provider
...
- Added kwaipilot/kat-coder-pro:free model configuration
- 256K context window, optimized for agentic coding tasks
- 73.4% SWE-Bench Verified performance
- Free tier model with $0 input/output costs
- Tool-call and temperature parameter support enabled
2025-11-11 12:30:47 -03:00
nk
0c6638c0d5
Update vercel minimax m2 cost
2025-11-11 16:36:11 +08:00
Frank
418b4abe5e
update zen models
2025-11-11 02:11:39 -05:00
fhennerkes
b9da6b5053
add more models, update script
2025-11-10 15:53:28 -08:00
fhennerkes
82e0d996a9
Merge branch 'sst:dev' into poe-pricing-sync
2025-11-10 15:51:10 -08:00
Frank
93d2ef6614
Merge pull request #366 from ccurme/cc/structured_output
...
feat: add structured_output
2025-11-10 14:57:53 -05:00
Frank
f169acedcf
render in web
2025-11-10 14:57:08 -05:00
Frank
8bfcbaf1ed
sync
2025-11-10 14:50:23 -05:00
Chester Curme
80e7846fb0
update google
2025-11-10 14:30:33 -05:00
Chester Curme
c4f212deea
update openai
2025-11-10 14:30:16 -05:00
Chester Curme
029c9a694d
update schema
2025-11-10 14:29:53 -05:00
Aiden Cline
1b4486ad75
fix: missing costs
2025-11-10 00:49:05 -06:00
Aiden Cline
bda672f541
Merge pull request #364 from alexanderbakin/dev
...
add OpenAI models for Deep Infra
2025-11-09 10:56:57 -08:00
Alexander Bakin
2128831a4a
add OpenAI models for Deep Infra
2025-11-09 21:48:14 +03:00
Aiden Cline
5b73efb39a
Merge pull request #361 from wojons/dev
...
bad file name forgot .toml
2025-11-08 14:08:55 -08:00
Alexis Okuwa
ff5ff83de7
bad file name forgot .toml
2025-11-08 17:05:33 -05:00
Aiden Cline
205b2fc0eb
Merge pull request #351 from matthusby/dev
...
update the chutes models per what the api is saying.
2025-11-08 11:50:52 -08:00
Aiden Cline
67b47aecaf
Merge pull request #360 from spmurrayzzz/fix/qwen3-coder-baseten
...
fix(providers): use correct baseten qwen3 coder prefix
2025-11-08 11:34:39 -08:00
Stephen Murray
dbee0a670b
fix(providers): use correct baseten qwen3 coder alias
2025-11-08 14:24:24 -05:00
Matt Husby
add928643c
Update models from the chutes api with context formatted correctly
2025-11-08 14:23:39 -05:00
Aiden Cline
15ed408968
Merge pull request #359 from wojons/patch-8
...
add kimi-k2-thinking for synthetic proivder
2025-11-08 10:42:14 -08:00
Alexis Okuwa
3542942557
add kimi-k2-thinking for synthetic proivder
2025-11-07 22:53:12 -08:00
fhennerkes
2d0c2c0d1d
Merge branch 'sst:dev' into dev
2025-11-07 09:57:09 -08:00
Aiden Cline
d563290c51
Merge pull request #357 from Arindam200/update
...
feat: update Nebius provider to Token Factory endpoints
2025-11-07 07:07:28 -08:00
Arindam Majumder
ff08f1fac9
Merge branch 'sst:dev' into update
2025-11-07 13:01:50 +05:30
Arindam200
400d090acd
feat: update Nebius provider to Token Factory endpoints
...
- Changed provider name from "Nebius AI Studio" to "Nebius Token Factory"
- Updated API and documentation URLs to tokenfactory.nebius.com domain
2025-11-07 13:00:29 +05:30
fhennerkes
8fb299c3a4
Merge prices from poe-pricing-sync
2025-11-06 18:08:46 -08:00
github-actions
425778ef96
chore: sync Poe pricing
2025-11-07 01:57:58 +00:00
fhennerkes
a711cda19e
Testing price update for GPT-5
2025-11-06 17:57:37 -08:00
fhennerkes
f1d8766771
Update naming and pricing update script
2025-11-06 16:55:26 -08:00
fhennerkes
19108aae85
False price change to test workflow
2025-11-06 16:16:24 -08:00
fhennerkes
77ed552ba0
Merge branch 'sst:dev' into poe-pricing-sync
2025-11-06 15:59:01 -08:00
fhennerkes
157f5b500f
Add automated price update for Poe
2025-11-06 15:55:57 -08:00
fhennerkes
45f2315cc1
Merge branch 'sst:dev' into dev
2025-11-06 15:49:44 -08:00
fhennerkes
560b4d19f3
add initial models (xai, openai, anthropic, google)
2025-11-06 15:48:13 -08:00
fhennerkes
9e13c58ee8
update provider Poe
2025-11-06 12:29:38 -08:00
Frank
db75a6d97e
add openrouter/polaris-alpha model
2025-11-06 15:14:22 -05:00
fhennerkes
3f73018e90
add provider: Poe
2025-11-06 11:58:38 -08:00
Aiden Cline
03d92b07d3
Merge pull request #356 from shariqriazz/add-kimi-k2-thinking-models
...
Add Kimi K2 thinking models
2025-11-06 08:41:44 -08:00
Shariq Riaz
0804a75fd9
Add Kimi K2 thinking models to Moonshot AI and OpenRouter
...
- Add kimi-k2-thinking and kimi-k2-thinking-turbo to moonshotai provider
- Add moonshotai/kimi-k2-thinking to openrouter provider
- All models marked as reasoning=true for thinking capabilities
- Set open_weights=true to match other Kimi K2 models
- Context window: 256K (262,144 tokens)
- Max output: 256K (262,144 tokens)
- Knowledge cutoff: 2024-08
- Cache read: $0.15/M tokens for all models
- Pricing: k2-thinking ($0.60 input, $2.50 output), k2-thinking-turbo ($1.15 input, $8 output)
- Released November 6, 2025
2025-11-06 21:33:40 +05:00
Frank
234ba091f2
update zen model
2025-11-04 17:51:08 -05:00
Aiden Cline
e208f35ba5
Merge pull request #352 from ProlowN/venice/zai-org-glm-4.6
...
Added new glm4.6 model to venice
2025-11-04 09:38:21 -06:00
Aiden Cline
d4062d94ab
Merge pull request #353 from ProlowN/venice/update-limit-format
...
chore/updated the limit format for venice models
2025-11-04 09:36:53 -06:00
Aiden Cline
60f6a3e8f2
Merge pull request #354 from nicognaW/dev
...
Add MiniMax M2 model to vercel
2025-11-04 09:35:23 -06:00
nk
2d0aa23319
Add MiniMax M2 model to vercel
2025-11-04 21:04:17 +08:00
Magnus
f22aecb8c8
fix/Updated glm4.6 to use new limit format
2025-11-04 12:35:03 +01:00
Magnus
b7a75e1103
chore/updated the limit format
2025-11-04 12:31:24 +01:00
Magnus
62079d181e
Added new glm4.6 model to venice
2025-11-04 11:23:32 +01:00
Frank
0e56ea3cca
update zen model
2025-11-03 17:39:44 -05:00
Frank
23c7d0b05f
update zen models
2025-11-03 15:03:29 -05:00
Aiden Cline
6f0071fbb3
Merge pull request #348 from wojons/dev
...
Updating Nvidia provider with qwen and nemotron
2025-11-03 10:46:37 -06:00
Frank
3eb1731be6
Update zen models
2025-11-03 11:19:48 -05:00
Aiden Cline
9a05e46d15
Merge pull request #349 from wojons/patch-7
...
Add configuration for nvidia-nemotron-nano-9b-v2
2025-11-02 18:03:41 -06:00
Alexis Okuwa
b60dac5222
Add configuration for nvidia-nemotron-nano-9b-v2
2025-11-02 15:47:12 -08:00
Alexis Okuwa
c8b274a187
Enable reasoning and open weights in Qwen model
2025-11-02 15:42:38 -08:00
Alexis Okuwa
554a9f8b2e
Update Qwen model configuration settings
2025-11-02 15:41:51 -08:00
Alexis Okuwa
da18b361d5
Update NVIDIA Nemotron Nano 9B model details
2025-11-02 15:35:56 -08:00
Aiden Cline
343ee552ca
fix: iflow logo
2025-11-02 11:43:17 -06:00
Aiden Cline
9e172ae125
Merge pull request #346 from shariqriazz/add-iflowcn-provider
...
Add iFlow provider with 17 models
2025-11-02 11:41:45 -06:00
Aiden Cline
26130c13a3
Revert "Updated iFlow logo to use currentColor"
...
This reverts commit 7a47f09825 .
2025-11-02 11:39:48 -06:00
opencode-agent[bot]
7a47f09825
Updated iFlow logo to use currentColor
...
Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com >
2025-11-02 17:35:58 +00:00
Shariq Riaz
eb6c2f2cc4
Add iFlow logo
...
- Added official iFlow logo SVG with gradient design
- Square format with transparent background
- Purple gradient from #5C5CFF to #AE5CFF
2025-11-02 21:04:10 +05:00
Aiden Cline
0e2c58b789
Merge pull request #345 from shariqriazz/add-minimax-m2-nvidia-provider
...
Add MiniMax-M2 model to NVIDIA provider
2025-11-02 09:53:49 -06:00
Shariq Riaz
059e6c9602
Add iFlow provider with 17 models
...
- Created iflowcn provider with OpenAI-compatible API
- Added TStars-2.0 (Taobao Star Language Model)
- Added Qwen3 series: Coder-Plus, Coder, Max, VL-Plus, Max-Preview, 32B, 235B variants
- Added Kimi-K2 and K2-Instruct-0905 models
- Added DeepSeek series: V3.2-Exp, V3.1-Terminus, R1, V3-671B
- Added GLM-4.6 model
- All models free with various context windows (128K-256K)
- Based on https://platform.iflow.cn/en/docs
2025-11-02 18:05:45 +05:00
Shariq Riaz
d6b4ee62f9
Add MiniMax-M2 model to NVIDIA provider
...
- Created minimax-m2.toml with proper configuration
- 128K context window, 16K output tokens
- Supports reasoning, tool calling, and temperature control
- Open weights model with MIT license
- Based on NVIDIA NIM documentation
2025-11-02 18:00:22 +05:00
Aiden Cline
4e76627126
Merge pull request #344 from djmaze/patch-1
...
Add minimax-m2 model to Fireworks
2025-11-01 17:15:25 -05:00
Martin Honermeyer
98e7c06049
Add minimax-m2 model to Fireworks
2025-11-01 17:37:42 +01:00
Aiden Cline
83792428cc
Merge pull request #341 from matthusby/rename-minimax-m2-on-chutes
...
Rename the folder to match what is on the card
2025-10-31 17:08:37 -05:00
Matt Husby
b8b6ac4c2a
Rename the folder to match what is on the card
2025-10-31 16:59:55 -05:00
Aiden Cline
91a03818a6
Merge pull request #339 from EasyDevv/edit
...
Update chutes provider models
2025-10-31 10:39:56 -05:00
Aiden Cline
6dc1c28049
Merge pull request #340 from sst/mark-gh-models-deprecated
...
certain copilot models were deprecated recently, marking them as such
2025-10-31 10:39:35 -05:00
Aiden Cline
8892829ba7
certain copilot models were deprecated recently, marking them as such
2025-10-31 10:38:05 -05:00
Frank
fdc2db4805
update zen logo
2025-10-31 09:28:14 -04:00
Aiden Cline
b97ee92330
Merge pull request #338 from kevint-cerebras/add-cerebras-zai-glm-4-6
...
Add cerebras zai glm 4 6
2025-10-30 15:38:28 -05:00
Aiden Cline
f2a45de6bb
Merge pull request #272 from yukukotani/rename-vertex-anthropic
...
Rename google-vertex-anthropic to avoid conflict with google-vertex
2025-10-30 14:46:50 -05:00
EasyDev
33b2f62454
add: minimaxai and updated zai-org models to chutes provider
...
- Add minimaxai provider directory with models
- Add GLM-4.5 and GLM-4.6 models to zai-org
2025-10-30 11:13:21 +09:00
EasyDev
7e67c08c03
chore: remove outdated models from chutes provider
...
- Remove Qwen3-30B-A3B-Thinking-2507
- Remove Devstral-Small-2505
- Remove DeepSeek-V3.1-turbo
- Remove Kimi-Dev-72B
- Remove GLM-4.5-turbo
2025-10-30 11:11:40 +09:00
kevint-cerebras
cfe27e858e
update cerebras models: glm 4.6
2025-10-29 13:03:53 -07:00
Aiden Cline
1a9b28e431
fix: logo color
2025-10-29 15:03:17 -05:00
kevint-cerebras
13f5013084
Add zai-glm-4.6 model to Cerebras provider
...
Adds Z.AI GLM-4.6 model hosted by Cerebras with:
- Context window: 128k tokens (131,072)
- Max completion: 40k tokens (40,960)
- Free pricing (0 input/output)
- Text-only modalities
- No prompt caching
2025-10-29 12:58:19 -07:00
Aiden Cline
d644b1526e
Merge pull request #335 from xiaojiezj/zenmux_dev
...
add(providers): add ZenMux provider
2025-10-29 14:33:29 -05:00
Aiden Cline
616172e08c
Merge pull request #337 from gary149/add-minimax-m2
...
Add MiniMax-M2 to Hugging Face
2025-10-29 10:09:51 -05:00
Victor Muštar
fccc07baec
Add MiniMax-M2 to Hugging Face
2025-10-29 15:59:53 +01:00
Aiden Cline
43199134db
Merge pull request #336 from Ilia-TheNetworkFirm/feat/aws-bedrock-qwen
...
Add AWS Bedrock Deepseek v3.1 and Qwen models
2025-10-29 09:52:37 -05:00
opencode-agent[bot]
a8863edde5
Fixed open_weights as required field
...
Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com >
2025-10-29 14:51:51 +00:00
Ilia Okhotnikov
d7d353fff7
Add AWS Bedrock Deepseek v3.1 and Qwen models
2025-10-29 13:39:21 +01:00
Aiden Cline
695ad2e648
Merge pull request #333 from la55u/patch-1
...
fix: remove grok-4-fast-free
2025-10-28 10:28:29 -05:00
xiaojie.zj
2ebec11676
add(provuders): ZenMux
2025-10-28 15:01:39 +08:00
Frank
adf931e21a
update zen models
2025-10-28 00:00:03 -04:00
Aiden Cline
c7a4506895
Merge pull request #334 from mahaat/dev
...
add minimax models to openrouter
2025-10-27 22:50:49 -05:00
adit
343dfdf009
add open weights field
2025-10-28 09:37:36 +07:00
Frank
86138343a8
Change output cost from 1.25 to 5.00
2025-10-27 21:23:58 -04:00
adit
2c0474a591
add minimax models to openrouter
2025-10-28 07:55:36 +07:00
Andras Lassu
a4325dc1e3
Merge pull request #1 from la55u/copilot/revert-last-commit
...
Restore kimi-k2:free.toml model configuration
2025-10-27 22:58:08 +01:00
copilot-swe-agent[bot]
e15bd893d6
Revert deletion of kimi-k2:free.toml
...
Co-authored-by: la55u <30611343+la55u@users.noreply.github.com >
2025-10-27 21:55:52 +00:00
copilot-swe-agent[bot]
6caa1d8625
Initial plan
2025-10-27 21:46:21 +00:00
Andras Lassu
23bfb56ca7
Delete providers/openrouter/models/moonshotai/kimi-k2:free.toml
2025-10-27 22:43:53 +01:00
Andras Lassu
b8367fb8d2
remove grok-4-fast-free
2025-10-27 22:38:10 +01:00
Dax
60d32aa297
Delete providers/opencode/models/code-supernova.toml
2025-10-27 16:29:23 -04:00
Aiden Cline
fce08f9ff1
Merge pull request #332 from Sewer56/minimax-m2
...
Added: MiniMax-M2 from Synthetic.new , update token limits on GLM
2025-10-27 10:04:38 -05:00
Sewer56
0cfd710300
Added: MiniMaxM2 from Synthetic
...
Verified with `https://dev.synthetic.new/docs/openai/models `
The limits- 64k output on self-hosted models, and 196_608 tokens are directly obtained from 1st party source.
2025-10-27 13:23:40 +00:00
Aiden Cline
c67908a3f0
Merge pull request #331 from sutoiku/dev
...
Add `gpt-5-pro` model cards for openai and openrouter providers
2025-10-27 07:12:18 -05:00
Aurelien Ribon
935abd695f
Set proper release dates
2025-10-26 21:10:07 +01:00
Aurelien Ribon
a3af044b76
Add gpt-5-pro model cards for openai and openrouter
2025-10-26 21:08:21 +01:00
Aiden Cline
6aaec4681f
Merge pull request #330 from Yub0/update-scw-models
...
feat(providers): update scaleway models
2025-10-25 16:28:11 -05:00
Valentin LAMBOLEY-DEPOIRE
2e6ea3fe46
feat(providers): update scaleway models
...
Signed-off-by: Valentin LAMBOLEY-DEPOIRE <vlamboley@scaleway.com >
2025-10-25 19:41:48 +02:00
Aiden Cline
1548a725f0
Merge pull request #327 from sst/add-latest
...
anthropic models add (latest)
2025-10-24 01:07:31 -05:00
Aiden Cline
99362b3812
anthropic models add (latest)
2025-10-24 01:06:39 -05:00
Aiden Cline
cbaf3389d7
Merge pull request #326 from cyberofficial/vultr
...
Fix: Adjust Vultr Model Context and Output Limits Based on Empirical Testing
2025-10-23 17:45:44 -05:00
Cyber Official
e0dbb542a6
Update context and output limits for Vultr models
...
Adjusted the 'context' and 'output' token limits in TOML configs for deepseek-r1-distill-llama-70b, deepseek-r1-distill-qwen-32b, gpt-oss-120b, kimi-k2-instruct, and qwen2.5-coder-32b-instruct models to reflect new capacity constraints.
2025-10-23 18:13:01 -04:00
Aiden Cline
c4f59629ca
Merge pull request #324 from vytenisstaugaitis/dev
...
fix(ui): use correct variable name for scroll position
2025-10-23 15:53:29 -05:00
Aiden Cline
1fc3f0fe04
add exacto models
2025-10-23 15:51:25 -05:00
Hammad Shami
76e0508747
add helicone models + helicone model generation script
2025-10-23 13:43:27 -07:00
vytenisstaugaitis
f3df9c33b6
fix(ui): use correct variable name for scroll position
2025-10-23 23:20:44 +03:00
Aiden Cline
3222c3fff2
fix: vercel claude 3.5 haiku
2025-10-23 15:14:39 -05:00
Aiden Cline
9c4b2f995d
Merge pull request #322 from ashktn/google-vertex-anthropic-claude-4-5
...
(fix) - use correct vertex model id for claude 4.5 models
2025-10-22 22:48:55 -05:00
ashktn
7f2199fa73
(fix) - use correct vertex model id for claude 4.5 models
2025-10-22 23:40:42 -04:00
Aiden Cline
bdfa9b20e3
fix: color
2025-10-22 15:39:51 -05:00
Aiden Cline
a8b3e0881e
Merge pull request #321 from cyberofficial/vultr
...
Add Vultr
2025-10-22 15:32:33 -05:00
Cyber Official
13d6d49ce0
Add open_weights flag to Vultr model configs
...
Added the open_weights property for deepseek-r1-distill-llama-70b, deepseek-r1-distill-qwen-32b, gpt-oss-120b, kimi-k2-instruct, and qwen2.5-coder-32b-instruct models. Also updated Vultr logo.svg viewBox from 36.09 to 42 to be square
2025-10-22 16:17:32 -04:00
Aiden Cline
22daff09ac
Merge pull request #312 from ashktn/google-vertex-anthropic-claude-4-5
...
Add claude-haiku-4.5@20251001 and claude-sonnet-4-5@20250929 to google-vertex-anthropic
2025-10-22 09:46:01 -05:00
Aiden Cline
bebe28eb3d
Merge pull request #318 from obostjancic/obostjancic/feat/embedding-models
...
Add Embedding Models
2025-10-22 09:44:23 -05:00
Cyber Official
0d4a3dd8c0
Adjust context limit in kimi-k2-instruct.toml
2025-10-22 08:49:39 -04:00
Cyber Official
5b355175ae
Adjust context limit in qwen2.5-coder model
2025-10-22 08:49:14 -04:00
Cyber Official
ea6adce1e9
Adjust context limit in gpt-oss-120b model config
2025-10-22 08:48:35 -04:00
Cyber Official
b341b1cecf
Update output limit to match context size
2025-10-22 06:10:18 -04:00
Cyber Official
b49f607030
Update Vultr model metadata with true values
2025-10-22 03:39:28 -04:00
Cyber Official
76e1ef2697
Add Vultr provider with 5 models, pricing, and logo
2025-10-22 03:19:23 -04:00
Ogi
ff4bd7daa3
add output costs
2025-10-22 09:11:47 +02:00
Frank
29938a2c41
Merge pull request #320 from akakenle/add-aihubmix-provider
...
Provider AIhubmix Information Optimization
2025-10-21 12:18:31 -04:00
Frank
e98a8e2a5e
Update logo.svg with new SVG content
2025-10-21 12:17:56 -04:00
akakenle
fe740b7b03
Change nmp to AIhubmix in the package @aihubmix/ai-sdk-provider within aisdk
2025-10-21 23:01:55 +08:00
Ogi
1c8e970188
fix validation
2025-10-21 10:08:13 +02:00
Aiden Cline
bbf0e6f634
Merge pull request #317 from Yub0/add-scaleway-provider
...
feat(providers): add scaleway
2025-10-20 10:21:06 -05:00
Ogi
b1227d7e51
Add Embedding Models
2025-10-20 14:38:54 +02:00
Valentin LAMBOLEY-DEPOIRE
da32d0de05
feat(providers): add scaleway
...
Signed-off-by: Valentin LAMBOLEY-DEPOIRE <vlamboley@scaleway.com >
2025-10-20 13:32:45 +02:00
akakenle
420f163541
Merge branch 'add-aihubmix-provider' of https://github.com/akakenle/models.dev into add-aihubmix-provider
2025-10-20 17:58:30 +08:00
akakenle
f5af8930c9
Update logo and optimize information
2025-10-20 17:57:07 +08:00
Frank
54903a77c9
Merge pull request #315 from akakenle/add-aihubmix-provider
...
Add AIHubMix provider with 23 AI models
2025-10-19 22:09:31 -04:00
Frank
753f70a18a
Delete providers/aihubmix/logo.svg
2025-10-19 22:08:48 -04:00
akakenle
19631535be
Add AIHubMix provider with 23 AI models
...
- Add new provider AIHubMix with OpenAI-compatible API
- Include 23 popular AI models:
- Claude series (Sonnet 4.5, Haiku 4.5, Opus 4.1)
- GPT-5 series (GPT-5, GPT-5-Pro, GPT-5-Mini, GPT-5-Nano, GPT-5-Codex)
- GPT-4 series (GPT-4.1, GPT-4.1-Mini, GPT-4.1-Nano, GPT-4o variants)
- o4-mini
- Gemini series (2.5-Pro, 2.5-Flash)
- DeepSeek series (V3.2-Exp, V3.2-Exp-Think)
- Qwen3 series (Coder 480B, 235B Instruct, 235B Thinking)
- GLM-4.6
- Kimi K2-0905
2025-10-18 21:24:33 +08:00
ashktn
4a07e28475
Add claude-haiku-4.5@20251001 and claude-sonnet-4-5@20250929 to google-vertex-anthropic
2025-10-17 23:41:06 -04:00
Frank
72053ca665
Update zen model
2025-10-17 19:04:06 -04:00
Aiden Cline
bf50aec8c8
Merge pull request #310 from Alejandro-CSt/dev
...
update copilot claude haiku 4.5 limits
2025-10-17 13:50:25 -05:00
Alejandro Chinchilla
845896f7f9
update copilot claude haiku 4.5 limits
2025-10-17 11:56:35 -06:00
Aiden Cline
d045d9c77b
update copilot sonnet 4.5
2025-10-17 10:49:55 -05:00
Aiden Cline
2ec786f87b
Merge pull request #306 from d-oit/NVIDIA-DeepSeek-V3.1-Terminus
...
feat(nvidia): add DeepSeek V3.1 Terminus model configuration
2025-10-17 09:28:48 -05:00
Aiden Cline
036a7868e1
Merge pull request #309 from nicolasgere/dev
...
chore(baseten): Add glm model
2025-10-17 09:28:01 -05:00
nicolasgere
47b455c1d0
add glm model
2025-10-17 09:38:53 -04:00
Dominik Oswald
350bc439ca
feat(nvidia): add DeepSeek V3.1 Terminus model configuration
...
Added DeepSeek V3.1 Terminus configuration file at
providers/nvidia/models/deepseek-ai/deepseek-v3.1-terminus.toml.
This model follows the NVIDIA-style configuration pattern and includes
unique capabilities for DeepSeek V3.1 Terminus.
Key details:
- Release date: 2025-09-22
- Last updated: 2025-09-22
- Reasoning + temperature enabled
- Tool call supported
- Closed weights
- Context limit: 128k
- Output limit: 8,192 tokens
- Input/output modalities: text
2025-10-17 10:51:57 +02:00
Aiden Cline
8660aaf404
Merge pull request #303 from dragove/patch-2
...
fix: rename GLM-4.6 to GLM-4.6.toml
2025-10-16 20:34:06 -05:00
金雄镕
c31b4b8a60
fix: rename GLM-4.6 to GLM-4.6.toml
2025-10-17 09:12:57 +08:00
Aiden Cline
0b61a1a687
Merge pull request #302 from Alejandro-CSt/dev
...
fix: github copilot claude haiku 4.5 filename
2025-10-16 17:27:14 -05:00
Alejandro Chinchilla
8ba9299d84
fix: github copilot claude haiku 4.5 filename
2025-10-16 16:08:31 -06:00
Frank
ac2f036229
Update zen models
2025-10-16 16:27:34 -04:00
Frank
45c42336f8
Merge pull request #301 from sambarnes/patch-1
...
fix: rename openrouter claude-4.5-haiku to claude-haiku-4.5
2025-10-16 15:56:14 -04:00
sam
0b830ce9e8
fix: rename openrouter claude-4.5-haiku to claude-haiku-4.5
2025-10-16 13:52:52 -06:00
Frank
6bf185d37e
Update zen models
2025-10-16 09:50:29 -04:00
Frank
d2989e0b49
Update deprecated status
2025-10-16 09:50:06 -04:00
Frank
ab2400a943
Merge pull request #299 from titouv/dev
...
add github-copilot/claude-haiku-4.5
2025-10-16 09:14:10 -04:00
Frank
af64ee23c6
Merge pull request #300 from krissetto/add-anthropic-model-aliases
...
Add all Anthropic model aliases
2025-10-16 09:13:10 -04:00
Christopher Petito
e0af92e404
Add all Anthropic model aliases
...
model aliases found on https://docs.claude.com/en/docs/about-claude/models/overview
Signed-off-by: Christopher Petito <chrisjpetito@gmail.com >
2025-10-16 13:32:59 +02:00
Titouan V
d65ee47bed
add github-copilot/claude-haiku-4.5
2025-10-16 07:08:49 +00:00
Aiden Cline
f737ea3bc8
Merge pull request #298 from mattgillard/add-bedrock-haiku-4-5
...
added haiku 4.5 to bedrock
2025-10-16 00:49:26 -05:00
Matt Gillard
1d0a08da4e
added haiku 4.5 to bedrock
2025-10-16 16:31:18 +11:00
Aiden Cline
3ef025e2f7
Merge pull request #296 from dragove/patch-1
...
Add GLM-4.6 to ModelScope provider models
2025-10-15 23:16:22 -05:00
Aiden Cline
f04a24b49a
Merge pull request #297 from 0xrsydn/dev
...
feat: add claude haiku 4.5 & gpt 5 image on openrouter
2025-10-15 23:16:12 -05:00
0xrsydn
4fa419c57b
feat: add claude haiku 4.5 & gpt 5 image on openrouter
2025-10-16 10:59:58 +07:00
金雄镕
b860271916
Add GLM-4.6 to ModelScope provider models
2025-10-16 10:36:59 +08:00
Aiden Cline
7005d6b4e2
Merge pull request #294 from shaper/shaper/pr/haiku-4.5
...
Vercel AI Gateway: add claude haiku 4.5
2025-10-15 19:46:38 -05:00
Walter Korman
e3ee74e6c9
Vercel AI Gateway: add claude haiku 4.5
2025-10-15 17:37:10 -07:00
Aiden Cline
7493e1dbab
Merge pull request #293 from mikesoylu/patch-1
...
[fix] Update output cost in claude-haiku-4-5 model
2025-10-15 17:14:20 -05:00
Mike Soylu
fef49d5216
Update output cost in claude-haiku-4-5 model
...
Based on pricing here: https://docs.claude.com/en/docs/about-claude/pricing
2025-10-15 15:07:14 -07:00
Frank
fccf735ccf
Update zen models
2025-10-15 13:59:58 -04:00
Aiden Cline
db133a691d
fix: haiku 4.5 cost
2025-10-15 12:51:46 -05:00
Aiden Cline
3fc673bb3e
flip reasoning
2025-10-15 12:25:08 -05:00
Aiden Cline
0c3cff5a9e
claude haiku 4.5
2025-10-15 12:24:36 -05:00
Frank
7007d191ff
Merge pull request #266 from mikehostetler/dev
...
Add optional `deprecated` field to model schema
2025-10-15 12:46:33 -04:00
Frank
621f160e03
sync
2025-10-15 12:45:06 -04:00
Frank
fda7c96feb
Merge branch 'dev' into pr/266
2025-10-15 12:13:52 -04:00
Frank
8940213999
Merge pull request #289 from shaper/shaper/pr/update-oct-14
...
Vercel AI Gateway: update to reflect latest model library
2025-10-15 12:08:11 -04:00
Frank
f314c1388f
Merge pull request #267 from rubnogueira/feat/google-ai-flash-09-2025
...
fix: gemini 2.5 family pricing
2025-10-15 12:05:35 -04:00
Frank
5b653772f4
Merge branch 'dev' into pr/267
2025-10-15 12:03:18 -04:00
Frank
3ba2e3a547
remove non svg logo
2025-10-15 12:03:00 -04:00
Aiden Cline
10bf001687
Merge pull request #291 from kkailaasa/dev
...
fix: rename nvidia kimi-k2-0905-preview.toml to kimi-k2-instruct-0905.toml
2025-10-15 09:44:29 -05:00
kk
500143d74c
Merge pull request #1 from kkailaasa/update-nvidia-kimi-k2-0905-model-name
...
fix: rename kimi-k2-0905-preview.toml to kimi-k2-instruct-0905.toml
2025-10-15 15:49:03 +02:00
kk
5e9ca14f15
fix: rename kimi-k2-0905-preview.toml to kimi-k2-instruct-0905.toml to match nvidia model name
2025-10-15 09:46:56 -04:00
Frank
e03bc6a696
Update zen models
2025-10-15 02:53:32 -04:00
Frank
3bddaab1a3
Update zen models
2025-10-15 02:33:46 -04:00
Frank
32c9fe87d5
Update zen models
2025-10-15 02:28:46 -04:00
Aiden Cline
1d3d1bd1a5
Merge pull request #268 from niharm/add-gemini-2.5-flash-image
...
Add gemini-2.5-flash-image pricing
2025-10-14 21:38:27 -05:00
Aiden Cline
d4ac99304b
Merge pull request #270 from niharm/add-gemini-live-2.5-flash-2
...
Add Gemini Live 2.5 Flash
2025-10-14 21:38:17 -05:00
Aiden Cline
d742b42d1b
Merge pull request #269 from niharm/add-gemini-live-2.5-flash
...
Add Gemini Pro/Flash TTS Models
2025-10-14 21:37:53 -05:00
Walter Korman
8e51f08515
Vercel AI Gateway: update to reflect latest model library
2025-10-14 19:03:33 -07:00
Frank
1f666feccb
Merge pull request #271 from Arindam200/dev
...
Add: Nebius AI Studio Provider
2025-10-14 13:43:16 -04:00
Frank
473684aef4
Merge pull request #274 from jeanbispo/patch-1
...
Fix npm package for Perplexity provider
2025-10-14 13:42:18 -04:00
Frank
aae6fd4333
Merge branch 'dev' into pr/271
2025-10-14 13:41:38 -04:00
Frank
7a284aa576
Merge branch 'dev' into pr/274
2025-10-14 13:40:20 -04:00
Frank
e6c2ed3ef2
Merge pull request #273 from shariqriazz/add-nvidia-kimi-k2-0905
...
Add Kimi K2 0905 model to NVIDIA provider
2025-10-14 13:39:58 -04:00
Frank
e479a1102f
Merge pull request #275 from wojons/patch-2
...
Add configuration for DeepSeek V3.2 Exp model
2025-10-14 13:39:03 -04:00
Frank
31d6117b7b
Merge pull request #276 from wojons/patch-3
...
Change model name to 'GPT OSS 20B' and update costs
2025-10-14 13:38:52 -04:00
Frank
e8a229db95
Merge pull request #282 from wojons/patch-4
...
openrouter Qwen: Qwen3 30B A3B Thinking 2507
2025-10-14 13:38:03 -04:00
Frank
3ced1a4723
Merge pull request #284 from wojons/patch-6
...
Add Qwen3 Next 80B A3B Thinking model configuration
2025-10-14 13:37:21 -04:00
Frank
5a470ca285
Merge pull request #283 from wojons/patch-5
...
opencode Qwen: Qwen3 30B A3B Instruct 2507 Enable tool_call and adjust context/output limits
2025-10-14 13:37:05 -04:00
Frank
2516f9f458
Merge pull request #287 from ASMAE20/feat/add-claude-sonnet-4.5-to-cortecs
...
Feat: add claude sonnet 4.5 to Cortecs
2025-10-14 13:36:36 -04:00
Frank
828f2a7651
Merge branch 'dev' into pr/284
2025-10-14 13:36:28 -04:00
Frank
268d157d07
Merge branch 'dev' into pr/287
2025-10-14 13:36:06 -04:00
Frank
9511348dd7
Merge pull request #288 from marvinroman/add-alibaba-models
...
Add comprehensive Alibaba Cloud Model Studio models
2025-10-14 13:34:46 -04:00
Frank
21b3814006
Merge branch 'dev' into pr/288
2025-10-14 13:25:22 -04:00
Aiden Cline
e65dec17da
Merge pull request #285 from sst/fix-codex-cost
...
fix: add cost to codex
2025-10-14 11:50:11 -05:00
Aiden Cline
1f25a3018c
Revert "fix: script"
...
This reverts commit bd725a0b19c6ed2689b26d583f95e40ca1eecbd4.
2025-10-14 11:47:55 -05:00
Aiden Cline
c0e1380178
fix: add cost to codex
2025-10-14 11:46:47 -05:00
Aiden Cline
11b24f0ae1
Merge pull request #286 from no1wudi/dev
...
providers/modelscope: Remove Qwen3-Coder-480B-A35B-Instruct model
2025-10-14 11:46:24 -05:00
Frank
8e1c9c9a89
Merge branch 'dev' into pr/286
2025-10-14 12:17:30 -04:00
Frank
dfbbb9e1ac
ci: fix
2025-10-14 12:10:05 -04:00
Marvin Roman
0c53491bbe
Add comprehensive Alibaba Cloud Model Studio models
...
Adds 88 models across Alibaba International (Singapore) and Alibaba-CN (Beijing) regions:
- 39 models for alibaba provider (Singapore pricing)
- 59 models for alibaba-cn provider (Beijing pricing)
Includes:
- Text generation models (Qwen3, Qwen, QwQ series)
- Vision models (Qwen-VL, Qwen3-VL, QVQ)
- Multimodal models (Qwen-Omni with audio/video support)
- Open-source models (Qwen2.5, Qwen3 series)
- Specialized models (coding, math, translation, OCR, ASR)
- Third-party models (DeepSeek, Kimi - Beijing only)
2025-10-14 13:36:50 +08:00
Frank
06745bade4
display beta models
2025-10-13 22:19:12 -04:00
ASMAE20
c6b855bf0e
feat: add Sonnet 4.5 to Cortecs provider
2025-10-13 11:31:34 +01:00
Huang Qi
71c87f0cb7
providers/modelscope: Remove Qwen3-Coder-480B-A35B-Instruct model variant
...
Remove Qwen3-Coder-480B-A35B-Instruct.toml from the modelscope provider
as the API service for this model variant is no longer available.
This ensures the model catalog accurately reflects the currently
supported models.
2025-10-13 14:45:00 +08:00
Alexis Okuwa
cb828af6aa
Add Qwen3 Next 80B A3B Thinking model configuration
2025-10-09 17:18:31 -07:00
Alexis Okuwa
1c2208d532
Enable tool_call and adjust context/output limits
...
Updated tool_call setting and increased context and output limits.
2025-10-09 17:15:25 -07:00
Alexis Okuwa
351bafc004
Update context and output limits in TOML file
2025-10-09 17:13:02 -07:00
Aiden Cline
f9281cca60
Merge pull request #277 from bowber/dev
...
Added GLM 4.6 Turbo & DeepSeek V3.2 Exp models for Chutes provider
2025-10-09 09:05:41 -05:00
bowber
ecf2cd98e0
Add open_weights and update release dates in TOML
2025-10-09 21:00:51 +07:00
bowber
1af75357a9
Add GLM 4.6 Turbo model configuration for Chutes
2025-10-09 20:32:54 +07:00
bowber
062a6ecc59
Update DeepSeek V3.2 Exp configuration settings for Chutes
2025-10-09 20:28:18 +07:00
Jean Bispo
73511f0776
Fix npm package for Perplexity provider
2025-10-08 20:43:51 -03:00
Frank
8d397086d8
Update zen model
2025-10-08 16:03:30 -04:00
Frank
9ed51f688e
Update zen model
2025-10-08 16:00:10 -04:00
Frank
11e2efd78d
Update zen models
2025-10-08 14:53:21 -04:00
Shariq Riaz
5aa751037a
Fix: Set NVIDIA Kimi K2 0905 costs to 0.0
...
- Updated input/output costs to 0.0 to match other NVIDIA models
- Removed cache_read cost as NVIDIA models don't have associated costs
2025-10-08 00:32:38 +05:00
Shariq Riaz
7946a5e9a3
Add Kimi K2 0905 model to NVIDIA provider
...
- Added moonshotai/kimi-k2-0905-preview.toml to NVIDIA provider
- Model is open source and available through NVIDIA's API
- Same specifications as the original MoonshotAI provider version
2025-10-08 00:29:28 +05:00
Yuku Kotani
fe5e6a57fb
Rename google-vertex-anthropic to avoid conflict with google-vertex
2025-10-07 16:19:45 +09:00
Arindam200
d2ec5b06cd
update model name
2025-10-07 01:24:38 +05:30
Arindam Majumder
203e1b7cb7
Merge branch 'sst:dev' into dev
2025-10-06 23:53:33 +05:30
Arindam200
26a8106564
feat: add Nebius AI Studio provider
2025-10-06 23:53:06 +05:30
Alexis Okuwa
96152858b6
Change model name to 'GPT OSS 20B' and update costs
...
Updated model name and cost values for GPT OSS 20B.
2025-10-05 01:57:10 -07:00
Alexis Okuwa
ba65c91e90
Add configuration for DeepSeek V3.2 Exp model
2025-10-05 01:53:17 -07:00
nihar
fd2c462316
Add Gemini Live 2.5 Flash
2025-10-03 18:19:24 -07:00
nihar
684c227a9a
Remove key
2025-10-03 17:57:35 -07:00
nihar
573eb59575
Add Gemini Pro/Flash TTS Models
2025-10-03 17:53:39 -07:00
nihar
15bd77a926
Add gemini-2.5-flash-image
2025-10-03 17:22:08 -07:00
Ruben Nogueira
95ada8a5ad
fix: gemini 2.5 family pricing
2025-10-03 22:56:05 +01:00
Jay
e9fddf9844
Update documentation URL in provider.toml
2025-10-03 16:36:05 -04:00
Jay
9062458823
Update provider name and documentation URL
2025-10-03 16:35:45 -04:00
Mike Hostetler
460c87b1c3
Add optional deprecated field to model schema and update README documentation
2025-10-03 08:26:03 -05:00
Frank
dfcfe80408
Merge pull request #265 from reissbaker/glm-4.6
...
Add GLM-4.6 to Synthetic's model listing
2025-10-03 09:21:13 -04:00
Matt Baker
63104a33bb
Add GLM-4.6
2025-10-02 12:50:48 -07:00
Frank
b6e9e2a6d0
Update zen models
2025-10-02 15:08:30 -04:00
ASMAE20
bb8a100b63
Resolve conflicts and update logo
2025-10-02 14:56:48 +01:00
Frank
f9767590ee
Update zen model
2025-10-01 17:54:24 -04:00
Aiden Cline
c2efda2aeb
fix: anthropic sonnet 4.5 ( #262 )
2025-10-01 17:39:58 -04:00
Frank
61e44c56ff
Merge pull request #254 from 0xrsydn/dev
...
chore: update claude 4.5 context length to 1M on openrouter & add glm 4.6 on openrouter
2025-10-01 09:08:47 -04:00
Frank
03456e3651
Merge pull request #255 from gary149/add-glm-4-6-hf
...
Add GLM-4.6 to Hugging Face
2025-10-01 09:08:25 -04:00
Frank
d3ab3d9116
Merge pull request #257 from thuanpham582002/dev
...
[chores] Add GLM-4.6 model for chutes provider
2025-10-01 09:08:16 -04:00
Frank
2ee0000a4d
Merge pull request #259 from niharm/remove-sonnet-4-5-reasoning-price
...
Remove reasoning prices for Sonnet 4.5
2025-10-01 09:00:25 -04:00
nihar
83ef452ab6
Remove incorrect reasoning prices for Sonnet models
2025-09-30 17:56:40 -07:00
thuanpham582002
516cacfd0e
Add GLM-4.6 model with expanded 200k context window and 128k max output tokens across chutes providers
2025-10-01 05:57:04 +07:00
thuanpham582002
521f04de9a
Add GLM-4.6 model with expanded 200k context window and 128k max output tokens across chutes providers
2025-10-01 05:57:04 +07:00
Victor Muštar
bc3c32898e
Add Hugging Face metadata for GLM-4.6
2025-09-30 18:52:12 +02:00
Aiden Cline
fa702b0353
fix: bedrock model id ( #253 )
2025-09-30 11:23:25 -05:00
0xrsydn
9a1efdac57
feat add glm 4.6 on openrouter
2025-09-30 23:10:33 +07:00
0xrsydn
d14d7301ec
update 1M context length on openrouter
2025-09-30 23:04:31 +07:00
ai13f
1d3df54b2e
Update claude-sonnet-4.5.toml ( #252 )
2025-09-30 10:23:29 -05:00
Frank
e621ae94b1
Add sonnet 4.5 to Vercel AI Gateway
2025-09-30 07:04:41 -04:00
Frank
c5b265ce52
Merge pull request #249 from edbramwell/dev
...
bedrock 4.5
2025-09-30 07:00:54 -04:00
Frank
b8ec034463
Merge pull request #251 from no1wudi/dev
...
Add GLM-4.6 model with expanded 200k context window and 128k output
2025-09-30 06:59:46 -04:00
Huang Qi
35f920aa6c
Add GLM-4.6 model with expanded 200k context window and 128k max output tokens across zai and zhipuai providers
2025-09-30 15:25:39 +08:00
Ed Bramwell
5ce8878778
bedrock 4.5
2025-09-29 20:27:32 +01:00
Aiden Cline
47a71d06c5
github copilot sonnet 4.5 ( #247 )
2025-09-29 14:09:57 -04:00
Frank
094060436f
Add sonnet 4.5 to openrouter
2025-09-29 13:49:10 -04:00
Frank
2ddd8dd162
Merge pull request #246 from ai13f/patch-4
...
Create claude-sonnet-4-5-20250929.toml
2025-09-29 13:40:31 -04:00
ai13f
ba4f46da6b
Create claude-sonnet-4-5-20250929.toml
2025-09-29 13:33:19 -04:00
Frank
8dd47a2a34
Add sonnet 4.5 models to Zen
2025-09-29 13:11:29 -04:00
Frank
91d02e553d
fix styling
2025-09-29 13:01:34 -04:00
Frank
e1a3ea7fe9
Merge pull request #227 from niharm/gemini-2-5-audio
...
Add Audio input/output tokens as special columns, filling in for Gemini 2.5 Flash
2025-09-29 12:21:14 -04:00
Frank
93ebf12980
Merge pull request #237 from epicwhale/dev
...
add -latest alias for gemini flash and flash-lite
2025-09-29 11:50:03 -04:00
Frank
12f904a9bb
Merge pull request #245 from nwp/add-xai-grok-code-fast-1-to-vercel-provider
...
Add Grok Code Fast 1 model to Vercel provider
2025-09-29 11:49:25 -04:00
Nathan Phelps
da95d7067b
Add Grok Code Fast 1 model to Vercel provider
2025-09-29 09:16:02 -05:00
Frank
d8c0f2bf4d
Merge pull request #239 from CarlosGtrz/add-deepseek-v3.1-terminus-chutes
...
Add DeepSeek V3.1 Terminus model to Chutes provider
2025-09-29 09:28:29 -04:00
Frank
e3efd48829
Merge pull request #240 from thuanpham582002/dev
...
fix: rename Turbo to turbo in model filenames DeepSeek-V3.1-Turbo and GLM-4.5-Turbo
2025-09-29 09:27:27 -04:00
Frank
694095bec9
Merge pull request #242 from nwp/add-xai-grok-code-fast-1
...
Add Grok Code Fast 1 Model to xAI Provider
2025-09-29 09:27:17 -04:00
Frank
ed67b13c64
Merge pull request #243 from nwp/add-xai-grok-4-fast-to-vercel-provider
...
Add Grok 4 Fast models to Vercel Provider
2025-09-29 09:26:12 -04:00
Frank
3bfa20e027
Merge pull request #244 from wojons/patch-1
...
Modify Grok 4 Fast configuration parameters
2025-09-29 09:25:59 -04:00
Alexis Okuwa
5009c8713c
Modify Grok 4 Fast configuration parameters
...
Updated cost parameters and output limits for Grok 4 Fast.
2025-09-28 19:28:49 -07:00
Nathan Phelps
b81b92bfe7
Add Grok 4 Fast models to Vercel Provider
2025-09-28 15:38:02 -05:00
Nathan Phelps
ea1bddfe8d
Add Grok Code Fast 1 Model
2025-09-28 15:25:37 -05:00
nihar
dfcd3fc268
Add output_audio and gemini 2.5 flash lite preview
2025-09-27 14:21:14 -07:00
nihar
9718c42638
PR Feedback
2025-09-27 12:22:28 -07:00
Frank
ba48140362
Update zen models
2025-09-27 12:38:59 -04:00
thuanpham582002
5cc449e343
fix: rename Turbo to turbo in model filenames
...
- DeepSeek-V3.1-Turbo.toml -> DeepSeek-V3.1-turbo.toml
- GLM-4.5-Turbo.toml -> GLM-4.5-turbo.toml
2025-09-27 20:35:14 +07:00
Carlos Gutierrez
3c19a29013
Add DeepSeek V3.1 Terminus model to Chutes provider
2025-09-26 15:11:16 -07:00
dayson
b405b5a616
Delete providers/google/models/models/gemini-flash-lite-latest
2025-09-26 18:28:02 +01:00
dayson
8a3d24ef1e
feat: add gemini flash-lite latest (alias)
...
alias always points to most recent flash-lite version
2025-09-26 18:27:46 +01:00
dayson
27ffe234e2
feat: add gemini flash-lite latest (alias)
...
alias always points to most recent flash-lite version
2025-09-26 18:26:36 +01:00
dayson
178de2e0a7
feat: add gemini flash latest (alias)
...
alias always points to most recent flash version
2025-09-26 18:23:27 +01:00
Frank
ac659a3002
update zen models
2025-09-26 13:06:10 -04:00
Jay
166c64941f
Fix logo
2025-09-26 12:43:31 -04:00
Frank
607ecb189b
Merge pull request #231 from trevorrecker/gpt-4o-snapshots
...
feat: Add OpenAI gpt-4o snapshot versions
2025-09-26 12:42:56 -04:00
Frank
070d29f523
Merge pull request #229 from thuanpham582002/dev
...
chore(chutes): add zai-org/GLM-4.5-Turbo, deepseek-ai/DeepSeek-V3.1-Turbo
2025-09-26 12:37:15 -04:00
Frank
f203eb4bae
Merge pull request #230 from tamirzb/dev
...
Add new chutes Qwen3 models
2025-09-26 12:31:36 -04:00
Frank
10c3576990
Merge pull request #235 from apepper/GEMINI_API_KEY
...
Google provider: Add additional env GEMINI_API_KEY
2025-09-26 12:30:30 -04:00
Frank
f83061d1c9
Merge pull request #225 from billycao/billy/DeepSeek-V3.1-Terminus
...
chore(synthetic): Add DeepSeek-V3.1-Terminus
2025-09-26 12:02:58 -04:00
Frank
2551142623
Merge pull request #232 from rekram1-node/add-gemini-previews
...
feat: add gemini 2.5 & 2.5 flash lite previews for 09-25
2025-09-26 12:02:13 -04:00
Billy Cao
66a691c025
Set reasoning = true for DeepSeek V3.1 models
2025-09-26 06:52:45 -07:00
ASMAE20
45384a5038
fix: logo types and pricing models
2025-09-26 11:14:06 +01:00
Alexander Pepper
c430cc3e18
Google provider: Add additional env GEMINI_API_KEY
...
This is the same env that Gemini CLI uses:
> Option 2: Gemini API Key
> ✨ Best for: Developers who need specific model control or paid tier access
>
> Benefits:
>
> Free tier: 100 requests/day with Gemini 2.5 Pro
> Model selection: Choose specific Gemini models
> Usage-based billing: Upgrade for higher limits when needed
> ```
> # Get your key from https://aistudio.google.com/apikey
> export GEMINI_API_KEY="YOUR_API_KEY"
> gemini
> ```
Source: https://github.com/google-gemini/gemini-cli?tab=readme-ov-file#option-2-gemini-api-key
2025-09-26 10:23:17 +02:00
Fredy Álvarez
33bcd8863c
chore(vercel): gpt-5-codex ( #226 )f
2025-09-25 23:12:12 -04:00
Noah Gao
845d26162e
chore(openrouter): add gpt-5-codex ( #228 )
2025-09-25 23:12:03 -04:00
rekram1-node
f8fc588447
feat: add gemini 2.5 & 2.5 flash lite previews for 09-25
2025-09-25 14:44:13 -05:00
Trevor Recker
34fc629c51
Add OpenAI gpt-4o snapshot versions
2025-09-25 11:52:20 -05:00
Tamir Zahavi-Brunner
dd881da4d2
Add new chutes Qwen3 models
2025-09-25 20:02:54 +08:00
thuanpham582002
b8548fa688
chore(chutes): add deepseek-ai/DeepSeek-V3.1-Turbo
2025-09-25 18:35:26 +07:00
thuanpham582002
762b45ec75
chore(chutes): add zai-org/GLM-4.5-Turbor
2025-09-25 18:15:37 +07:00
nihar
92934f8814
Add audio input as a column
2025-09-24 22:56:37 -07:00
Billy Cao
93e07266ad
Add DeepSeek-V3.1-Terminus for provider Synthetic
2025-09-24 10:39:58 -07:00
Frank
7c86f7f945
Merge pull request #223 from niharm/add-gemini-models
...
Add Google/gemini-2.5-flash-lite.toml (separately from preview model)
2025-09-24 12:48:52 -04:00
Frank
82c717053b
Merge pull request #224 from ASMAE20/feat/add-cortecs-provider
...
Feat: Add Cortecs Provider
2025-09-24 12:47:41 -04:00
Frank
c24d7c3fe7
Delete providers/cortecs/logo.svg
2025-09-24 12:43:32 -04:00
ASMAE20
0426253af0
feat: add cortecs provider
2025-09-24 15:43:14 +01:00
Frank
5e67df81a7
update zen provider
2025-09-24 09:16:50 -04:00
nihar
8199b29fbb
Update context for gemini-2.5-flash-lite-preview-06-17
2025-09-23 22:32:59 -07:00
nihar
83802fc49c
Add Gemini 2.5 Flash Lite
2025-09-23 22:13:00 -07:00
Frank
d6a17db8d5
allow model overriding provider api
2025-09-24 01:05:04 -04:00
Frank
a49a1fed26
Merge pull request #216 from no1wudi/dev
...
fix: remove Kimi-K2-Instruct from ModelScope provider
2025-09-23 21:14:44 -04:00
Frank
100f614d52
Merge pull request #222 from aemr3/add-copilot-gpt5-codex
...
feat: add github copilot gpt-5-codex
2025-09-23 19:06:28 -04:00
Frank
6cee1b055a
Merge pull request #209 from InfHorus/dev
...
Add LucidQuery provider with LucidNova RF1-100B and LucidQuery Nexus Coder models
2025-09-23 18:47:26 -04:00
Frank
bf16007610
sync
2025-09-23 18:46:54 -04:00
Emre
038f68c509
feat: add github copilot gpt-5-codex
2025-09-23 14:34:38 -07:00
InfHorus
b01a72b87c
Update logo.svg
2025-09-23 23:23:00 +02:00
Dax
724fb159c8
Remove experimental flag from gpt-5-codex.toml
...
Removed experimental flag from gpt-5-codex model configuration.
2025-09-23 16:59:55 -04:00
Frank
0afec59ce1
add gpt-5-codex to zen
2025-09-23 16:45:01 -04:00
Frank
8410bad044
Merge pull request #193 from d-oit/feat/nvidia-provider
...
Add NVIDIA provider models with standardized IDs
2025-09-23 15:00:23 -04:00
Frank
d2f99794f4
update readme
2025-09-23 14:58:41 -04:00
Frank
37f1c0854c
remove mode id
2025-09-23 14:56:20 -04:00
Frank
10ce3c7e38
Merge pull request #221 from ai13f/patch-3
...
Create gpt-5-codex.toml
2025-09-23 14:46:11 -04:00
ai13f
9321898b75
Create gpt-5-codex.toml
2025-09-23 14:36:18 -04:00
Frank
b4f1289ce7
Merge pull request #191 from OpeOginni/fix/update-requesty-config
...
fix(requesty): update npm package to openai-compatible
2025-09-23 14:32:25 -04:00
Frank
33746fb463
Merge pull request #205 from gary149/qwen3-next-80b
...
Add new Qwen models and Kimi-K2-Instruct-0905 configuration files
2025-09-23 14:29:47 -04:00
Frank
747a0932a0
sync
2025-09-23 14:29:07 -04:00
Frank
83d7934522
sync
2025-09-23 14:23:21 -04:00
Frank
7b7d005865
Merge pull request #214 from zhangweiii/feat/add-model-zhipu-coding-plan
...
feat: add zhipu ai coding plan
2025-09-23 12:17:44 -04:00
Frank
87a116b32d
sync
2025-09-23 12:16:04 -04:00
Frank
3ecfe2dea5
Merge pull request #215 from albertilagan/xai/grok-4-fast
...
feat: add Grok 4 fast
2025-09-23 12:11:02 -04:00
Frank
f4e84e77a8
Merge pull request #217 from esafak/deepseek-terminus
...
feat: add Deepseek v3.1 Terminus
2025-09-23 11:57:57 -04:00
Frank
8000fa483d
Update gpt-5-codex
2025-09-23 11:52:42 -04:00
Frank
f1baab1a0d
Merge pull request #220 from shantur/patch-1
...
Create gpt-5-codex.toml
2025-09-23 11:44:40 -04:00
Shantur Rathore
9b6d6a2375
Create gpt-5-codex.toml
2025-09-23 13:10:26 +01:00
Emre Şafak
02f99bbab5
feat: add Deepseek v3.1 Terminus
2025-09-22 12:46:16 -04:00
Huang Qi
af4b703c92
fix: remove Kimi-K2-Instruct from ModelScope provider
2025-09-22 17:41:29 +08:00
Albert Ilagan
79c89af8db
feat: add Grok 4 fast
2025-09-21 22:14:02 +08:00
zhangweiii
edf69d1422
feat: add zhipu ai coding plan
2025-09-21 20:23:30 +08:00
Emre Şafak
bbe94a950d
feat: add Grok 4 fast (free) ( #213 )
...
* feat: add Grok 4 fast (free)
* Update providers/openrouter/models/x-ai/grok-4-fast:free.toml
Co-authored-by: heguro <65112898+heguro@users.noreply.github.com >
---------
Co-authored-by: heguro <65112898+heguro@users.noreply.github.com >
2025-09-20 18:54:30 -04:00
Frank
1c7799fe76
Add zen code-supernova
2025-09-19 16:56:07 -04:00
Frank
5eb9f03f76
Add zen code-supernova
2025-09-19 16:53:18 -04:00
Frank
bb40a42fb7
Merge pull request #173 from ghostdevv/more-cf-ai-models
2025-09-19 00:56:11 -04:00
Frank
c18843b550
Merge pull request #194 from d-oit/add-perplexity-provider
2025-09-19 00:54:35 -04:00
Frank
443cc3f595
Merge pull request #198 from anntnzrb/feature/add-longcat-model
2025-09-19 00:53:37 -04:00
Frank
dee5eb9f2f
Merge pull request #200 from sudokai/patch-1
2025-09-19 00:53:06 -04:00
Frank
a91addbaff
Merge pull request #201 from yuan-alex/yuan-alex/fix-fireworks-gpt-oss
...
fix(fireworks): move GPT OSS models to correct directory
2025-09-19 00:52:02 -04:00
Frank
25c88d22c6
Merge pull request #211 from rekram1-node/fix-baseten
2025-09-19 00:48:53 -04:00
rekram1-node
f898e5e104
fix: baseten models
2025-09-18 16:14:44 -05:00
Frank
4ee605deb0
Add alibaba-cn provider
2025-09-18 00:03:18 -04:00
Frank
584cb04fb4
Add z.ai coding plan
2025-09-17 16:47:36 -04:00
InfHorus
826ef33a29
Added Provider: LucidQuery and their two models
...
lucidquery-nexus-coder: specialized for coding tasks using an inverted hybrid architecture
lucidnova-rf1-100b: General model with web-access, diffusion-based reasonning coupled with AR response engine
2025-09-16 18:20:34 +02:00
Chad Kunde
6374b7c56f
Add openrouter qwen3-next 80b A3b instruct ( #203 )
...
Knowledge cutoff is assumed to be the same as qwen3 models, but it's
not clearly posted.
2025-09-16 03:15:52 -04:00
Matt Baker
a1350d5f40
Update Kimi-K2-Instruct-0905 context length ( #208 )
...
We support 256k context length for the newest Kimi K2
2025-09-16 03:15:24 -04:00
Frank
5a458325aa
Update zen provider
2025-09-15 17:42:17 -04:00
Dax
06d63e12ee
Remove experimental flag from kimi-k2.toml
2025-09-13 06:07:39 -04:00
Jay
2340429972
Delete providers/synthetic/logo.svg
...
Incorrect format, use currentColor only
2025-09-12 19:23:39 -04:00
Victor Muštar
32a520a3d3
Fix whiteline consistency in Qwen3-Next-80B-A3B-Thinking.toml
...
Remove extra blank line to match repository conventions.
2025-09-12 18:37:41 +02:00
Victor Muštar
bca4226878
Add new Qwen models and Kimi-K2-Instruct-0905 configuration files
2025-09-12 18:22:20 +02:00
Alex Yuan
2e347648a9
fix: move Fireworks GPT OSS models to correct directory structure
...
Moved gpt-oss-120b.toml and gpt-oss-20b.toml from accounts/fireworks/ to accounts/fireworks/models/ to match the expected directory structure.
2025-09-11 14:57:52 -04:00
Kaixi Luo
19d5399a6d
Update kimi-k2-turbo-preview.toml
...
> "Latest release of kimi-k2-0905-preview model, with an expanded 256K context window and enhanced coding capabilities. If you need faster response speed, you can use the kimi-k2-turbo-preview model, which always tracks the latest version of kimi-k2 and maintains the same functionality, but the output speed has been increased to 60tokens/s, with a maximum of 100tokens/s."
2025-09-11 10:06:34 +02:00
Aiden Cline
93585ba4fa
fix: github copilot models ( #199 )
2025-09-11 00:51:30 -04:00
Frank
a9301afe8e
Update zen provider
2025-09-10 23:53:18 -04:00
Frank
2a488016f5
Update zen provider
2025-09-10 23:24:06 -04:00
anntnzrb
b5db915f0f
feat: add pricing info to LongCat Flash Chat model
...
- Add missing [cost] section with input/output pricing
2025-09-10 20:16:41 -05:00
anntnzrb
bf11bf4ac8
feat: add LongCat-Flash-Chat-FP8 model to Chutes provider
...
- Create TOML configuration for meituan-longcat/LongCat-Flash-Chat-FP8 model
- Include proper pricing, context limits, and modality settings
- Validate configuration with bun validate command
- Verify model availability through Chutes API
This commit adds a new model from the meituan-longcat provider to the Chutes platform configuration.
2025-09-10 16:00:40 -05:00
Frank
c4ef61971b
Merge pull request #197 from bismitpanda/dev
...
Update pricing of `openrouter` `openai/gpt-oss-120b`
2025-09-10 15:58:31 -04:00
Frank
6eb01aac67
Merge pull request #186 from anntnzrb/feat/update-prov-chutes
...
sync: update chutes provider Kimi models to match API endpoint
2025-09-10 15:57:44 -04:00
Bismit Panda
dbeaccf169
Update pricing of openrouter openai/gpt-oss-120b
2025-09-11 00:44:52 +05:30
_nderscore
6733520985
fix: unique name for Synthetic's Kimi K2 0905 ( #196 )
2025-09-09 23:07:48 -04:00
Frank
caf8bec61d
Display reasoning token cost
2025-09-09 18:16:41 -04:00
Frank
dafb86f42e
Update zen provider
2025-09-09 17:30:24 -04:00
Frank
b71977af78
Add reasoning cost for grok models
2025-09-09 16:03:17 -04:00
Frank
b4896d7ada
Update zen provider
2025-09-09 15:50:54 -04:00
CI/CD Tester
a29960db3f
Reorganize NVIDIA models into subfolders by provider and update README with optional organization instructions
2025-09-09 17:07:45 +02:00
Frank
2ecca630e6
Update zen models
2025-09-09 05:49:50 -04:00
Frank
7fcfb3afb4
Update zen models
2025-09-09 02:46:26 -04:00
Matt Baker
86238a7b72
Fix Synthetic model IDs ( #188 )
2025-09-09 01:33:18 -04:00
CI/CD Tester
415a74fac5
Add Perplexity provider with Sonar models
2025-09-08 21:19:20 +02:00
CI/CD Tester
97c303a3f9
Add id fields to NVIDIA provider models and update registry
2025-09-08 20:58:57 +02:00
OpeOginni
033436243d
fix(requesty): update npm package to openai-compatible and add API endpoint
2025-09-08 15:26:13 +02:00
anntnzrb
a1e594f7d9
restore: keep Kimi-K2-Instruct-75k model during transition period
2025-09-07 12:17:08 -05:00
anntnzrb
811277dec7
sync: update chutes provider Kimi models to match API endpoint
2025-09-06 21:05:02 -05:00
Frank
5ed40fe25f
Merge pull request #181 from d-oit/feat/nvidia-provider
...
feat(nvidia): add models
2025-09-06 17:55:01 -04:00
Stephen Murray
770e4b4b6d
feat: add sonoma alpha models ( #185 )
2025-09-05 21:47:42 -04:00
nicolasgere
5be267c0aa
add kimi and fix qwen ( #184 )
2025-09-05 21:34:28 -04:00
Stephen Murray
806542cd41
fix(openrouter): use correct context limits for qwen3 max ( #183 )
...
Co-authored-by: Dax <d@ironbay.co >
2025-09-05 13:31:22 -04:00
Tom
befacedb2b
feat(groq): add Kimi K2 Instruct 0905 model ( #180 )
...
* feat: add Kimi K2 Instruct 0905 model for Groq
* fix: update pricing for Kimi K2 Instruct 0905 model
2025-09-05 13:31:08 -04:00
Dax
d653b23a1e
Modify limit settings in qwen3-max.toml
...
Updated context and output values in the limit section.
2025-09-05 13:30:06 -04:00
Stephen Murray
0fed5ac629
feat(openrouter): add qwen3 max ( #182 )
2025-09-05 11:51:40 -04:00
CI/CD Tester
8d965020ae
Add additional NVIDIA models: DeepSeek R1, Llama Ultra 253B, Gemma 3 27B, Phi 4 Multimodal, Qwen3 235B, Parakeet TDT 0.6B
2025-09-05 12:52:16 +02:00
CI/CD Tester
c554bf3877
Add NVIDIA models: OCR v1, Whisper Large v3, Flux 1 Dev, Cosmos Nemotron 34B
2025-09-05 12:50:14 +02:00
CI/CD Tester
e5ef54715a
feat: Add Qwen3 Coder 480B A35B Instruct to Nvidia provider
...
- Add Qwen3 Coder 480B A35B Instruct model
- 262K context window, code generation optimized
- Tool calling and temperature support
- Trial pricing (0.0 cost)
2025-09-05 12:35:11 +02:00
CI/CD Tester
f940317a97
feat: Add Nvidia provider with DeepSeek V3.1 model
...
- Add Nvidia provider configuration for NIM
- Include DeepSeek V3.1 model with 128K context
- Support for reasoning and tool calling
- OpenAI-compatible API integration
2025-09-05 12:32:54 +02:00
Frank
ba1d5a6ce2
add kimi k2 0905 model
2025-09-05 01:23:07 -04:00
Frank
6922b4d279
Fail deploy if build fails
2025-09-05 01:11:31 -04:00
Frank
c47561e488
fix baseten logo
2025-09-05 00:57:55 -04:00
Frank
ed7b830131
Merge pull request #174 from esafak/feat/hermes-4
...
feat: add Hermes 4 70B, Hermes 4 405B
2025-09-05 00:41:02 -04:00
Frank
54f7b29388
Merge pull request #165 from 0xrsydn/dev
...
Added Grok Code Fast 1 on Openrouter provider
2025-09-05 00:39:57 -04:00
Frank
7674f353a0
Merge pull request #177 from bigs/feat/fireworks-add-4-models
...
Add DeepSeek V3.1, GLM-4.5 variants, Qwen3 Coder 480B to Fireworks provider
2025-09-05 00:39:30 -04:00
Frank
082a9739b8
fix basten provider
2025-09-05 00:37:30 -04:00
Tom
eb35280316
feat: add kimi-k2-0905 model ( #178 )
2025-09-05 00:28:25 -04:00
Tom
e4f38d773c
fix: update baseten npm to openai-compatible ( #179 )
2025-09-05 00:28:02 -04:00
nicolasgere
ea151a21fc
Add baseten as provider ( #168 )
...
* add baseten providers for qwen
* add baseten providers for qwen
2025-09-04 23:43:46 -04:00
ai13f
fdb5b01486
Added Grok Code Fast 1 on Github Copilot ( #167 )
2025-09-04 23:42:50 -04:00
Frank
ef094bb857
update oc zen provider
2025-09-03 14:29:53 -04:00
Cole Brown
035ff459c2
feat(fireworks): add DeepSeek V3.1, GLM-4.5 (+Air), Qwen3 Coder 480B A35B Instruct
2025-09-03 14:12:02 -04:00
Frank
77527e8b22
Merge pull request #175 from rekram1-node/fix-deepseek-chat
...
fix: deepseek-chat output limit
2025-09-03 13:19:36 -04:00
Dax
9343c5f015
Rename provider from 'opencode zen' to 'opencode'
2025-09-03 12:36:38 -04:00
Frank
f3d58ac50d
update oc zen provider
2025-09-03 10:48:53 -04:00
Frank
a64c58bd6f
Update opencode zen provider
2025-09-03 09:09:32 -04:00
rekram1-node
acb1551f83
fix: deepseek-chat output limit
2025-08-31 22:18:47 -05:00
Fayçal Mitidji
0a87de42ab
Feat: Add Synthetic.new provider and models ( #170 )
2025-08-30 07:23:34 -05:00
Emre Şafak
8533f88c6d
feat: add Hermes 4 70B, Hermes 4 405B
2025-08-30 01:34:05 -04:00
GHOST
0b77631219
feat: add new cf workers ai models
2025-08-30 03:01:30 +01:00
Frank
58cb8fe59e
Update grok code name
2025-08-27 10:30:45 -04:00
Frank
de24ff9053
Revert adding openai compatible endpoing to non openai compatible sdk
2025-08-27 10:30:16 -04:00
Aiden Cline
408ba3c4cf
fix: google model api ( #166 )
2025-08-27 08:17:04 -05:00
0xrsydn
ea3ca4b188
Added Grok Code Fast 1 on Openrouter provider
2025-08-27 11:44:59 +07:00
Frank
cf6249c393
update sonic model name
2025-08-26 16:32:23 -04:00
Frank
f1d9c09de4
Update sonic model name
2025-08-26 16:14:53 -04:00
Frank
1a475835c7
Merge pull request #135 from cork89/dev
...
Add multiple model searching
2025-08-27 00:16:42 +08:00
Frank
c7a0b6a941
Merge pull request #132 from deathbeam/add-some-providers
...
Add API endpoints for Anthropic and Google openai compatible
2025-08-27 00:01:50 +08:00
Frank
c0290ebae1
sync
2025-08-26 12:00:52 -04:00
Frank
31a48cc6c2
Merge branch 'dev' into pr/132
2025-08-26 11:40:17 -04:00
Frank
cf933e3330
Merge pull request #156 from vamsimnet/fastrouter
...
Fastrouter
2025-08-26 23:15:28 +08:00
vamsimnet
b9014eead9
change logo file
2025-08-26 13:20:14 +05:30
Frank
1c70e282ce
Merge pull request #138 from ghostdevv/cloudflare-workers-ai
...
feat: add cloudflare workers ai
2025-08-26 05:48:20 +08:00
Frank
c9dc279b2a
Merge pull request #164 from edbramwell/dev
...
Update GPT-5-Chat on Azure with correct info
2025-08-26 05:47:16 +08:00
GHOST
b35f9dff56
chore: make cloudflare svg square
2025-08-25 21:13:50 +01:00
GHOST
b266a32a07
chore: remove old model
...
This uses their old billing system and a different name (`meta-llama`)
to the rest of the meta models. This model is available from cloudflare
under `@cf/meta/meta-llama-3-8b-instruct`.
2025-08-25 21:13:50 +01:00
GHOST
f3f850fa16
fix: missing costs
2025-08-25 21:13:50 +01:00
GHOST
42ee48e556
fix: add missing limit/limit.output
...
I don't believe a lot of these have limits in the same way, primarily
due to being audio models. Putting 0 to satisfy the linter.
2025-08-25 21:13:50 +01:00
GHOST
31478d7180
fix: missing limit.output fields
...
The Cloudflare docs don't explicity provide this value, but their
glossary says that `max_tokens` cannot exceed the context window
2025-08-25 21:13:50 +01:00
GHOST
41721958c4
fix: cloudflare logo
2025-08-25 21:13:50 +01:00
GHOST
b02b8e142b
chore: update dates
...
From what I can tell all but a few of the models Cloudflare are running
are on Hugging Face, so I've gotten this data from there. It's not 100%
accurate, but it's better than nothing.
2025-08-25 21:13:50 +01:00
GHOST
b5c883b3db
feat: add cloudflare workers ai
2025-08-25 21:13:50 +01:00
Ed Bramwell
5026ce0ad6
update gpt-5-chat
2025-08-25 20:28:10 +01:00
Frank
589a5a485a
Merge pull request #139 from ghostdevv/docs-provider-update
...
docs(fix): provider info has additional requirements
2025-08-26 01:10:12 +08:00
Frank
adc6de0575
sync
2025-08-26 01:09:38 +08:00
Frank
8e008bc1c6
Merge pull request #155 from paflopes/dev
...
feat: Add Gemini 2.5 Flash model configuration for google-vertex
2025-08-26 00:44:39 +08:00
Frank
bc3884d074
Merge pull request #160 from SubModel/dev
...
Add new provider: Submodel
2025-08-26 00:38:05 +08:00
Frank
a24afbdccd
Merge pull request #163 from hubertpysklo/add-qwen235b
...
Add Qwen 3 235B Instruct to Cerebras
2025-08-26 00:36:07 +08:00
Frank
6144f84d79
Merge pull request #158 from Mahamed-Belkheir/deepseek-3.1-updates
...
add: chutes deepseek v3.1 and thinking model, update deepseek provider context
2025-08-26 00:35:54 +08:00
Frank
b7d964df77
Merge pull request #143 from d3vr/add-mistral-3.1-medium
...
Add: new Mistral Medium 3.1 and older Medium 3
2025-08-26 00:28:47 +08:00
Frank
8ca8325d2e
test
2025-08-25 12:14:25 -04:00
Frank
fec79a992c
Merge pull request #157 from rekram1-node/deepseek-v3.1
...
add deepseek v3.1
2025-08-25 23:09:41 +08:00
vamsimnet
e38ffce883
Merge branch 'fastrouter' of https://github.com/vamsimnet/models.dev into fastrouter
2025-08-25 12:40:04 +05:30
vamsimnet
26864dc8f0
change fill in logo svg file
2025-08-25 12:39:38 +05:30
Hubert Marek Pysklo
7340a9826e
model_id
2025-08-24 21:11:45 -07:00
Hubert Marek Pysklo
54500283f9
add Qwen 3 235B Instruct
2025-08-24 21:08:23 -07:00
Mason
a6c8accdf8
Add provider submodel and fix to new prices
2025-08-25 05:34:56 +08:00
Mahamed-Belkheir
7d34f2e678
add: chutes deepseek v3.1 and thinking model, update deepseek's chat and reasoner context
2025-08-24 11:13:48 +00:00
Mason
7fbf92a95b
Add new provider: Submodel
2025-08-24 06:31:08 +08:00
rekram1-node
65a6de1f9d
add deepseek v3.1
2025-08-22 22:17:51 -05:00
vamsimnet
6bbbf33ab5
Merge branch 'sst:dev' into fastrouter
2025-08-22 12:16:32 +05:30
vamsimnet
3e134a0964
add logo.svg
2025-08-22 12:15:28 +05:30
Phillipe Lopes
8f59a4bdb3
feat: Add Gemini 2.5 Flash model configuration for google-vertex
2025-08-21 09:58:39 -03:00
Mahamed-Belkheir
7d417bd1b5
add chutes' updated qwen3 30b models ( #148 )
2025-08-21 08:51:13 -04:00
Aiden Cline
66b4b3bf43
fix: kimi k2 free ( #149 )
2025-08-21 06:52:12 -05:00
Timo Clasen
403366db6d
Remove preview from copilot gemini pro 2.5 ( #151 )
2025-08-21 06:51:57 -05:00
Aiden Cline
9e780af877
fix: opus id ( #154 )
2025-08-21 06:51:42 -05:00
vamsimnet
a9af994900
Merge branch 'sst:dev' into fastrouter
2025-08-21 11:40:23 +05:30
vamsimnet
26aa29566e
add and remove models
2025-08-21 11:39:05 +05:30
vamsimnet
e2f5790a19
change dates of gemini models
2025-08-21 10:40:10 +05:30
Jay
7a258ab8ca
Merge pull request #150 from rekram1-node/fix-opus
...
fix: gh copilot opus 4.1
2025-08-20 17:52:37 -04:00
rekram1-node
549f408671
fix: gh copilot opus 4.1
2025-08-20 10:59:07 -05:00
Dax Raad
448784a3ca
sync
2025-08-20 01:01:17 -04:00
Dax Raad
58becd61ad
sync
2025-08-20 00:59:22 -04:00
Dax Raad
fb31035d51
sync
2025-08-20 00:57:01 -04:00
Dax Raad
a28e9a4b90
add sonic
2025-08-20 00:52:22 -04:00
Jay V
95135a9bd6
fix logo
2025-08-18 19:52:15 -04:00
Jay
755ccf0552
Merge pull request #144 from Sawyerb/mercury-models
...
Adding Inception Logo
2025-08-18 19:25:55 -04:00
Frank
f42ddd35b7
Add Zhipu AI provider
2025-08-15 13:53:45 +08:00
Frank
6d3491f8d5
Rename Zhipu AI to z.ai
2025-08-15 13:20:07 +08:00
Sawyer Birnbaum
b54b5c47ca
Rename Logomark.svg to logo.svg
2025-08-14 16:14:36 -07:00
Sawyer Birnbaum
28f23ceef8
Add files via upload
2025-08-14 16:13:58 -07:00
Andreas Parusel
341d9574cc
Add gpt-5-chat.toml ( #142 )
2025-08-14 12:48:05 -04:00
d3vr
26553362f4
Add: new Mistral Medium 3.1 and older Medium 3
2025-08-14 12:04:43 +01:00
Dax Raad
70bfd50038
Rename Claude 4 Sonnet model file for consistent naming convention
2025-08-13 19:01:18 -04:00
ai13f
00f1cb68f9
Create gpt-5-mini.toml ( #140 )
2025-08-13 18:05:11 -04:00
GHOST
15efe2cfc6
docs(fix): provider info has additional requirements
2025-08-13 19:39:42 +01:00
Isaac Raja
4b381e74a5
fix: correct npm package reference for Google Vertex Anthropic provider ( #136 )
2025-08-13 07:14:06 -05:00
Frank
a52492c095
Add moonshot ai china provider
2025-08-13 12:20:01 +08:00
Frank
6a02667dd8
Merge pull request #134 from d3vr/add-glm-45v
...
Add: GLM-4.5v
2025-08-13 00:07:50 -04:00
Jay V
09a2cc1e82
more logos
2025-08-12 19:44:18 -04:00
Jay V
19b9af7e30
displaying logos, adding more
2025-08-12 19:32:14 -04:00
Jay V
f7cbcec648
Adding docs for logos
2025-08-12 17:18:32 -04:00
Jay V
6f264bb345
adding svg logos
2025-08-12 16:54:51 -04:00
Jay V
f01842d5c4
adding agents.md
2025-08-12 15:02:06 -04:00
cork89
687fc2a859
Add multiple model searching
2025-08-12 09:01:08 -04:00
d3vr
e429b2e624
Add: GLM-4.5v
2025-08-11 16:17:47 +01:00
Frank
429b76581c
Add moonshot ai provider
2025-08-08 17:57:50 -04:00
Frank
6868e74ed9
Merge pull request #128 from kevcube/patch-2
...
chore: copilot/gpt-5 reduce context
2025-08-08 17:33:02 -04:00
Frank
56ff56bd25
Merge pull request #123 from Reidaa/lmstudio-gpt-oss
...
Add GPT OSS (20b only) to LM Studio provider
2025-08-08 17:32:04 -04:00
Frank
bd27b40bec
Merge pull request #118 from ben-vargas/vercel-gpt-oss
...
Vercel: Add GPT OSS models
2025-08-08 17:31:14 -04:00
Frank
78e7d13026
Merge pull request #117 from d3vr/chutes-together-gpt-oss
...
Chutes & TogetherAI: Added gpt-oss-120b
2025-08-08 17:30:55 -04:00
Frank
3f489fd309
Merge pull request #119 from Good1Cheese/dev
...
add qwen/qwen3-235b-a22b-thinking-2507 on openrouter
2025-08-08 17:29:54 -04:00
Frank
25adf12a2d
fix info
2025-08-08 17:29:19 -04:00
Frank
8612c65a24
Merge pull request #127 from lentil32/feat/add-gpt5-azure-models
...
Add GPT-5 model configs for Azure
2025-08-08 17:26:32 -04:00
Frank
4c1de11f08
fix info
2025-08-08 17:23:37 -04:00
Frank
93e325de60
Merge pull request #130 from ImTheLeviDR/patch-3
...
Create gpt-5-nano.toml
2025-08-08 17:18:45 -04:00
Frank
0ab1d1ad71
Merge pull request #131 from ImTheLeviDR/patch-4
...
Create gpt-5-mini.toml
2025-08-08 17:18:41 -04:00
Frank
b856f8e0ac
Merge pull request #129 from ImTheLeviDR/patch-1
...
Create gpt-5.toml
2025-08-08 17:18:22 -04:00
Frank
fef3780944
fix info
2025-08-08 17:17:41 -04:00
Frank
765ad56ab6
fix info
2025-08-08 17:17:19 -04:00
Frank
1b7cb8074d
fix info
2025-08-08 17:16:42 -04:00
Frank
8753d3ba21
Merge pull request #120 from nickdowse-stripe/update-gpt4-pricing
...
Update OpenAI GPT-4 input/output token pricing
2025-08-08 17:10:25 -04:00
Frank
13b6ab800e
update cache read cost for gpt-5 models
2025-08-08 17:09:56 -04:00
Frank
e24d61197d
typo
2025-08-08 17:03:33 -04:00
Frank
55750ec7f7
typo
2025-08-08 17:03:19 -04:00
Frank
8eba67ee46
sync
2025-08-08 17:03:09 -04:00
Frank
5cae032f72
Merge pull request #125 from d3vr/gpt-5-chat
...
Add gpt-5-chat-latest
2025-08-08 16:57:07 -04:00
Tomas Slusny
5a78e3d0a9
Add API endpoints for Anthropic and Google openai compatible
...
Google: https://ai.google.dev/gemini-api/docs/openai
Anthropic: https://docs.anthropic.com/en/api/openai-sdk
Signed-off-by: Tomas Slusny <slusnucky@gmail.com >
2025-08-08 13:10:07 +02:00
TheLeviDR
6ae05850f0
Create gpt-5-mini.toml
2025-08-08 10:37:51 +02:00
TheLeviDR
248eefc6a1
Create gpt-5-nano.toml
2025-08-08 10:35:33 +02:00
TheLeviDR
3b6ee56e42
Create gpt-5.toml
2025-08-08 10:31:23 +02:00
Kevin
1502837fa6
chore: copilot/gpt-5 reduce context
...
I received an error when my context was over 128k, updating model.
2025-08-08 12:48:40 +08:00
lentil32
06e7859933
Add GPT-5 model configs for Azure
2025-08-08 12:48:18 +09:00
Boston Cartwright
f7d8b3932a
add gpt-5 model config for github-copilot ( #126 )
2025-08-07 15:57:59 -04:00
d3vr
d247a07754
gpt-5-chat: fix output token count
2025-08-07 19:38:01 +01:00
d3vr
dbb76290e5
Add gpt-5-chat to OpenRouter too
2025-08-07 19:36:52 +01:00
Andrew Barba
ebb2f73cd5
chore(vercel): gpt-5 ( #124 )
2025-08-07 14:32:38 -04:00
d3vr
a21767e993
Add gpt-5-chat-latest
2025-08-07 19:32:22 +01:00
Dax Raad
d4400a06bb
disable temperature
2025-08-07 14:02:14 -04:00
Fayçal Mitidji
70397b8045
Add new GPT-5 models ( #122 )
2025-08-07 12:59:07 -05:00
Thomas KEMKEMIAN
ab1a75f3ef
Add GPT OSS (20b only) to LM Studio provider
2025-08-07 19:22:41 +02:00
Nick Dowse
37f1d59ef0
Update OpenAI GPT-4 input/output token pricing
2025-08-07 10:33:52 -04:00
Good1Cheese
5e6997110a
add qwen/qwen3-235b-a22b-thinking-2507 on openrouter
2025-08-07 13:07:39 +09:00
Ben Vargas
a69d3dacdd
Add GPT OSS models to Vercel provider
...
- Add gpt-oss-120b with pricing $0.10/$0.50 per million tokens
- Add gpt-oss-20b with pricing $0.07/$0.30 per million tokens
- Both models support 131K context, 32K output, reasoning, and tool calling
- Pricing based on Vercel's AI Gateway documentation
2025-08-06 16:28:12 -06:00
d3vr
63ef6301e3
Chutes: Add gpt-oss-120b
2025-08-06 14:48:38 +01:00
d3vr
06e76672c5
TogetherAI: add gpt-oss-120b
2025-08-06 12:40:27 +01:00
vamsimnet
089a3738a8
add qwen model
2025-08-06 13:26:14 +05:30
vamsimnet
297715a9ff
Removed .iml and .xml files from Git tracking and added to .gitignore
2025-08-06 13:02:22 +05:30
vamsimnet
db4bc6557a
add models
2025-08-06 12:59:25 +05:30
vamsimnet
40b40ad039
add models
2025-08-06 12:36:38 +05:30
vamsi.h
75e6804ca7
add open ai gpt 4.1
2025-08-06 11:38:00 +05:30
Fayçal Mitidji
8cdcfe09c0
Chutes: added missing models, updated costs and context windows ( #111 )
2025-08-05 13:56:49 -04:00
Fayçal Mitidji
3907a2231d
Groq, Cerebras, Fireworks: Add new GPT OSS models ( #114 )
...
* Openrouter: Add new GPT OSS models
* Added new GPT models to Groq, Fireworks and Cerebras
2025-08-05 13:50:42 -04:00
Maaz Chowdhry
0adfd65bc1
Add Claude Opus 4.1 model configurations across multiple providers ( #112 )
...
* add Claude Opus 4.1 model configurations across multiple providers
* remove cost parameters from githyb-copilot opus 4.1
2025-08-05 13:50:09 -04:00
Dax Raad
7254aab04d
add opus 4.1
2025-08-05 12:40:43 -04:00
Frank
3a5a74901f
Merge pull request #110 from Mahamed-Belkheir/add-glm-4.5-fp8
...
add GLM-4.5-FP8 to chutes provider
2025-08-05 11:15:29 -04:00
Frank
6912c2b86f
sync
2025-08-05 11:14:21 -04:00
Mahamed-Belkheir
976cdd7197
add GLM-4.5-FP8 to chutes provider
2025-08-05 14:42:02 +00:00
Frank
74b91dc710
sync
2025-08-04 21:32:07 -04:00
Frank
69d051f56f
add opencode provider
2025-08-04 21:19:33 -04:00
Frank
8a3afb1543
Add LM Studio provider
2025-08-04 02:03:32 -04:00
Frank
937796bc23
Merge pull request #108 from sgoedecke/sgoedecke/add-cost-to-github-models
...
Add cost field to GitHub Models provider models
2025-08-04 01:44:23 -04:00
Sean Goedecke
8ad67cbe5d
Add cost field to GitHub Models provider models
2025-08-04 00:23:40 +00:00
Frank
73d850748e
Merge pull request #107 from joshualipman123/add-cerebras-via-vercel-ai-gateway
...
Add cerebras provided qwen3 coder via vercel ai gateway
2025-08-03 17:35:05 -04:00
Dax Raad
b10a1a050a
add posthog
2025-08-03 15:12:50 -04:00
joshualipman123
f1b6c7a46c
Add cerebras provided qwen3 coder via vercel ai gateway
2025-08-03 11:57:18 -07:00
Frank
39dc586458
User worker to serve the site and api
2025-08-03 14:16:27 -04:00
Frank
27889b89ec
Merge pull request #100 from Sawyerb/mercury-models
...
Adding Mercury Models
2025-08-02 21:25:37 -04:00
Frank
6e2dbb807b
sync
2025-08-02 21:12:04 -04:00
Frank
1e2f933330
Add Zhipu AI provider
2025-08-02 21:01:12 -04:00
Sawyer Birnbaum
f2c6825755
Update mercury.toml
2025-08-02 17:42:05 -07:00
Sawyer Birnbaum
7b38f54bb1
Update mercury-coder.toml
2025-08-02 17:41:42 -07:00
Frank
294d9c3fa4
Merge pull request #105 from shariqriazz/feat/provider-chutes
...
add chutes provider
2025-08-02 20:27:04 -04:00
Frank
05d8db3f3c
sync
2025-08-02 20:26:27 -04:00
Frank
477a2daec8
Merge pull request #104 from d3vr/fix-cerebras-qwen3-coder-cost
...
fix: Corrected Cerebras Qwen 3 Coder cost
2025-08-02 20:24:08 -04:00
Frank
cc48fccb0e
sync
2025-08-02 20:22:51 -04:00
Frank
aed58ce1e6
remove comments
2025-08-02 20:21:35 -04:00
Frank
6d12b216bb
Merge pull request #99 from d3vr/add-modelscope-provider
...
feat: add ModelScope provider with 8 models
2025-08-02 20:20:13 -04:00
Frank
cce82d5301
Merge pull request #98 from 0xrsydn/dev
...
feat: Add Qwen3 30B A3B-Instruct 2507 on OpenRouter
2025-08-02 20:08:06 -04:00
0xrsydn
de198555ac
add mistral:codestra- 2508 on openrouter
2025-08-03 04:34:41 +07:00
Chris Covington
aa91010df3
Add Horizon Beta to OpenRouter provider ( #106 )
2025-08-01 21:24:45 -04:00
Shariq Riaz
818590d998
feat(chutes): add provider + models (DeepSeek V3 0324, DeepSeek R1 0528, Kimi K2 Instruct, Qwen3 Coder 480B A35B FP8, GLM-4.5 Air, Mistral Small 3.2 24B Instruct 2506, Devstral Small 2505)
2025-08-02 03:49:53 +05:00
d3vr
7678a063e2
fix: Corrected Cerebras Qwen 3 Coder cost
2025-08-01 22:22:40 +01:00
Dax Raad
9e817b0e42
add cerebras provider
2025-08-01 17:15:35 -04:00
Dax Raad
2e3f718c40
enable worker logs
2025-07-31 23:31:22 -04:00
Sawyer Birnbaum
15f8ff29d0
Update mercury-coder.toml
2025-07-31 15:33:14 -07:00
Sawyer Birnbaum
e0b083c33d
Update mercury.toml
2025-07-31 15:32:19 -07:00
Sawyer Birnbaum
de9d11b8c7
Update provider.toml
2025-07-31 15:31:44 -07:00
Sawyer Birnbaum
bba66f3a88
Create Mercury Coder
2025-07-31 15:27:58 -07:00
Sawyer Birnbaum
c06b0bdd77
Create Mercury Model
2025-07-31 15:27:25 -07:00
Sawyer Birnbaum
1b3a98ecec
Create Inception provider
2025-07-31 15:26:52 -07:00
d3vr
14d91be19c
Add ModelScope provider models
...
- Added 6 Qwen models:
- Qwen3-Coder-480B-A35B-Instruct
- Qwen3-235B-A22B-Thinking-2507
- Qwen3-235B-A22B-Instruct-2507
- Qwen3-30B-A3B-Instruct-2507
- Qwen3-30B-A3B-Thinking-2507
- Qwen3-Coder-30B-A3B-Instruct
- Added ZhipuAI/GLM-4.5
- Added moonshotai/Kimi-K2-Instruct
2025-07-31 18:03:54 +01:00
d3vr
81bf97664a
Add ModelScope provider
...
- New provider for ModelScope API
- Uses OpenAI-compatible SDK
- Requires MODELSCOPE_API_KEY environment variable
2025-07-31 17:37:45 +01:00
0xrsydn
2e34292d04
add qwen3 30b a3b instruct 2507 on openrouter provider
2025-07-31 23:36:22 +07:00
Frank
0c69e58ba9
Merge pull request #95 from d3vr/add-wandb-provider
...
feat: add Weights & Biases provider with 10 models
2025-07-31 10:54:18 -04:00
Frank
c3cb4e116b
Merge pull request #97 from sst/opencode/issue63-20250731144520
...
Fixed Gemini context windows: 2M→128K, 2M→1M
2025-07-31 10:53:13 -04:00
Frank
602cd057a5
sync
2025-07-31 10:52:54 -04:00
opencode-agent[bot]
91c28a8f57
Fixed Gemini context windows: 2M→128K, 2M→1M
...
Co-authored-by: fwang <fwang@users.noreply.github.com >
2025-07-31 14:46:39 +00:00
Frank
dac7e214c3
Merge pull request #96 from sst/opencode/issue86-20250731140830
...
Fixed Claude Sonnet 4 GitHub Copilot config
2025-07-31 10:46:19 -04:00
opencode-agent[bot]
1fe1133add
Fixed Claude Sonnet 4 GitHub Copilot config
...
Co-authored-by: fwang <fwang@users.noreply.github.com >
2025-07-31 14:09:57 +00:00
Frank
70837a8c6a
Setup opencode action
2025-07-31 10:08:00 -04:00
d3vr
3595170026
refactor: reorganize W&B models into AI lab subfolders
...
Move all model configurations into proper AI lab subdirectories with
correct case-sensitive naming to match model IDs exactly.
2025-07-31 14:41:36 +01:00
d3vr
01095082ed
feat: add Weights & Biases model configurations
...
Add 10 model configurations for W&B provider with accurate context windows,
pricing, and modalities based on official documentation.
2025-07-31 14:34:07 +01:00
d3vr
516398299e
feat: add Weights & Biases provider
...
Add new provider configuration for Weights & Biases inference API with OpenAI-compatible interface.
2025-07-31 14:19:23 +01:00
Frank
973b50e3b4
Set Qwen3-235B-A22B-Thinking-2507 reasoning to true
...
closes #92
2025-07-31 08:36:50 -04:00
Frank
a6ecdc75c9
Merge pull request #94 from d3vr/add-openrouter-horizon-alpha
...
feat: add OpenRouter Horizon Alpha model
2025-07-31 08:30:59 -04:00
d3vr
4ef310c78e
feat: add OpenRouter Horizon Alpha model
2025-07-31 12:10:05 +01:00
Nick Galluzzo
838d918a08
fix: correct naming for z-ai/glm-4.5-air:free ( #93 )
2025-07-31 05:28:15 -05:00
Frank
60f2d80bc0
fix doc link
2025-07-30 17:13:30 -04:00
Frank
2bc25f1c57
Merge pull request #89 from gary149/add-new-hf-models
...
Add new Hugging Face models and fix file naming conventions
2025-07-30 08:41:55 -04:00
Frank
fd01d421fb
Merge pull request #91 from nick-galluzzo/feat/add-glm-4.5-air-free
...
feat: Add support for GLM 4.5 Air (free) model
2025-07-30 08:41:14 -04:00
Frank
696dc5e2f4
Merge pull request #90 from nick-galluzzo/fix/glm4.5-naming
...
fix: Remove "Air" from OpenRouter GLM 4.5
2025-07-30 08:40:52 -04:00
Nick Galluzzo
ddca8005a1
feat: Add support for GLM 4.5 Air (free) model
2025-07-30 11:49:04 +07:00
Nick Galluzzo
c297cbdf55
fix: Remove "Air" from OpenRouter GLM 4.5
2025-07-30 11:43:13 +07:00
Victor Muštar
798bee7337
Update Qwen3-235B-A22B-Thinking-2507 model configuration
...
- Update model metadata and capabilities
2025-07-30 01:22:12 +02:00
Victor Muštar
6a62b0eee0
Update GLM-4.5 model configuration
...
- Add cost information for input/output pricing
- Update model metadata
2025-07-30 01:19:48 +02:00
Victor Muštar
b5b15e8bae
Add new Hugging Face models and fix file naming conventions
...
- Rename DeepSeek model files to use proper capitalization
- Rename Kimi model file to use proper capitalization
- Add new Qwen3-235B-A22B-Thinking-2507 model
- Add GLM-4.5 and GLM-4.5-Air models from zai-org
2025-07-30 01:17:12 +02:00
Frank
69e91b1cee
Merge pull request #74 from andrewneilson/copilot-july2025
...
(issue #70 ) Add copilot pro+ models and remove unsupported o1
2025-07-29 10:59:15 -04:00
Frank
439099c412
Merge pull request #73 from gary149/reorganize-hf-models
...
Reorganize Hugging Face models and fix model id
2025-07-29 10:58:09 -04:00
Frank
27a1005a63
sync
2025-07-29 10:24:38 -04:00
Frank
7a9f66a08a
Add alibaba cloud provider
2025-07-29 10:21:12 -04:00
Frank
fc90194ab4
Merge pull request #60 from isaacraja/feat/add-vertex-claude-models
...
feat: add Google Vertex AI Anthropic provider with Claude models
2025-07-29 09:39:25 -04:00
Frank
349010a3d0
Merge pull request #75 from obiMadu/dev
...
Add v0 models to Vercel AI Gateway
2025-07-29 09:32:47 -04:00
Frank
d16da2b790
use symlinks
2025-07-29 09:31:43 -04:00
Frank
0840f4ba90
Merge pull request #78 from Nutlope/dev
...
Add Together AI as a provider
2025-07-29 09:19:05 -04:00
Frank
1195881a06
Merge pull request #80 from nick-galluzzo/fix/deepseek-tool-allowance
...
fix: Disable tool_call for deepseek-r1t2-chimera:free
2025-07-29 09:01:00 -04:00
Frank
02df845c58
Merge pull request #87 from simon-wg/patch-1
...
Adds codex mini to azure model list
2025-07-29 08:59:01 -04:00
Frank
f08044362c
Merge pull request #85 from 0xrsydn/dev
...
Added GLM 4.5 Air & Fixed GLM 4.5 TOML
2025-07-29 08:56:18 -04:00
Simon Westlin Green
8f96f4068a
Create codex-mini.toml
...
Create azure codex mini model
2025-07-29 09:27:30 +02:00
0xrsydn
d8ec134860
added glm 4.5 air on openrouter, fixed context & output limit, fix reasoning to true as it supports reasoning parameter
2025-07-29 11:20:09 +07:00
Frank
db9731198f
preserve provider and model id cases
2025-07-28 23:17:08 -04:00
Frank
291f4e6fc5
sync
2025-07-28 22:45:31 -04:00
Frank
e891b5042a
Add deepinfra provider
2025-07-28 22:27:34 -04:00
Frank
48bb64c4ee
Merge pull request #79 from yihuikhuu/qwen3-coder-free
...
feat: add qwen3 coder free for openrouter
2025-07-27 19:54:31 -04:00
Frank
fe98f371e6
Merge pull request #62 from gutomotta/fireworks-ai
...
Add Fireworks AI provider with some models useful for writing code
2025-07-27 19:53:30 -04:00
Frank
ba5067ac4b
Merge pull request #81 from nick-galluzzo/feature/add-kimi-k2-free
...
feat: add kimi-k2:free model
2025-07-27 19:51:57 -04:00
Frank
fbdf227b45
Include model path in validation error
2025-07-27 19:41:45 -04:00
Frank
2060d3656b
Merge pull request #55 from dmarjenburgh/venice-ai
...
Add Venice AI provider and 13 associated model configurations
2025-07-27 19:39:35 -04:00
Frank
5ee76694e1
Merge pull request #41 from hunkimForks/dev
...
feat: Add Upstage Solar models support
2025-07-27 19:38:05 -04:00
Frank
cb261c479d
Merge pull request #40 from mrmps/dev
...
Adds models provided by Inference.net
2025-07-27 19:36:55 -04:00
Frank
49ab5c5566
Merge pull request #34 from dtrugman/add-requesty-model-provider
...
Add Requesty provider
2025-07-27 19:35:19 -04:00
Frank
1f1d1431f6
Merge pull request #30 from sgoedecke/sgoedecke/add-github-models-provider
...
Add GitHub Models provider
2025-07-27 19:22:50 -04:00
Nick Galluzzo
3580b08f0a
feat: add kimi-k2:free model
2025-07-26 16:28:46 +07:00
Nick Galluzzo
bf6edbeeac
chore: remove new line at EOF
2025-07-26 16:14:34 +07:00
Nick Galluzzo
7ebcacc095
fix: deepseek-r1t2-chimera:free to not allow tool calls
2025-07-26 16:01:27 +07:00
Aiden Cline
206fe69690
fix: qwen3-32b ( #76 )
2025-07-26 01:09:38 -04:00
Yihui Khuu
4d1db6e0ac
feat: add qwen3 coder free for openrouter
2025-07-26 13:48:59 +10:00
Hassan El Mghari
7637e22548
fixed typo
2025-07-25 16:34:14 -04:00
Hassan El Mghari
aa50022ef6
added Together AI as a provider
2025-07-25 16:32:27 -04:00
Obi Madu
7ae5fa9cf8
feat: remove 1.5 lg
2025-07-25 01:59:55 +01:00
Obi Madu
bdb0b041b1
feat: add v0 models to vercel ai gateway
2025-07-25 01:58:28 +01:00
Andrew Neilson
c585c38f91
(issue #70 ) Add copilot pro+ models and remove unsupported o1
2025-07-23 17:46:54 -07:00
Victor Muštar
e4b9b6acd6
Reorganize Hugging Face models into vendor-specific directories
...
Move deepseek, Qwen, and moonshotai models into their own subdirectories for better organization
2025-07-23 11:19:55 +02:00
spoons-and-mirrors
affbfa8012
Add Openrouter Qwen3 Coder ( #71 )
2025-07-22 20:34:20 -04:00
lolo md
755849cd90
add info for gpt-3.5-turbo ( #67 )
2025-07-22 20:22:50 -04:00
spoons-and-mirrors
6bfff28e20
Add Openrouter Qwen3 235B A22B Instruct 2507 model configurations ( #69 )
2025-07-21 15:26:37 -05:00
Victor Muštar
d1c1306626
feat: add Hugging Face Inference provider ( #61 )
...
* feat: add Hugging Face Inference provider
- Add Hugging Face provider configuration with OpenAI-compatible API
- Include moonshotai/Kimi-K2-Instruct model with Groq routing
- Include deepseek-ai/DeepSeek-V3-0324 model
- Include deepseek-ai/DeepSeek-R1-0528 model
- All model configurations match their implementations in other providers
* names = huggingface ids
* Update model names in HuggingFace TOML files
2025-07-19 10:34:15 -04:00
Dax Raad
151da87a50
sync
2025-07-19 10:05:36 -04:00
Dax Raad
fd9750d2c6
fix caps
2025-07-19 10:00:22 -04:00
Dax Raad
0f33de3ad9
added vercel ai gateway and renamed to v0
2025-07-19 09:52:33 -04:00
Guto Motta
4969f1ee7c
Add Fireworks AI provider with some models useful for writing code
2025-07-18 11:09:32 -03:00
Isaac Raja
07c2f532c7
fix: change provider name from 'Vertex AI Anthropic' to 'Vertex'
...
- Update provider.toml name field to match maintainer feedback
- Keep consistent with existing Vertex provider naming
2025-07-17 16:14:09 +05:30
Isaac Raja
32c67d697c
feat: add Google Vertex AI Anthropic provider with Claude models
...
- Add google-vertex-anthropic provider supporting @ai-sdk/google-vertex/anthropic
- Include 5 Claude models: claude-3-5-sonnet@20241022, claude-3-5-haiku@20241022, claude-3-7-sonnet@20250219, claude-sonnet-4@20250514, claude-opus-4@20250514
- Follow Vercel AI SDK naming convention with @YYYYMMDD suffix format
- Match existing schema with pricing, context limits, and modalities
- Follows pattern established by Google Vertex Gemini provider
2025-07-17 15:39:56 +05:30
Kendell R
a0eedfb30f
adjust mistralai/devstral-small-2505:free context limit ( #49 )
2025-07-16 14:37:53 -04:00
Dan Hernandez
1b69a4d2da
Delete providers/openai/models/gpt-4.5-preview.toml ( #56 )
2025-07-16 07:19:59 -05:00
Rico Sta. Cruz
428ee4d7ab
feat(openrouter): replace Gemini 2.5 Flash preview models with stable version ( #58 )
2025-07-16 07:19:00 -05:00
Daniel Marjenburgh
3d8fc6446b
Mark all Venice AI models as having open weights in configuration files
2025-07-15 21:52:25 +02:00
Dax Raad
ec3c80f071
add haiku to openrouter
2025-07-15 13:07:49 -04:00
Daniel Marjenburgh
0cb5c4b515
Update Venice AI provider configuration to include environment variable setup
2025-07-15 17:55:04 +02:00
Daniel Marjenburgh
a1a4d02ab8
Add Venice AI provider and 13 associated model configurations
2025-07-15 16:40:27 +02:00
Kendell R
077a2dc7c6
fix: Kimi K2 reasoning and attachment flags in OpenRouter config ( #51 )
...
* Fix Kimi K2 reasoning flag in OpenRouter config
Kimi K2 is a regular instruct model, not a reasoning model like o1.
Set reasoning = false to correctly reflect its capabilities.
🤖 Generated with [Claude Code](https://claude.ai/code )
Co-Authored-By: Claude <noreply@anthropic.com >
* Disable attachment
---------
Co-authored-by: Claude <noreply@anthropic.com >
2025-07-15 06:20:41 -05:00
Jeremy Hon
0a256f87a2
fix: reduce kimi k2 output tokens from 131072 to 16384 ( #54 )
2025-07-15 06:18:32 -05:00
Kendell R
7863a8e0a8
Add Kimi K2 Instruct model support for Groq ( #52 )
...
* Add Kimi K2 Instruct model support for Groq
Adds moonshotai/kimi-k2-instruct model configuration for Groq provider.
- 131k context and output tokens
- Open source model with tool calling capabilities
🤖 Generated with [Claude Code](https://claude.ai/code )
Co-Authored-By: Claude <noreply@anthropic.com >
* Disable attachment
---------
Co-authored-by: Claude <noreply@anthropic.com >
2025-07-15 00:27:32 -04:00
Maaz Chowdhry
2b0849aa20
Add OpenRouter free model endpoints ( #38 ) ( #48 )
...
* Added moonshotai/kimi-k2
* Add OpenRouter free model endpoints (#38 )
2025-07-13 22:49:10 -04:00
Rafal Kondratowicz
9384b47617
Add devstral models to openrouter ( #35 )
2025-07-11 21:35:33 -04:00
Timo Clasen
5945690d66
Update copilot sonnet 4 model name ( #36 )
2025-07-11 20:12:20 -04:00
Maaz Chowdhry
732c4198f6
Added moonshotai/kimi-k2 ( #47 )
2025-07-11 17:56:09 -04:00
Rasyidan Akbar F
9e4f8a730f
Add Devstral Models to Openrouter ( #45 )
...
* Add devstral models to openrouter
* also add newest devstral small & medium
---------
Co-authored-by: Rafal Kondratowicz <rkondratowicz@users.noreply.github.com >
2025-07-11 17:35:16 -04:00
Dax Raad
1295b9dd9a
mistral updates
2025-07-10 11:01:02 -04:00
Dax Raad
8b747baa3d
temporary lower grok 4 output limit
2025-07-10 10:15:20 -04:00
Dax Raad
d3e7a1d55a
grok-4 openrouter
2025-07-10 07:35:40 -04:00
Kevin
852d705a7e
Create grok-4.toml ( #43 )
2025-07-10 07:32:05 -04:00
Jay
8a9d20dad1
Create LICENSE
2025-07-09 19:11:53 -04:00
Sung Kim
830a8b0b61
feat: Add Upstage Solar models support
...
Add support for Upstage's Solar models, bringing Korea's #1 LLM provider to models.dev.
Upstage is a leading AI company in Korea, renowned for their high-performance Solar LLM series. This addition introduces two powerful Solar models:
�� Solar Pro2:
- Advanced reasoning capabilities with chain-of-thought support
- Tool calling and function execution
- 65,536 context window with 8,192 output tokens
- Competitive pricing at /bin/zsh.25/M tokens (input/output)
- Knowledge cutoff: 2025-03
⚡ Solar Mini:
- Efficient, cost-effective model for production workloads
- Tool calling support without reasoning overhead
- 32,768 context window with 4,096 output tokens
- Budget-friendly at /bin/zsh.15/M tokens (input/output)
- Knowledge cutoff: 2024-09
Technical Implementation:
- Uses OpenAI-compatible API endpoint (https://api.upstage.ai )
- Requires UPSTAGE_API_KEY environment variable
- Full text input/output modality support
- Temperature control for both models
- Comprehensive TOML configuration following project standards
This integration expands models.dev's coverage of international AI providers, particularly strengthening representation of the Korean AI ecosystem.
2025-07-10 05:51:34 +09:00
Michael Ryaboy
0f732188cf
Merge pull request #1 from mrmps/codex/add-inference.net-llm-models-and-pricing
...
Add Inference provider models
2025-07-09 12:53:47 -07:00
Michael Ryaboy
cc01d0d47f
Add Inference provider models
2025-07-09 12:49:56 -07:00
Dax Raad
7d25c5eee4
switch to openai compatible provider for openrouter
2025-07-02 14:53:54 -04:00
Daniel Trugman
4e559d647b
Add requesty provider
2025-07-01 11:13:27 +01:00
Frank
6fd530b6b4
Merge pull request #33 from wienans/openrouter/models
...
Add more models from openrouter
2025-07-01 01:16:22 -04:00
Frank
1c7c8cc2fc
Update o4-mini.toml
2025-07-01 01:13:42 -04:00
Frank
7a25a69f7e
Merge pull request #28 from danfhernandez/feat/add-deep-research-models
...
feat: add OpenAI o3-deep-research and o4-mini-deep-research models
2025-07-01 01:11:54 -04:00
Frank
3427662f41
Merge pull request #32 from maskdotdev/patch-1
...
Fix modalities.output typo in README.md
2025-07-01 00:47:13 -04:00
wienans
c575fcfef3
Add more openai models
2025-06-29 09:01:49 +00:00
wienans
d30cd29066
Add Openrouter xAI
2025-06-29 08:52:30 +00:00
Kiyotaka
f2d0ce14b5
Fix modalities.output typo in README.md
2025-06-28 07:24:27 -05:00
Jay V
1f9b6fbd26
style changes to web
2025-06-27 16:51:06 -04:00
Sean Goedecke
3b2d4a19a8
Add GitHub Models provider
2025-06-27 09:44:03 +00:00
Frank
bc307aa078
Add openrouter gemini 2.5 pro model
2025-06-27 02:12:06 -04:00
Dan Hernandez
9009a74440
feat: add OpenAI o3-deep-research and o4-mini-deep-research models
2025-06-26 15:05:59 -04:00
Frank
7dffb5d031
Add cost for openrouter models
...
Closes #25
2025-06-24 16:18:40 -04:00
Frank
d9a1adb1d5
Restructure nested model ids
2025-06-24 15:29:11 -04:00
Frank
d3e9843abd
Updated modalities structure
2025-06-23 17:41:14 -04:00
Frank
b166d2a5de
Update README.md
2025-06-23 17:15:19 -04:00
Frank
0e7a52fe0c
Render cost to 2 decimals
2025-06-23 17:01:06 -04:00
Frank
320c099c02
Merge pull request #21 from ndraiman/openrouter
...
Added openrouter provider and top 10 programming models
2025-06-23 16:53:34 -04:00
Frank
d2ab3fddc5
sync
2025-06-23 16:52:39 -04:00
Frank
c8372a9f91
Merge branch 'dev' into pr/21
2025-06-23 15:54:29 -04:00
Frank
7d20df523e
Merge pull request #23 from obiMadu/dev
...
Add Vertex AI Models
2025-06-23 15:44:21 -04:00
Frank
e2ec99e9a3
sync
2025-06-23 15:43:27 -04:00
Frank
bf825e8e17
Merge branch 'dev' into pr/23
2025-06-23 15:23:49 -04:00
Frank
89cf9c63b9
Merge pull request #24 from banjo/fix/gpt-4-correct-name
...
Update name for GPT-4 in OpenAI provider
2025-06-23 15:10:23 -04:00
Frank
6fe5e0de7c
Rename open to open_weights
2025-06-23 15:05:42 -04:00
Frank
8f4c403b64
Track if model weights are public
2025-06-23 14:24:37 -04:00
Anton Ödman
e9d68c4edb
Update name for GPT-4 in OpenAI provider
2025-06-23 14:26:45 +02:00
Frank
a418631ad4
Add missing release date
2025-06-22 22:30:44 -04:00
Frank
413b00aff4
Merge pull request #20 from aryasaatvik/feat/model-dates
...
feat: add release_date and last_updated fields
2025-06-22 22:24:09 -04:00
Frank
573c30c139
sync
2025-06-22 21:23:09 -04:00
Frank
69cc57f565
Mark release_date and last_updated required
2025-06-22 20:56:23 -04:00
Frank
e260395f83
Fix sorting reset to asc on page refresh
2025-06-22 20:55:26 -04:00
Dax
11be6a3025
Update provider.toml
2025-06-22 19:18:10 -04:00
Dax Raad
414cbe47aa
fix copilot names
2025-06-22 19:06:32 -04:00
Dax Raad
3eb8c0832c
fix env
2025-06-22 18:38:10 -04:00
Dax Raad
6fd1a5a776
add api field
2025-06-22 18:35:34 -04:00
Dax Raad
3d1e5cfee0
github copilot models
2025-06-22 18:34:07 -04:00
Obi.M
e9e89279f6
Merge branch 'sst:dev' into dev
2025-06-22 13:49:51 +01:00
Obi Madu
5e2363d6a0
feat: add vertex ai provider
2025-06-22 13:47:29 +01:00
Netanel Draiman
2e5a81ecab
claude-4-sonnet-20250522
2025-06-21 17:42:31 +03:00
Netanel Draiman
dca15642b4
Added openrouter provider and top 10 programming models
2025-06-21 15:51:43 +03:00
Saatvik Arya
96d57c90a5
chore: add @types/bun as a devDependency in package.json and bun.lock
...
- Included @types/bun version 1.2.16 in devDependencies for type definitions.
- Updated bun.lock to reflect the addition of @types/bun and related dependencies.
2025-06-21 14:18:22 +05:30
Saatvik Arya
6face3acb8
feat: implement URL state management for table sorting and filtering
...
- Added functions to manage URL query parameters for sorting and searching in the table.
- Implemented initialization of table state from URL parameters on page load and popstate events.
- Refactored search input handling to update URL parameters accordingly.
2025-06-21 14:18:04 +05:30
Saatvik Arya
77f330acb5
fix: add sortable cursor style to table header
2025-06-21 14:17:43 +05:30
Saatvik Arya
86b3368921
feat: add release date and last updated columns to rendered output
...
- Introduced new columns for Release Date and Last Updated in the rendered output.
- Updated the rendering logic to display corresponding model data for these fields.
2025-06-21 14:17:32 +05:30
Saatvik Arya
59ef568d79
fix: update release_date and last_updated for multiple models
...
- Updated release_date and last_updated fields for Anthropic Claude 2.1, Claude 2, DeepSeek Chat, Codestral, and Vercel models.
- Ensured all dates are accurate and follow the YYYY-MM-DD format.
2025-06-21 13:27:32 +05:30
Saatvik Arya
fbc87e3434
feat: add comprehensive release dates for all AI models
...
- Updated 151+ model files across 11 providers with accurate release_date and last_updated fields
- Added dates for OpenAI, Azure, Anthropic, Google, Amazon Bedrock, Meta Llama, DeepSeek, xAI, Mistral, Groq, and other providers
- Corrected Llama 4 model dates to accurate release date (2025-04-05)
- Aligned Azure OpenAI models with corresponding OpenAI model dates
- Verified DeepSeek model dates through web research
- All dates follow YYYY-MM-DD format as per schema requirements
2025-06-21 13:13:40 +05:30
Saatvik Arya
7c007ccf77
feat(schema): add release_date and last_updated fields
2025-06-21 12:14:03 +05:30
Frank
e3ecc39a94
Add tooltip
2025-06-20 17:54:21 -04:00
Frank
d29a6bb7f3
Update model name
2025-06-19 18:06:28 -04:00
Frank
c85cf693b5
Add cors
2025-06-19 17:54:56 -04:00
Frank
1feb325d51
refactor
2025-06-19 14:53:52 -04:00
Frank
381e37c4b1
Fix sorting
2025-06-19 14:50:27 -04:00
Frank
a727649beb
Reorder columns
2025-06-19 14:37:05 -04:00
Frank
ead281da3c
Update schema parsing
2025-06-19 14:22:53 -04:00
Frank
add11fd432
Update data
2025-06-19 13:54:57 -04:00
Frank
0b2fc87444
Update data
2025-06-19 13:36:12 -04:00
Frank
1a19484b8c
Update data
2025-06-19 12:59:13 -04:00
Frank
43c84718b8
Update data
2025-06-19 03:03:54 -04:00
Frank
edc4a464e5
Update data
2025-06-19 02:56:13 -04:00
Frank
60eddd6231
Update data
2025-06-19 02:26:41 -04:00
Frank
9247d455ab
Update modalities icon
2025-06-19 02:05:33 -04:00
Frank
f8edfc4978
Update data
2025-06-19 02:05:06 -04:00
Frank
72f4d75424
Update data for google models
2025-06-19 01:53:30 -04:00
Frank
0b87a750d0
Render knowledge, tool call, input and output modalities
2025-06-19 01:39:52 -04:00
Frank
84fe7fd3ab
Track tool_call, knowledge, and modalities
2025-06-19 01:28:00 -04:00
Frank
d7fa41c64d
organize css
2025-06-18 19:32:25 -04:00
Frank
26bfab18ea
change copied color
2025-06-18 19:23:01 -04:00
Frank
04575856fe
organize code
2025-06-18 19:10:22 -04:00
Frank
bb5c741e11
copy model id
2025-06-18 18:44:57 -04:00
Frank
da2b414136
Highlight useful columns
2025-06-18 18:31:36 -04:00
Frank
4d54b26a4a
render numbers better
2025-06-18 18:26:57 -04:00
Frank
f13c3d178a
Fix styling
2025-06-18 18:23:56 -04:00
Frank
aa0cca6366
cmd+k esc
2025-06-18 18:22:20 -04:00
Frank
763a34565b
cmd+k
2025-06-18 18:16:29 -04:00
Frank
46172f4159
add sorting
2025-06-18 17:58:41 -04:00
Dax Raad
cffe57f166
sync
2025-06-18 14:31:40 -04:00
Frank
74209c949a
Merge pull request #4 from adeleke5140/fix-input-color-in-dark-mode
...
fix(style): make input text readable in dark mode
2025-06-18 14:15:16 -04:00
Frank
54efd37f20
sync
2025-06-18 14:14:29 -04:00
Frank
54f207b2a6
Merge branch 'dev' into pr/4
2025-06-18 14:10:56 -04:00
Frank
799c921848
Update Morph provider
2025-06-18 14:09:45 -04:00
Frank
152baf7d53
Add documentation links for various providers in TOML files
2025-06-18 13:56:21 -04:00
Frank
937b3c3559
Merge pull request #5 from danielmerja/llama-models
...
Add new provider Llama (LLama API) and all models for the Llama API.
2025-06-18 13:37:11 -04:00
Frank
347f02a063
sync
2025-06-18 13:36:25 -04:00
Frank
14221a1222
Delete package-lock.json
2025-06-18 12:49:56 -04:00
Frank
461d6506a3
Merge branch 'dev' into pr/5
2025-06-18 12:45:46 -04:00
Frank
44919f5c9d
Merge pull request #14 from monotykamary/feat/add-google-gemini-2.5-models
...
feat(google): add gemini 2.5 pro, flash, and flash lite preview models
2025-06-18 09:23:28 -04:00
Tom X Nguyen
7acccd4471
feat(google): add gemini 2.5 pro, flash, and flash lite preview models
...
🤖 Generated with [opencode](https://opencode.ai )
Co-Authored-By: opencode <noreply@opencode.ai >
2025-06-18 10:20:59 +07:00
Terence Bezman
c40fcefb2b
fix height of github icon ( #13 )
2025-06-17 21:14:41 -04:00
Dax Raad
2af16036a5
sync
2025-06-17 20:41:38 -04:00
Daniel Merja
0f00fc5559
Fix model name formatting in Cerebras Llama configuration
2025-06-18 00:39:38 +00:00
Kenny
d3bfa6bec4
fix(style): make input text readable in dark mode
2025-06-17 00:41:17 +01:00