fix: bedrock devstral

feat: add GPT-5 series models to requesty provider

providers/abacus/models/gemini-3-pro-preview.toml

@@ -1,21 +0,0 @@
-name = "Gemini 3 Pro Preview"
-family = "gemini-pro"
-release_date = "2025-06-01"
-last_updated = "2025-06-01"
-attachment = true
-reasoning = true
-temperature = true
-tool_call = true
-open_weights = false
-
-[cost]
-input = 2.00
-output = 12.00
-
-[limit]
-context = 1_000_000
-output = 65_000
-
-[modalities]
-input = ["text", "image", "audio", "video"]
-output = ["text"]

providers/abacus/models/gpt-5.4.toml

@@ -0,0 +1,24 @@
+name = "GPT-5.4"
+family = "gpt"
+release_date = "2026-03-05"
+last_updated = "2026-03-05"
+attachment = true
+reasoning = true
+temperature = false
+knowledge = "2025-08-31"
+tool_call = true
+structured_output = true
+open_weights = false
+
+[cost]
+input = 2.50
+output = 15.00
+
+[limit]
+context = 1_050_000
+input = 922_000
+output = 128_000
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]

providers/alibaba-coding-plan-cn/models/MiniMax-M2.5.toml

@@ -0,0 +1,26 @@
+name = "MiniMax-M2.5"
+family = "minimax"
+release_date = "2026-02-12"
+last_updated = "2026-02-12"
+attachment = false
+reasoning = true
+temperature = true
+tool_call = true
+open_weights = true
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0
+output = 0
+cache_read = 0
+cache_write = 0
+
+[limit]
+context = 196_608
+output = 24_576
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/alibaba-coding-plan-cn/models/qwen3-max-2026-01-23.toml

@@ -17,7 +17,7 @@ cache_write = 0
 
 [limit]
 context = 262_144
-output = 65_536
+output = 32_768
 
 [modalities]
 input = ["text"]

providers/alibaba-coding-plan/models/MiniMax-M2.5.toml

@@ -18,8 +18,8 @@ cache_read = 0
 cache_write = 0
 
 [limit]
-context = 204_800
-output = 32_768
+context = 16_608
+output = 24_576
 
 [modalities]
 input = ["text"]

providers/alibaba-coding-plan/models/qwen3-coder-plus.toml

@@ -16,7 +16,7 @@ cache_read = 0
 cache_write = 0
 
 [limit]
-context = 1_048_576
+context = 1_000_000
 output = 65_536
 
 [modalities]

providers/alibaba-coding-plan/models/qwen3-max-2026-01-23.toml

@@ -17,7 +17,7 @@ cache_write = 0
 
 [limit]
 context = 262_144
-output = 65_536
+output = 32_768
 
 [modalities]
 input = ["text"]

providers/amazon-bedrock/models/moonshot.kimi-k2-thinking.toml

@@ -1,5 +1,6 @@
 name = "Kimi K2 Thinking"
 release_date = "2025-12-02"
+family = "kimi-thinking"
 last_updated = "2025-12-02"
 attachment = false
 reasoning = true

providers/amazon-bedrock/models/moonshotai.kimi-k2.5.toml

@@ -1,4 +1,5 @@
 name = "Kimi K2.5"
+family = "kimi"
 release_date = "2026-02-06"
 last_updated = "2026-02-06"
 attachment = false

providers/requesty/models/openai/gpt-5-chat.toml

@@ -0,0 +1,23 @@
+name = "GPT-5 Chat (latest)"
+family = "gpt-codex"
+release_date = "2025-08-07"
+last_updated = "2025-08-07"
+attachment = true
+reasoning = true
+temperature = true
+knowledge = "2024-09-30"
+tool_call = false
+structured_output = true
+open_weights = false
+
+[cost]
+input = 1.25
+output = 10.00
+
+[limit]
+context = 400_000
+output = 128_000
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]

providers/requesty/models/openai/gpt-5-codex.toml

@@ -0,0 +1,24 @@
+name = "GPT-5 Codex"
+family = "gpt-codex"
+release_date = "2025-09-15"
+last_updated = "2025-09-15"
+attachment = true
+reasoning = true
+temperature = true
+knowledge = "2024-10-01"
+tool_call = true
+structured_output = true
+open_weights = false
+
+[cost]
+input = 1.25
+output = 10.00
+cache_read = 0.125
+
+[limit]
+context = 400_000
+output = 128_000
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]

providers/requesty/models/openai/gpt-5-image.toml

@@ -0,0 +1,24 @@
+name = "GPT-5 Image"
+family = "gpt"
+release_date = "2025-10-14"
+last_updated = "2025-10-14"
+attachment = true
+reasoning = true
+temperature = true
+knowledge = "2024-10-01"
+tool_call = true
+structured_output = true
+open_weights = false
+
+[cost]
+input = 5.00
+output = 10.00
+cache_read = 1.25
+
+[limit]
+context = 400_000
+output = 128_000
+
+[modalities]
+input = ["text", "image", "pdf"]
+output = ["text", "image"]

providers/requesty/models/openai/gpt-5-pro.toml

@@ -0,0 +1,23 @@
+name = "GPT-5 Pro"
+family = "gpt-pro"
+release_date = "2025-10-06"
+last_updated = "2025-10-06"
+attachment = true
+reasoning = true
+temperature = false
+knowledge = "2024-09-30"
+tool_call = true
+structured_output = true
+open_weights = false
+
+[cost]
+input = 15.00
+output = 120.00
+
+[limit]
+context = 400_000
+output = 272_000
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]

providers/requesty/models/openai/gpt-5.1-chat.toml

@@ -0,0 +1,24 @@
+name = "GPT-5.1 Chat"
+family = "gpt-codex"
+release_date = "2025-11-13"
+last_updated = "2025-11-13"
+attachment = true
+reasoning = true
+temperature = true
+knowledge = "2024-09-30"
+tool_call = true
+structured_output = true
+open_weights = false
+
+[cost]
+input = 1.25
+output = 10.00
+cache_read = 0.125
+
+[limit]
+context = 128_000
+output = 16_384
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]

providers/requesty/models/openai/gpt-5.1-codex-max.toml

@@ -0,0 +1,24 @@
+name = "GPT-5.1-Codex-Max"
+family = "gpt-codex"
+release_date = "2025-11-13"
+last_updated = "2025-11-13"
+attachment = true
+reasoning = true
+temperature = true
+knowledge = "2024-09-30"
+tool_call = true
+structured_output = true
+open_weights = false
+
+[cost]
+input = 1.10
+output = 9.00
+cache_read = 0.11
+
+[limit]
+context = 400_000
+output = 128_000
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]

providers/requesty/models/openai/gpt-5.1-codex-mini.toml

@@ -0,0 +1,24 @@
+name = "GPT-5.1-Codex-Mini"
+family = "gpt-codex"
+release_date = "2025-11-13"
+last_updated = "2025-11-13"
+attachment = true
+reasoning = true
+temperature = true
+knowledge = "2024-09-30"
+tool_call = true
+structured_output = true
+open_weights = false
+
+[cost]
+input = 0.25
+output = 2.00
+cache_read = 0.025
+
+[limit]
+context = 400_000
+output = 100_000
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]

providers/requesty/models/openai/gpt-5.1-codex.toml

@@ -0,0 +1,24 @@
+name = "GPT-5.1-Codex"
+family = "gpt-codex"
+release_date = "2025-11-13"
+last_updated = "2025-11-13"
+attachment = true
+reasoning = true
+temperature = true
+knowledge = "2024-09-30"
+tool_call = true
+structured_output = true
+open_weights = false
+
+[cost]
+input = 1.25
+output = 10.00
+cache_read = 0.125
+
+[limit]
+context = 400_000
+output = 128_000
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]

providers/requesty/models/openai/gpt-5.1.toml

@@ -0,0 +1,24 @@
+name = "GPT-5.1"
+family = "gpt"
+release_date = "2025-11-13"
+last_updated = "2025-11-13"
+attachment = true
+reasoning = true
+temperature = true
+knowledge = "2024-09-30"
+tool_call = true
+structured_output = true
+open_weights = false
+
+[cost]
+input = 1.25
+output = 10.00
+cache_read = 0.125
+
+[limit]
+context = 400_000
+output = 128_000
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]

providers/requesty/models/openai/gpt-5.2-chat.toml

@@ -0,0 +1,24 @@
+name = "GPT-5.2 Chat"
+family = "gpt-codex"
+release_date = "2025-12-11"
+last_updated = "2025-12-11"
+attachment = true
+reasoning = true
+temperature = false
+knowledge = "2025-08-31"
+tool_call = true
+structured_output = true
+open_weights = false
+
+[cost]
+input = 1.75
+output = 14.00
+cache_read = 0.175
+
+[limit]
+context = 128_000
+output = 16_384
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]

providers/requesty/models/openai/gpt-5.2-codex.toml

@@ -0,0 +1,24 @@
+name = "GPT-5.2-Codex"
+family = "gpt-codex"
+release_date = "2026-01-14"
+last_updated = "2026-01-14"
+attachment = true
+reasoning = true
+temperature = true
+knowledge = "2025-08-31"
+tool_call = true
+structured_output = true
+open_weights = false
+
+[cost]
+input = 1.75
+output = 14.00
+cache_read = 0.175
+
+[limit]
+context = 400_000
+output = 128_000
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]

providers/requesty/models/openai/gpt-5.2-pro.toml

@@ -0,0 +1,23 @@
+name = "GPT-5.2 Pro"
+family = "gpt-pro"
+release_date = "2025-12-11"
+last_updated = "2025-12-11"
+attachment = true
+reasoning = true
+temperature = false
+knowledge = "2025-08-31"
+tool_call = true
+structured_output = true
+open_weights = false
+
+[cost]
+input = 21.00
+output = 168.00
+
+[limit]
+context = 400_000
+output = 128_000
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]

providers/requesty/models/openai/gpt-5.2.toml

@@ -0,0 +1,24 @@
+name = "GPT-5.2"
+family = "gpt"
+release_date = "2025-12-11"
+last_updated = "2025-12-11"
+attachment = true
+reasoning = true
+temperature = false
+knowledge = "2025-08-31"
+tool_call = true
+structured_output = true
+open_weights = false
+
+[cost]
+input = 1.75
+output = 14.00
+cache_read = 0.175
+
+[limit]
+context = 400_000
+output = 128_000
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]

providers/requesty/models/openai/gpt-5.3-codex.toml

@@ -0,0 +1,24 @@
+name = "GPT-5.3-Codex"
+family = "gpt-codex"
+release_date = "2026-02-24"
+last_updated = "2026-02-24"
+attachment = true
+reasoning = true
+temperature = false
+knowledge = "2025-08-31"
+tool_call = true
+structured_output = true
+open_weights = false
+
+[cost]
+input = 1.75
+output = 14.00
+cache_read = 0.175
+
+[limit]
+context = 400_000
+output = 128_000
+
+[modalities]
+input = ["text", "image", "pdf"]
+output = ["text"]

providers/requesty/models/openai/gpt-5.4-pro.toml

@@ -0,0 +1,25 @@
+name = "GPT-5.4 Pro"
+family = "gpt-pro"
+release_date = "2026-03-05"
+last_updated = "2026-03-05"
+attachment = true
+reasoning = true
+temperature = false
+knowledge = "2025-08-31"
+tool_call = true
+structured_output = false
+open_weights = false
+
+[cost]
+input = 30.00
+output = 180.00
+cache_read = 30.00
+
+[limit]
+context = 1_050_000
+input = 922_000
+output = 128_000
+
+[modalities]
+input = ["text", "image", "pdf"]
+output = ["text"]

providers/requesty/models/openai/gpt-5.4.toml

@@ -0,0 +1,30 @@
+name = "GPT-5.4"
+family = "gpt"
+release_date = "2026-03-05"
+last_updated = "2026-03-05"
+attachment = true
+reasoning = true
+temperature = false
+knowledge = "2025-08-31"
+tool_call = true
+structured_output = true
+open_weights = false
+
+[cost]
+input = 2.50
+output = 15.00
+cache_read = 0.25
+
+[cost.context_over_200k]
+input = 5.00
+output = 22.50
+cache_read = 0.50
+
+[limit]
+context = 1_050_000
+input = 922_000
+output = 128_000
+
+[modalities]
+input = ["text", "image", "pdf"]
+output = ["text"]

providers/vercel/models/google/gemini-3.1-flash-lite-preview.toml

@@ -0,0 +1,30 @@
+name = "Gemini 3.1 Flash Lite Preview"
+family = "gemini-flash-lite"
+release_date = "2026-03-03"
+last_updated = "2026-03-03"
+attachment = true
+reasoning = true
+temperature = true
+tool_call = true
+structured_output = true
+knowledge = "2025-01"
+open_weights = false
+
+[cost]
+input = 0.50
+output = 3.00
+cache_read = 0.05
+
+[cost.context_over_200k]
+input = 0.25
+output = 1.5
+cache_read = 0.025
+cache_write = 1.00
+
+[limit]
+context = 1048576
+output = 65536
+
+[modalities]
+input = ["text", "image", "video", "audio", "pdf"]
+output = ["text"]