chore: update output limits for various models

mthezi · mthezi · commit 53d77d2f2b93 · 2026-01-15T18:42:04.000+08:00
diff --git a/providers/302ai/models/MiniMax-M1.toml b/providers/302ai/models/MiniMax-M1.toml
@@ -14,7 +14,7 @@ output = 1.254
 
 [limit]
 context = 1_000_000
-output = 80_000
+output = 128_000
 
 [modalities]
 input = ["text"]
diff --git a/providers/302ai/models/MiniMax-M2.1.toml b/providers/302ai/models/MiniMax-M2.1.toml
@@ -13,7 +13,7 @@ output = 1.200
 
 [limit]
 context = 1_000_000
-output = 80_000
+output = 131_072
 
 [modalities]
 input = ["text"]
diff --git a/providers/302ai/models/MiniMax-M2.toml b/providers/302ai/models/MiniMax-M2.toml
@@ -13,7 +13,7 @@ output = 1.320
 
 [limit]
 context = 1_000_000
-output = 80_000
+output = 128_000
 
 [modalities]
 input = ["text"]
diff --git a/providers/302ai/models/chatgpt-4o-latest.toml b/providers/302ai/models/chatgpt-4o-latest.toml
@@ -15,6 +15,7 @@ output = 15.000
 
 [limit]
 context = 128_000
+output = 16_384
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/claude-haiku-4-5-20251001.toml b/providers/302ai/models/claude-haiku-4-5-20251001.toml
@@ -14,6 +14,7 @@ output = 5.000
 
 [limit]
 context = 200_000
+output = 64_000
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/claude-opus-4-1-20250805-thinking.toml b/providers/302ai/models/claude-opus-4-1-20250805-thinking.toml
@@ -14,6 +14,7 @@ output = 75.000
 
 [limit]
 context = 200_000
+output = 32_000
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/claude-opus-4-1-20250805.toml b/providers/302ai/models/claude-opus-4-1-20250805.toml
@@ -14,6 +14,7 @@ output = 75.000
 
 [limit]
 context = 200_000
+output = 32_000
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/claude-opus-4-5-20251101-thinking.toml b/providers/302ai/models/claude-opus-4-5-20251101-thinking.toml
@@ -14,6 +14,7 @@ output = 25.000
 
 [limit]
 context = 200_000
+output = 64_000
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/claude-opus-4-5-20251101.toml b/providers/302ai/models/claude-opus-4-5-20251101.toml
@@ -14,6 +14,7 @@ output = 25.000
 
 [limit]
 context = 200_000
+output = 64_000
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/claude-sonnet-4-5-20250929-thinking.toml b/providers/302ai/models/claude-sonnet-4-5-20250929-thinking.toml
@@ -14,6 +14,7 @@ output = 15.000
 
 [limit]
 context = 200_000
+output = 64_000
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/claude-sonnet-4-5-20250929.toml b/providers/302ai/models/claude-sonnet-4-5-20250929.toml
@@ -14,6 +14,7 @@ output = 15.000
 
 [limit]
 context = 200_000
+output = 64_000
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/deepseek-chat.toml b/providers/302ai/models/deepseek-chat.toml
@@ -15,6 +15,7 @@ output = 0.430
 
 [limit]
 context = 128_000
+output = 8_192
 
 [modalities]
 input = ["text"]
diff --git a/providers/302ai/models/deepseek-reasoner.toml b/providers/302ai/models/deepseek-reasoner.toml
@@ -15,6 +15,7 @@ output = 0.430
 
 [limit]
 context = 128_000
+output = 128_000
 
 [modalities]
 input = ["text"]
diff --git a/providers/302ai/models/deepseek-v3.2-thinking.toml b/providers/302ai/models/deepseek-v3.2-thinking.toml
@@ -14,6 +14,7 @@ output = 0.430
 
 [limit]
 context = 128_000
+output = 128_000
 
 [modalities]
 input = ["text"]
diff --git a/providers/302ai/models/deepseek-v3.2.toml b/providers/302ai/models/deepseek-v3.2.toml
@@ -14,6 +14,7 @@ output = 0.430
 
 [limit]
 context = 128_000
+output = 8_192
 
 [modalities]
 input = ["text"]
diff --git a/providers/302ai/models/gemini-2.0-flash-lite.toml b/providers/302ai/models/gemini-2.0-flash-lite.toml
@@ -15,6 +15,7 @@ output = 0.300
 
 [limit]
 context = 2_000_000
+output = 8_192
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/gemini-2.5-flash-image.toml b/providers/302ai/models/gemini-2.5-flash-image.toml
@@ -14,6 +14,7 @@ output = 30.000
 
 [limit]
 context = 32_768
+output = 32_768
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/gemini-2.5-flash-lite-preview-09-2025.toml b/providers/302ai/models/gemini-2.5-flash-lite-preview-09-2025.toml
@@ -14,6 +14,7 @@ output = 0.400
 
 [limit]
 context = 1_000_000
+output = 65_536
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/gemini-2.5-flash-nothink.toml b/providers/302ai/models/gemini-2.5-flash-nothink.toml
@@ -15,6 +15,7 @@ output = 2.500
 
 [limit]
 context = 1_000_000
+output = 65_536
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/gemini-2.5-flash-preview-09-2025.toml b/providers/302ai/models/gemini-2.5-flash-preview-09-2025.toml
@@ -14,6 +14,7 @@ output = 2.500
 
 [limit]
 context = 1_000_000
+output = 65_536
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/gemini-2.5-flash.toml b/providers/302ai/models/gemini-2.5-flash.toml
@@ -15,6 +15,7 @@ output = 2.500
 
 [limit]
 context = 1_000_000
+output = 65_536
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/gemini-2.5-pro.toml b/providers/302ai/models/gemini-2.5-pro.toml
@@ -15,6 +15,7 @@ output = 10.000
 
 [limit]
 context = 1_000_000
+output = 65_536
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/gemini-3-flash-preview.toml b/providers/302ai/models/gemini-3-flash-preview.toml
@@ -14,6 +14,7 @@ output = 3.000
 
 [limit]
 context = 1_000_000
+output = 65_536
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/gemini-3-pro-image-preview.toml b/providers/302ai/models/gemini-3-pro-image-preview.toml
@@ -14,6 +14,7 @@ output = 120.000
 
 [limit]
 context = 32_768
+output = 64_000
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/gemini-3-pro-preview.toml b/providers/302ai/models/gemini-3-pro-preview.toml
@@ -14,6 +14,7 @@ output = 12.000
 
 [limit]
 context = 1_000_000
+output = 64_000
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/glm-4.5.toml b/providers/302ai/models/glm-4.5.toml
@@ -14,6 +14,7 @@ output = 1.142
 
 [limit]
 context = 128_000
+output = 98_304
 
 [modalities]
 input = ["text"]
diff --git a/providers/302ai/models/glm-4.5v.toml b/providers/302ai/models/glm-4.5v.toml
@@ -14,6 +14,7 @@ output = 0.860
 
 [limit]
 context = 64_000
+output = 16_384
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/glm-4.6.toml b/providers/302ai/models/glm-4.6.toml
@@ -14,6 +14,7 @@ output = 1.142
 
 [limit]
 context = 200_000
+output = 131_072
 
 [modalities]
 input = ["text"]
diff --git a/providers/302ai/models/glm-4.6v.toml b/providers/302ai/models/glm-4.6v.toml
@@ -14,6 +14,7 @@ output = 0.430
 
 [limit]
 context = 128_000
+output = 32_768
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/glm-4.7.toml b/providers/302ai/models/glm-4.7.toml
@@ -14,6 +14,7 @@ output = 1.142
 
 [limit]
 context = 200_000
+output = 131_072
 
 [modalities]
 input = ["text"]
diff --git a/providers/302ai/models/gpt-4o.toml b/providers/302ai/models/gpt-4o.toml
@@ -15,6 +15,7 @@ output = 10.000
 
 [limit]
 context = 128_000
+output = 16_384
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/gpt-5-pro.toml b/providers/302ai/models/gpt-5-pro.toml
@@ -14,7 +14,7 @@ output = 120.000
 
 [limit]
 context = 400_000
-output = 128_000
+output = 272_000
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/gpt-5.1-chat-latest.toml b/providers/302ai/models/gpt-5.1-chat-latest.toml
@@ -14,6 +14,7 @@ output = 10.000
 
 [limit]
 context = 128_000
+output = 16_384
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/gpt-5.1.toml b/providers/302ai/models/gpt-5.1.toml
@@ -14,6 +14,7 @@ output = 10.000
 
 [limit]
 context = 400_000
+output = 128_000
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/grok-4-1-fast-non-reasoning.toml b/providers/302ai/models/grok-4-1-fast-non-reasoning.toml
@@ -14,6 +14,7 @@ output = 0.500
 
 [limit]
 context = 2_000_000
+output = 30_000
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/grok-4-1-fast-reasoning.toml b/providers/302ai/models/grok-4-1-fast-reasoning.toml
@@ -14,6 +14,7 @@ output = 0.500
 
 [limit]
 context = 2_000_000
+output = 30_000
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/grok-4-fast-non-reasoning.toml b/providers/302ai/models/grok-4-fast-non-reasoning.toml
@@ -14,6 +14,7 @@ output = 0.500
 
 [limit]
 context = 2_000_000
+output = 30_000
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/grok-4-fast-reasoning.toml b/providers/302ai/models/grok-4-fast-reasoning.toml
@@ -14,6 +14,7 @@ output = 0.500
 
 [limit]
 context = 2_000_000
+output = 30_000
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/grok-4.1.toml b/providers/302ai/models/grok-4.1.toml
@@ -14,6 +14,7 @@ output = 10.000
 
 [limit]
 context = 200_000
+output = 64_000
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/kimi-k2-0905-preview.toml b/providers/302ai/models/kimi-k2-0905-preview.toml
@@ -14,6 +14,7 @@ output = 2.530
 
 [limit]
 context = 262_144
+output = 262_144
 
 [modalities]
 input = ["text"]
diff --git a/providers/302ai/models/kimi-k2-thinking-turbo.toml b/providers/302ai/models/kimi-k2-thinking-turbo.toml
@@ -14,6 +14,7 @@ output = 9.119
 
 [limit]
 context = 262_144
+output = 262_144
 
 [modalities]
 input = ["text"]
diff --git a/providers/302ai/models/kimi-k2-thinking.toml b/providers/302ai/models/kimi-k2-thinking.toml
@@ -14,6 +14,7 @@ output = 2.300
 
 [limit]
 context = 262_144
+output = 262_144
 
 [modalities]
 input = ["text"]
diff --git a/providers/302ai/models/ministral-14b-2512.toml b/providers/302ai/models/ministral-14b-2512.toml
@@ -14,6 +14,7 @@ output = 0.330
 
 [limit]
 context = 128_000
+output = 128_000
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/mistral-large-2512.toml b/providers/302ai/models/mistral-large-2512.toml
@@ -14,6 +14,7 @@ output = 3.300
 
 [limit]
 context = 128_000
+output = 262_144
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/302ai/models/qwen-flash.toml b/providers/302ai/models/qwen-flash.toml
@@ -13,6 +13,7 @@ output = 0.220
 
 [limit]
 context = 1_000_000
+output = 32_768
 
 [modalities]
 input = ["text"]
diff --git a/providers/302ai/models/qwen-max-latest.toml b/providers/302ai/models/qwen-max-latest.toml
@@ -1,5 +1,7 @@
 name = "Qwen-Max-Latest"
 family = "qwen-max-latest"
+release_date = "2024-04-03"
+last_updated = "2025-01-25"
 attachment = false
 reasoning = false
 temperature = true
@@ -13,6 +15,7 @@ output = 1.372
 
 [limit]
 context = 131_072
+output = 8_192
 
 [modalities]
 input = ["text"]
diff --git a/providers/302ai/models/qwen-plus.toml b/providers/302ai/models/qwen-plus.toml
@@ -15,6 +15,7 @@ output = 1.200
 
 [limit]
 context = 1_000_000
+output = 32_768
 
 [modalities]
 input = ["text"]
diff --git a/providers/302ai/models/qwen3-235b-a22b.toml b/providers/302ai/models/qwen3-235b-a22b.toml
@@ -15,7 +15,7 @@ output = 2.860
 
 [limit]
 context = 128_000
-output = 8_192
+output = 16_384
 
 [modalities]
 input = ["text"]
