Update model configs [2026-02-15T00:00:25.137Z] (#56)

nikp1172 · web-flow · commit 9347270be9de · 2026-02-15T14:44:36.000+05:30
diff --git a/providers/aws-bedrock/deepseek.v3.2.yaml b/providers/aws-bedrock/deepseek.v3.2.yaml
@@ -0,0 +1,11 @@
+model: deepseek.v3.2
+costs:
+  - region: '*'
+    input_cost_per_token: 6.2e-7
+    output_cost_per_token: 0.00000185
+limits:
+  max_tokens: 163840
+  max_input_tokens: 163840
+  max_output_tokens: 163840
+features: [function_calling]
+mode: chat
diff --git a/providers/aws-bedrock/eu.deepseek.v3.2.yaml b/providers/aws-bedrock/eu.deepseek.v3.2.yaml
@@ -0,0 +1,11 @@
+model: eu.deepseek.v3.2
+costs:
+  - region: '*'
+    input_cost_per_token: 7.4e-7
+    output_cost_per_token: 0.00000222
+limits:
+  max_tokens: 163840
+  max_input_tokens: 163840
+  max_output_tokens: 163840
+features: [function_calling]
+mode: chat
diff --git a/providers/aws-bedrock/minimax.minimax-m2.1.yaml b/providers/aws-bedrock/minimax.minimax-m2.1.yaml
@@ -0,0 +1,11 @@
+model: minimax.minimax-m2.1
+costs:
+  - region: '*'
+    input_cost_per_token: 3.e-7
+    output_cost_per_token: 0.0000012
+limits:
+  max_tokens: 8192
+  max_input_tokens: 196000
+  max_output_tokens: 8192
+features: [function_calling]
+mode: chat
diff --git a/providers/aws-bedrock/moonshotai.kimi-k2.5.yaml b/providers/aws-bedrock/moonshotai.kimi-k2.5.yaml
@@ -1,11 +1,11 @@
 model: moonshotai.kimi-k2.5
 costs:
   - region: '*'
-    input_cost_per_token: 7.3e-7
-    output_cost_per_token: 0.00000303
+    input_cost_per_token: 6.e-7
+    output_cost_per_token: 0.000003
 limits:
   max_tokens: 262144
   max_input_tokens: 262144
   max_output_tokens: 262144
-features: [function_calling]
+features: [function_calling, vision]
 mode: chat
diff --git a/providers/aws-bedrock/nvidia.nemotron-nano-3-30b.yaml b/providers/aws-bedrock/nvidia.nemotron-nano-3-30b.yaml
@@ -0,0 +1,11 @@
+model: nvidia.nemotron-nano-3-30b
+costs:
+  - region: '*'
+    input_cost_per_token: 6.e-8
+    output_cost_per_token: 2.4e-7
+limits:
+  max_tokens: 8192
+  max_input_tokens: 262144
+  max_output_tokens: 8192
+features: [function_calling]
+mode: chat
diff --git a/providers/aws-bedrock/qwen.qwen3-coder-next.yaml b/providers/aws-bedrock/qwen.qwen3-coder-next.yaml
@@ -0,0 +1,11 @@
+model: qwen.qwen3-coder-next
+costs:
+  - region: '*'
+    input_cost_per_token: 5.e-7
+    output_cost_per_token: 0.0000012
+limits:
+  max_tokens: 8192
+  max_input_tokens: 262144
+  max_output_tokens: 8192
+features: [function_calling]
+mode: chat
diff --git a/providers/aws-bedrock/us.deepseek.v3.2.yaml b/providers/aws-bedrock/us.deepseek.v3.2.yaml
@@ -0,0 +1,11 @@
+model: us.deepseek.v3.2
+costs:
+  - region: '*'
+    input_cost_per_token: 6.2e-7
+    output_cost_per_token: 0.00000185
+limits:
+  max_tokens: 163840
+  max_input_tokens: 163840
+  max_output_tokens: 163840
+features: [function_calling]
+mode: chat
diff --git a/providers/aws-bedrock/zai.glm-4.7.yaml b/providers/aws-bedrock/zai.glm-4.7.yaml
@@ -0,0 +1,11 @@
+model: zai.glm-4.7
+costs:
+  - region: '*'
+    input_cost_per_token: 6.e-7
+    output_cost_per_token: 0.0000022
+limits:
+  max_tokens: 128000
+  max_input_tokens: 200000
+  max_output_tokens: 128000
+features: [function_calling]
+mode: chat
diff --git a/providers/google-gemini/gemini-2.0-flash-lite-001.yaml b/providers/google-gemini/gemini-2.0-flash-lite-001.yaml
@@ -0,0 +1,13 @@
+model: gemini-2.0-flash-lite-001
+costs:
+  - region: '*'
+    input_cost_per_token: 7.5e-8
+    output_cost_per_token: 3.e-7
+    cache_read_input_token_cost: 1.875e-8
+    input_cost_per_audio_token: 7.5e-8
+limits:
+  max_tokens: 4096
+  max_input_tokens: 1048576
+  max_output_tokens: 8192
+features: [function_calling, vision, audio_output, chat, image, pdf, doc]
+mode: chat
diff --git a/providers/google-gemini/gemini-2.5-flash-native-audio-latest.yaml b/providers/google-gemini/gemini-2.5-flash-native-audio-latest.yaml
@@ -0,0 +1,12 @@
+model: gemini-2.5-flash-native-audio-latest
+costs:
+  - region: '*'
+    input_cost_per_token: 3.e-7
+    output_cost_per_token: 0.0000025
+    input_cost_per_audio_token: 0.000001
+limits:
+  max_tokens: 8192
+  max_input_tokens: 1048576
+  max_output_tokens: 8192
+features: [audio_input, audio_output]
+mode: chat
diff --git a/providers/google-gemini/gemini-flash-latest.yaml b/providers/google-gemini/gemini-flash-latest.yaml
@@ -3,7 +3,7 @@ costs:
   - region: '*'
     input_cost_per_token: 3.e-7
     output_cost_per_token: 0.0000025
-    cache_read_input_token_cost: 7.5e-8
+    cache_read_input_token_cost: 3.e-8
     input_cost_per_audio_token: 0.000001
 limits:
   max_tokens: 65535
diff --git a/providers/google-gemini/gemini-flash-lite-latest.yaml b/providers/google-gemini/gemini-flash-lite-latest.yaml
@@ -3,7 +3,7 @@ costs:
   - region: '*'
     input_cost_per_token: 1.e-7
     output_cost_per_token: 4.e-7
-    cache_read_input_token_cost: 2.5e-8
+    cache_read_input_token_cost: 1.e-8
     input_cost_per_audio_token: 3.e-7
 limits:
   max_tokens: 65535
diff --git a/providers/google-gemini/gemini-pro-latest.yaml b/providers/google-gemini/gemini-pro-latest.yaml
@@ -0,0 +1,22 @@
+model: gemini-pro-latest
+costs:
+  - region: '*'
+    input_cost_per_token: 0.00000125
+    output_cost_per_token: 0.00001
+    cache_read_input_token_cost: 1.25e-7
+    tiered_pricing:
+      cache_read:
+        - from: 200000
+          cost_per_token: 2.5e-7
+      input:
+        - from: 200000
+          cost_per_token: 0.0000025
+      output:
+        - from: 200000
+          cost_per_token: 0.000015
+limits:
+  max_tokens: 65535
+  max_input_tokens: 1048576
+  max_output_tokens: 65535
+features: [function_calling, vision, audio_input]
+mode: chat
diff --git a/providers/openai/chatgpt-image-latest.yaml b/providers/openai/chatgpt-image-latest.yaml
@@ -0,0 +1,6 @@
+model: chatgpt-image-latest
+costs:
+  - region: '*'
+    input_cost_per_token: 0.000005
+    cache_read_input_token_cost: 0.00000125
+mode: image
diff --git a/providers/openai/gpt-4o-mini-transcribe-2025-03-20.yaml b/providers/openai/gpt-4o-mini-transcribe-2025-03-20.yaml
@@ -0,0 +1,10 @@
+model: gpt-4o-mini-transcribe-2025-03-20
+costs:
+  - region: '*'
+    input_cost_per_token: 0.00000125
+    output_cost_per_token: 0.000005
+    input_cost_per_audio_token: 0.000003
+limits:
+  max_input_tokens: 16000
+  max_output_tokens: 2000
+mode: audio_transcription
diff --git a/providers/openai/gpt-4o-mini-transcribe-2025-12-15.yaml b/providers/openai/gpt-4o-mini-transcribe-2025-12-15.yaml
@@ -0,0 +1,10 @@
+model: gpt-4o-mini-transcribe-2025-12-15
+costs:
+  - region: '*'
+    input_cost_per_token: 0.00000125
+    output_cost_per_token: 0.000005
+    input_cost_per_audio_token: 0.000003
+limits:
+  max_input_tokens: 16000
+  max_output_tokens: 2000
+mode: audio_transcription
diff --git a/providers/openai/gpt-4o-mini-tts-2025-03-20.yaml b/providers/openai/gpt-4o-mini-tts-2025-03-20.yaml
@@ -0,0 +1,8 @@
+model: gpt-4o-mini-tts-2025-03-20
+costs:
+  - region: '*'
+    input_cost_per_token: 0.0000025
+    output_cost_per_token: 0.00001
+    output_cost_per_audio_token: 0.000012
+    output_cost_per_second: 0.00025
+mode: audio_speech
diff --git a/providers/openai/gpt-4o-mini-tts-2025-12-15.yaml b/providers/openai/gpt-4o-mini-tts-2025-12-15.yaml
@@ -0,0 +1,8 @@
+model: gpt-4o-mini-tts-2025-12-15
+costs:
+  - region: '*'
+    input_cost_per_token: 0.0000025
+    output_cost_per_token: 0.00001
+    output_cost_per_audio_token: 0.000012
+    output_cost_per_second: 0.00025
+mode: audio_speech
diff --git a/providers/openai/gpt-5-search-api-2025-10-14.yaml b/providers/openai/gpt-5-search-api-2025-10-14.yaml
@@ -0,0 +1,12 @@
+model: gpt-5-search-api-2025-10-14
+costs:
+  - region: '*'
+    input_cost_per_token: 0.00000125
+    output_cost_per_token: 0.00001
+    cache_read_input_token_cost: 1.25e-7
+limits:
+  max_tokens: 4096
+  max_input_tokens: 272000
+  max_output_tokens: 128000
+features: [function_calling, parallel_function_calling, vision, chat]
+mode: chat
diff --git a/providers/openai/gpt-5-search-api.yaml b/providers/openai/gpt-5-search-api.yaml
@@ -0,0 +1,12 @@
+model: gpt-5-search-api
+costs:
+  - region: '*'
+    input_cost_per_token: 0.00000125
+    output_cost_per_token: 0.00001
+    cache_read_input_token_cost: 1.25e-7
+limits:
+  max_tokens: 4096
+  max_input_tokens: 272000
+  max_output_tokens: 128000
+features: [function_calling, parallel_function_calling, vision, chat]
+mode: chat
diff --git a/providers/openai/gpt-realtime-mini-2025-10-06.yaml b/providers/openai/gpt-realtime-mini-2025-10-06.yaml
@@ -0,0 +1,16 @@
+model: gpt-realtime-mini-2025-10-06
+costs:
+  - region: '*'
+    input_cost_per_token: 6.e-7
+    output_cost_per_token: 0.0000024
+    cache_read_input_token_cost: 6.e-8
+    input_cost_per_audio_token: 0.00001
+    output_cost_per_audio_token: 0.00002
+    cache_creation_input_audio_token_cost: 3.e-7
+    input_cost_per_image: 8.e-7
+limits:
+  max_tokens: 4096
+  max_input_tokens: 128000
+  max_output_tokens: 4096
+features: [function_calling, parallel_function_calling, audio_input, audio_output]
+mode: chat
diff --git a/providers/openai/gpt-realtime-mini-2025-12-15.yaml b/providers/openai/gpt-realtime-mini-2025-12-15.yaml
@@ -0,0 +1,16 @@
+model: gpt-realtime-mini-2025-12-15
+costs:
+  - region: '*'
+    input_cost_per_token: 6.e-7
+    output_cost_per_token: 0.0000024
+    cache_read_input_token_cost: 6.e-8
+    input_cost_per_audio_token: 0.00001
+    output_cost_per_audio_token: 0.00002
+    cache_creation_input_audio_token_cost: 3.e-7
+    input_cost_per_image: 8.e-7
+limits:
+  max_tokens: 4096
+  max_input_tokens: 128000
+  max_output_tokens: 4096
+features: [function_calling, parallel_function_calling, audio_input, audio_output]
+mode: chat
diff --git a/providers/openai/o1.yaml b/providers/openai/o1.yaml
@@ -8,7 +8,7 @@ limits:
   max_tokens: 4096
   max_input_tokens: 200000
   max_output_tokens: 100000
-features: [function_calling, parallel_function_calling, vision, chat, image]
+features: [function_calling, vision, chat, image]
 messages:
   options:
     - user
diff --git a/providers/openai/tts-1-1106.yaml b/providers/openai/tts-1-1106.yaml
@@ -0,0 +1,5 @@
+model: tts-1-1106
+costs:
+  - region: '*'
+    input_cost_per_character: 0.000015
+mode: audio_speech
diff --git a/providers/openai/tts-1-hd-1106.yaml b/providers/openai/tts-1-hd-1106.yaml
@@ -0,0 +1,5 @@
+model: tts-1-hd-1106
+costs:
+  - region: '*'
+    input_cost_per_character: 0.00003
+mode: audio_speech
diff --git a/providers/openrouter/openai/gpt-5.2-codex.yaml b/providers/openrouter/openai/gpt-5.2-codex.yaml
@@ -0,0 +1,11 @@
+model: openai/gpt-5.2-codex
+costs:
+  - region: '*'
+    input_cost_per_token: 0.00000175
+    output_cost_per_token: 0.000014
+    cache_read_input_token_cost: 1.75e-7
+limits:
+  max_tokens: 128000
+  max_input_tokens: 272000
+  max_output_tokens: 128000
+mode: chat
