feat(openrouter): update model YAMLs [bot]

providers/openrouter/bytedance-seed/seed-2.0-lite.yaml

@@ -2,6 +2,13 @@ costs:
     - input_cost_per_token: 2.5e-7
       output_cost_per_token: 0.000002
       region: "*"
+      tiered_pricing:
+          input:
+              - cost_per_token: 5.e-7
+                from: 128000
+          output:
+              - cost_per_token: 0.000004
+                from: 128000
 features:
     - function_calling
     - structured_output
@@ -20,6 +27,14 @@ modalities:
         - text
 mode: chat
 model: bytedance-seed/seed-2.0-lite
+params:
+    - defaultValue: 128
+      key: max_tokens
+      maxValue: 131072
+      minValue: 1
+    - defaultValue: medium
+      key: reasoning_effort
+      type: string
 sources:
     - https://openrouter.ai/bytedance-seed/seed-2.0-lite/api
 thinking: true

providers/openrouter/cohere/command-r-plus.yaml

@@ -11,8 +11,16 @@ limits:
     context_window: 128000
     max_output_tokens: 4000
     max_tokens: 4000
+modalities:
+    input:
+        - text
+    output:
+        - text
 mode: chat
 model: cohere/command-r-plus
+params:
+    - key: max_tokens
+      maxValue: 4000
 sources:
     - https://openrouter.ai/cohere/command-r-plus/api
     - https://docs.cohere.com/docs/command-r-plus

providers/openrouter/google/gemini-3.1-flash-lite-preview.yaml

@@ -1,7 +1,7 @@
 costs:
     - cache_creation_input_token_cost: 8.333333333333334e-8
       cache_read_input_token_cost: 2.5e-8
-      input_cost_per_image: 2.5e-7
+      input_cost_per_audio_token: 5.e-7
       input_cost_per_token: 2.5e-7
       output_cost_per_token: 0.0000015
       region: "*"
@@ -30,6 +30,9 @@ params:
       key: max_tokens
       maxValue: 65536
       minValue: 1
+    - defaultValue: minimal
+      key: reasoning_effort
+      type: string
 sources:
     - https://openrouter.ai/google/gemini-3.1-flash-lite-preview/api
 thinking: true

providers/openrouter/minimax/minimax-m2.7.yaml

@@ -3,9 +3,15 @@ costs:
       input_cost_per_token: 3.e-7
       output_cost_per_token: 0.0000012
       region: "*"
+features:
+    - function_calling
+    - tool_choice
+    - structured_output
+    - tools
 limits:
     context_window: 204800
     max_output_tokens: 131072
+    max_tokens: 131072
 modalities:
     input:
         - text
@@ -18,3 +24,6 @@ params:
       key: temperature
     - defaultValue: 0.95
       key: top_p
+sources:
+    - https://openrouter.ai/minimax/minimax-m2.7/api
+thinking: true

providers/openrouter/mistralai/mistral-small-2603.yaml

@@ -3,6 +3,10 @@ costs:
       input_cost_per_token: 1.5e-7
       output_cost_per_token: 6.e-7
       region: "*"
+features:
+    - function_calling
+    - structured_output
+    - tool_choice
 limits:
     context_window: 262144
 modalities:
@@ -13,3 +17,13 @@ modalities:
         - text
 mode: chat
 model: mistralai/mistral-small-2603
+params:
+    - defaultValue: high
+      key: reasoning
+      type: string
+removeParams:
+    - "n"
+sources:
+    - https://openrouter.ai/mistralai/mistral-small-2603/api
+    - https://docs.mistral.ai/models/
+thinking: true

providers/openrouter/nvidia/nemotron-3-super-120b-a12b.yaml

@@ -1,6 +1,5 @@
 costs:
-    - cache_read_input_token_cost: 4.e-8
-      input_cost_per_token: 1.e-7
+    - input_cost_per_token: 1.e-7
       output_cost_per_token: 5.e-7
       region: "*"
 limits:
@@ -17,3 +16,6 @@ params:
       key: temperature
     - defaultValue: 0.95
       key: top_p
+sources:
+    - https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b/api
+thinking: true

providers/openrouter/openai/gpt-5.4-mini.yaml

@@ -3,15 +3,30 @@ costs:
       input_cost_per_token: 7.5e-7
       output_cost_per_token: 0.0000045
       region: "*"
+features:
+    - function_calling
+    - structured_output
+    - system_messages
+    - tool_choice
+    - tools
 limits:
     context_window: 400000
     max_output_tokens: 128000
+    max_tokens: 128000
 modalities:
     input:
-        - pdf
-        - image
         - text
+        - image
+        - pdf
     output:
         - text
 mode: chat
 model: openai/gpt-5.4-mini
+params:
+    - key: max_tokens
+      maxValue: 128000
+    - key: reasoning_effort
+      type: string
+sources:
+    - https://openrouter.ai/openai/gpt-5.4-mini/api
+thinking: true

providers/openrouter/openai/gpt-5.4-nano.yaml

@@ -3,15 +3,27 @@ costs:
       input_cost_per_token: 2.e-7
       output_cost_per_token: 0.00000125
       region: "*"
+features:
+    - function_calling
+    - tool_choice
+    - tools
+    - structured_output
 limits:
     context_window: 400000
     max_output_tokens: 128000
+    max_tokens: 128000
 modalities:
     input:
-        - pdf
-        - image
         - text
+        - image
+        - pdf
     output:
         - text
 mode: chat
 model: openai/gpt-5.4-nano
+params:
+    - key: reasoning_effort
+      type: string
+sources:
+    - https://openrouter.ai/openai/gpt-5.4-nano/api
+thinking: true

providers/openrouter/qwen/qwen3-max.yaml

@@ -3,12 +3,27 @@ costs:
       input_cost_per_token: 7.8e-7
       output_cost_per_token: 0.0000039
       region: "*"
+      tiered_pricing:
+          cache_read:
+              - cost_per_token: 4.8e-7
+                from: 32000
+              - cost_per_token: 6.e-7
+                from: 128000
+          input:
+              - cost_per_token: 0.0000024
+                from: 32000
+              - cost_per_token: 0.000003
+                from: 128000
+          output:
+              - cost_per_token: 0.000012
+                from: 32000
+              - cost_per_token: 0.000015
+                from: 128000
 features:
     - function_calling
     - tool_choice
     - tools
     - prompt_caching
-    - structured_output
     - system_messages
 limits:
     context_window: 262144
@@ -24,3 +39,4 @@ mode: chat
 model: qwen/qwen3-max
 sources:
     - https://openrouter.ai/qwen/qwen3-max/api
+thinking: true

providers/openrouter/xiaomi/mimo-v2-omni.yaml

@@ -3,9 +3,14 @@ costs:
       input_cost_per_token: 4.e-7
       output_cost_per_token: 0.000002
       region: "*"
+features:
+    - function_calling
+    - tool_choice
+    - structured_output
 limits:
     context_window: 262144
     max_output_tokens: 65536
+    max_tokens: 65536
 modalities:
     input:
         - text
@@ -21,3 +26,6 @@ params:
       key: temperature
     - defaultValue: 0.95
       key: top_p
+sources:
+    - https://openrouter.ai/xiaomi/mimo-v2-omni/api
+thinking: true

providers/openrouter/xiaomi/mimo-v2-pro.yaml

@@ -3,9 +3,24 @@ costs:
       input_cost_per_token: 0.000001
       output_cost_per_token: 0.000003
       region: "*"
+      tiered_pricing:
+          cache_read:
+              - cost_per_token: 4.e-7
+                from: 256000
+          input:
+              - cost_per_token: 0.000002
+                from: 256000
+          output:
+              - cost_per_token: 0.000006
+                from: 256000
+features:
+    - function_calling
+    - tool_choice
+    - structured_output
 limits:
     context_window: 1048576
     max_output_tokens: 131072
+    max_tokens: 131072
 modalities:
     input:
         - text
@@ -18,3 +33,6 @@ params:
       key: temperature
     - defaultValue: 0.95
       key: top_p
+sources:
+    - https://openrouter.ai/xiaomi/mimo-v2-pro/api
+thinking: true