tokencostauto 0.1.264__py3-none-any.whl → 0.1.333__py3-none-any.whl

tokencostauto/model_prices.json

@@ -33,6 +33,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_service_tier": true,
         "supports_vision": true
     },
     "gpt-4o-audio-preview": {
@@ -90,6 +91,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_service_tier": true,
         "supports_vision": true
     },
     "gpt-4o-mini-2024-07-18": {
@@ -115,6 +117,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_service_tier": true,
         "supports_vision": true
     },
     "o1-mini": {
@@ -131,6 +134,7 @@
         "supports_vision": true
     },
     "o1-mini-2024-09-12": {
+        "deprecation_date": "2025-10-27",
         "cache_read_input_token_cost": 1.5e-06,
         "input_cost_per_token": 3e-06,
         "litellm_provider": "openai",
@@ -226,6 +230,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_service_tier": true,
         "supports_vision": true
     },
     "gpt-4-turbo-preview": {
@@ -338,6 +343,7 @@
         "supports_vision": true
     },
     "gpt-4-1106-preview": {
+        "deprecation_date": "2026-03-26",
         "input_cost_per_token": 1e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 128000,
@@ -352,6 +358,7 @@
         "supports_tool_choice": true
     },
     "gpt-4-0125-preview": {
+        "deprecation_date": "2026-03-26",
         "input_cost_per_token": 1e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 128000,
@@ -434,6 +441,7 @@
         "supports_tool_choice": true
     },
     "gpt-3.5-turbo-1106": {
+        "deprecation_date": "2026-09-28",
         "input_cost_per_token": 1e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 16385,
@@ -845,6 +853,7 @@
         "supports_vision": true
     },
     "azure/gpt-4o-2024-08-06": {
+        "deprecation_date": "2026-02-27",
         "cache_read_input_token_cost": 1.25e-06,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
@@ -876,7 +885,7 @@
     },
     "azure/global-standard/gpt-4o-2024-08-06": {
         "cache_read_input_token_cost": 1.25e-06,
-        "deprecation_date": "2025-08-20",
+        "deprecation_date": "2026-02-27",
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -1184,6 +1193,7 @@
         "output_cost_per_token": 0.0
     },
     "azure/text-embedding-3-small": {
+        "deprecation_date": "2026-04-30",
         "input_cost_per_token": 2e-08,
         "litellm_provider": "azure",
         "max_input_tokens": 8191,
@@ -1942,7 +1952,6 @@
         "cache_creation_input_token_cost": 3e-07,
         "cache_creation_input_token_cost_above_1hr": 6e-06,
         "cache_read_input_token_cost": 3e-08,
-        "deprecation_date": "2025-03-01",
         "input_cost_per_token": 2.5e-07,
         "litellm_provider": "anthropic",
         "max_input_tokens": 200000,
@@ -1978,7 +1987,7 @@
         "cache_creation_input_token_cost": 1.875e-05,
         "cache_creation_input_token_cost_above_1hr": 6e-06,
         "cache_read_input_token_cost": 1.5e-06,
-        "deprecation_date": "2025-03-01",
+        "deprecation_date": "2026-05-01",
         "input_cost_per_token": 1.5e-05,
         "litellm_provider": "anthropic",
         "max_input_tokens": 200000,
@@ -6433,13 +6442,13 @@
         "supports_tool_choice": false
     },
     "deepinfra/Gryphe/MythoMax-L2-13b": {
-        "input_cost_per_token": 7.2e-08,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 4096,
         "max_input_tokens": 4096,
         "max_output_tokens": 4096,
-        "max_tokens": 4096,
+        "input_cost_per_token": 8e-08,
+        "output_cost_per_token": 9e-08,
+        "litellm_provider": "deepinfra",
         "mode": "chat",
-        "output_cost_per_token": 7.2e-08,
         "supports_tool_choice": true
     },
     "deepinfra/mistralai/Mistral-7B-Instruct-v0.1": {
@@ -6502,13 +6511,13 @@
         "supports_tool_choice": true
     },
     "deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1": {
-        "input_cost_per_token": 8e-08,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 32768,
         "max_input_tokens": 32768,
         "max_output_tokens": 32768,
-        "max_tokens": 32768,
+        "input_cost_per_token": 4e-07,
+        "output_cost_per_token": 4e-07,
+        "litellm_provider": "deepinfra",
         "mode": "chat",
-        "output_cost_per_token": 2.4e-07,
         "supports_tool_choice": true
     },
     "deepinfra/deepinfra/airoboros-70b": {
@@ -6581,13 +6590,13 @@
         "supports_tool_choice": true
     },
     "deepinfra/meta-llama/Meta-Llama-3-8B-Instruct": {
-        "input_cost_per_token": 3e-08,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 8192,
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
+        "input_cost_per_token": 3e-08,
         "output_cost_per_token": 6e-08,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/meta-llama/Meta-Llama-3-70B-Instruct": {
@@ -7720,6 +7729,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_service_tier": true,
         "supports_vision": true
     },
     "ft:gpt-4o-2024-11-20": {
@@ -7741,6 +7751,7 @@
         "supports_vision": true
     },
     "azure/gpt-4o-2024-11-20": {
+        "deprecation_date": "2026-03-01",
         "cache_read_input_token_cost": 1.25e-06,
         "input_cost_per_token": 2.75e-06,
         "litellm_provider": "azure",
@@ -7758,7 +7769,7 @@
     },
     "azure/global-standard/gpt-4o-2024-11-20": {
         "cache_read_input_token_cost": 1.25e-06,
-        "deprecation_date": "2025-12-20",
+        "deprecation_date": "2026-03-01",
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -9795,7 +9806,7 @@
         "cache_creation_input_token_cost": 3.75e-06,
         "cache_creation_input_token_cost_above_1hr": 6e-06,
         "cache_read_input_token_cost": 3e-07,
-        "deprecation_date": "2026-02-01",
+        "deprecation_date": "2026-02-19",
         "input_cost_per_token": 3e-06,
         "litellm_provider": "anthropic",
         "max_input_tokens": 200000,
@@ -10204,6 +10215,7 @@
         "supports_vision": false
     },
     "azure/us/gpt-4o-2024-11-20": {
+        "deprecation_date": "2026-03-01",
         "cache_creation_input_token_cost": 1.38e-06,
         "input_cost_per_token": 2.75e-06,
         "litellm_provider": "azure",
@@ -10219,6 +10231,7 @@
         "supports_vision": true
     },
     "azure/eu/gpt-4o-2024-11-20": {
+        "deprecation_date": "2026-03-01",
         "cache_creation_input_token_cost": 1.38e-06,
         "input_cost_per_token": 2.75e-06,
         "litellm_provider": "azure",
@@ -10234,6 +10247,7 @@
         "supports_vision": true
     },
     "azure/us/gpt-4o-2024-08-06": {
+        "deprecation_date": "2026-02-27",
         "cache_read_input_token_cost": 1.375e-06,
         "input_cost_per_token": 2.75e-06,
         "litellm_provider": "azure",
@@ -10250,6 +10264,7 @@
         "supports_vision": true
     },
     "azure/eu/gpt-4o-2024-08-06": {
+        "deprecation_date": "2026-02-27",
         "cache_read_input_token_cost": 1.375e-06,
         "input_cost_per_token": 2.75e-06,
         "litellm_provider": "azure",
@@ -10746,6 +10761,7 @@
         "mode": "chat"
     },
     "azure/global/gpt-4o-2024-11-20": {
+        "deprecation_date": "2026-03-01",
         "cache_read_input_token_cost": 1.25e-06,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
@@ -10762,6 +10778,7 @@
         "supports_vision": true
     },
     "azure/global/gpt-4o-2024-08-06": {
+        "deprecation_date": "2026-02-27",
         "cache_read_input_token_cost": 1.25e-06,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
@@ -11009,6 +11026,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_service_tier": true,
         "supports_vision": true
     },
     "gpt-4.1-2025-04-14": {
@@ -11042,6 +11060,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_service_tier": true,
         "supports_vision": true
     },
     "gpt-4.1-mini": {
@@ -11078,6 +11097,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_service_tier": true,
         "supports_vision": true
     },
     "gpt-4.1-mini-2025-04-14": {
@@ -11111,6 +11131,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_service_tier": true,
         "supports_vision": true
     },
     "gpt-4.1-nano": {
@@ -11147,6 +11168,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_service_tier": true,
         "supports_vision": true
     },
     "gpt-4.1-nano-2025-04-14": {
@@ -11180,16 +11202,17 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_service_tier": true,
         "supports_vision": true
     },
     "watsonx/ibm/granite-3-8b-instruct": {
-        "input_cost_per_token": 0.0002,
+        "input_cost_per_token": 2e-07,
         "litellm_provider": "watsonx",
         "max_input_tokens": 8192,
         "max_output_tokens": 1024,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 0.0002,
+        "output_cost_per_token": 2e-07,
         "supports_audio_input": false,
         "supports_audio_output": false,
         "supports_function_calling": true,
@@ -11262,6 +11285,7 @@
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
+        "supports_service_tier": true,
         "supports_vision": true
     },
     "o3-2025-04-16": {
@@ -11293,6 +11317,7 @@
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
+        "supports_service_tier": true,
         "supports_vision": true
     },
     "o4-mini": {
@@ -11317,6 +11342,7 @@
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
+        "supports_service_tier": true,
         "supports_vision": true
     },
     "o4-mini-2025-04-16": {
@@ -11335,6 +11361,7 @@
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
+        "supports_service_tier": true,
         "supports_vision": true
     },
     "gpt-image-1": {
@@ -11592,6 +11619,7 @@
         "supports_web_search": false
     },
     "azure/gpt-4.1-2025-04-14": {
+        "deprecation_date": "2026-11-04",
         "cache_read_input_token_cost": 5e-07,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_batches": 1e-06,
@@ -11658,6 +11686,7 @@
         "supports_web_search": false
     },
     "azure/gpt-4.1-mini-2025-04-14": {
+        "deprecation_date": "2026-11-04",
         "cache_read_input_token_cost": 1e-07,
         "input_cost_per_token": 4e-07,
         "input_cost_per_token_batches": 2e-07,
@@ -11723,6 +11752,7 @@
         "supports_vision": true
     },
     "azure/gpt-4.1-nano-2025-04-14": {
+        "deprecation_date": "2026-11-04",
         "cache_read_input_token_cost": 2.5e-08,
         "input_cost_per_token": 1e-07,
         "input_cost_per_token_batches": 5e-08,
@@ -11784,6 +11814,7 @@
         "supports_vision": true
     },
     "azure/o3-2025-04-16": {
+        "deprecation_date": "2026-04-16",
         "cache_read_input_token_cost": 2.5e-06,
         "input_cost_per_token": 1e-05,
         "litellm_provider": "azure",
@@ -13948,6 +13979,7 @@
         "cache_creation_input_token_cost_above_1hr": 3e-05,
         "cache_read_input_token_cost": 1.5e-06,
         "input_cost_per_token": 1.5e-05,
+        "deprecation_date": "2026-05-14",
         "litellm_provider": "anthropic",
         "max_input_tokens": 200000,
         "max_output_tokens": 32000,
@@ -13971,6 +14003,7 @@
         "tool_use_system_prompt_tokens": 159
     },
     "claude-sonnet-4-20250514": {
+        "deprecation_date": "2026-05-14",
         "cache_creation_input_token_cost": 3.75e-06,
         "cache_creation_input_token_cost_above_1hr": 6e-06,
         "cache_read_input_token_cost": 3e-07,
@@ -14368,7 +14401,7 @@
         "input_cost_per_token_above_200k_tokens": 6e-06,
         "litellm_provider": "anthropic",
         "max_input_tokens": 1000000,
-        "max_output_tokens": 1000000,
+        "max_output_tokens": 64000,
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
@@ -15396,7 +15429,7 @@
         "tpm": 800000
     },
     "gemini-2.5-flash": {
-        "cache_read_input_token_cost": 7.5e-08,
+        "cache_read_input_token_cost": 3e-08,
         "input_cost_per_audio_token": 1e-06,
         "input_cost_per_token": 3e-07,
         "litellm_provider": "vertex_ai-language-models",
@@ -15546,6 +15579,10 @@
     },
     "openrouter/anthropic/claude-sonnet-4": {
         "input_cost_per_image": 0.0048,
+        "cache_creation_input_token_cost": 3.75e-06,
+        "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
+        "cache_read_input_token_cost": 3e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "input_cost_per_token": 3e-06,
         "input_cost_per_token_above_200k_tokens": 6e-06,
         "output_cost_per_token_above_200k_tokens": 2.25e-05,
@@ -15558,6 +15595,7 @@
         "supports_assistant_prefill": true,
         "supports_computer_use": true,
         "supports_function_calling": true,
+        "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
         "supports_vision": true,
@@ -15658,7 +15696,8 @@
         "tpm": 250000
     },
     "gemini-2.5-pro": {
-        "cache_read_input_token_cost": 3.125e-07,
+        "cache_read_input_token_cost": 1.25e-07,
+        "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07,
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
         "litellm_provider": "vertex_ai-language-models",
@@ -16228,35 +16267,36 @@
         "output_cost_per_token": 1.5e-05,
         "source": "https://docs.x.ai/docs/models",
         "supports_function_calling": true,
-        "supports_reasoning": true,
         "supports_tool_choice": true,
         "supports_web_search": true
     },
     "xai/grok-4-0709": {
         "input_cost_per_token": 3e-06,
+        "input_cost_per_token_above_128k_tokens": 6e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 256000,
         "max_output_tokens": 256000,
         "max_tokens": 256000,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
+        "output_cost_per_token_above_128k_tokens": 3e-05,
         "source": "https://docs.x.ai/docs/models",
         "supports_function_calling": true,
-        "supports_reasoning": true,
         "supports_tool_choice": true,
         "supports_web_search": true
     },
     "xai/grok-4-latest": {
         "input_cost_per_token": 3e-06,
+        "input_cost_per_token_above_128k_tokens": 6e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 256000,
         "max_output_tokens": 256000,
         "max_tokens": 256000,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
+        "output_cost_per_token_above_128k_tokens": 3e-05,
         "source": "https://docs.x.ai/docs/models",
         "supports_function_calling": true,
-        "supports_reasoning": true,
         "supports_tool_choice": true,
         "supports_web_search": true
     },
@@ -16977,7 +17017,8 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 6.3e-07,
-        "supports_tool_choice": true
+        "supports_tool_choice": true,
+        "supports_vision": true
     },
     "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct": {
         "input_cost_per_token": 6e-07,
@@ -17836,6 +17877,7 @@
         "cache_creation_input_token_cost_above_1hr": 3e-05,
         "cache_read_input_token_cost": 1.5e-06,
         "input_cost_per_token": 1.5e-05,
+        "deprecation_date": "2026-08-05",
         "litellm_provider": "anthropic",
         "max_input_tokens": 200000,
         "max_output_tokens": 32000,
@@ -17995,8 +18037,8 @@
         "input_cost_per_token_batches": 7.5e-06,
         "litellm_provider": "vertex_ai-anthropic_models",
         "max_input_tokens": 200000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
+        "max_output_tokens": 32000,
+        "max_tokens": 32000,
         "mode": "chat",
         "output_cost_per_token": 7.5e-05,
         "output_cost_per_token_batches": 3.75e-05,
@@ -18012,8 +18054,8 @@
         "input_cost_per_token_batches": 7.5e-06,
         "litellm_provider": "vertex_ai-anthropic_models",
         "max_input_tokens": 200000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
+        "max_output_tokens": 32000,
+        "max_tokens": 32000,
         "mode": "chat",
         "output_cost_per_token": 7.5e-05,
         "output_cost_per_token_batches": 3.75e-05,
@@ -18084,6 +18126,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_service_tier": true,
         "supports_vision": true
     },
     "gpt-5-mini": {
@@ -18122,6 +18165,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_service_tier": true,
         "supports_vision": true
     },
     "gpt-5-nano": {
@@ -18196,9 +18240,9 @@
         "cache_read_input_token_cost": 1.25e-07,
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 272000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1e-05,
         "supported_endpoints": [
@@ -18299,6 +18343,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_service_tier": true,
         "supports_vision": true
     },
     "gpt-5-nano-2025-08-07": {
@@ -18565,9 +18610,9 @@
         "cache_read_input_token_cost": 1.25e-07,
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 272000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1e-05,
         "supported_endpoints": [
@@ -19211,23 +19256,23 @@
         "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
     },
     "deepinfra/deepseek-ai/DeepSeek-V3": {
-        "input_cost_per_token": 3.8e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 163840,
         "max_input_tokens": 163840,
         "max_output_tokens": 163840,
-        "max_tokens": 163840,
-        "mode": "chat",
+        "input_cost_per_token": 3.8e-07,
         "output_cost_per_token": 8.9e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": {
-        "input_cost_per_token": 1.5e-08,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
+        "input_cost_per_token": 2e-08,
+        "output_cost_per_token": 3e-08,
+        "litellm_provider": "deepinfra",
         "mode": "chat",
-        "output_cost_per_token": 2e-08,
         "supports_tool_choice": true
     },
     "deepinfra/google/gemma-2-9b-it": {
@@ -19241,13 +19286,13 @@
         "supports_tool_choice": false
     },
     "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo": {
-        "input_cost_per_token": 1e-06,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 32768,
         "max_input_tokens": 32768,
         "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
+        "input_cost_per_token": 1e-06,
         "output_cost_per_token": 3e-06,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/Qwen/Qwen2-7B-Instruct": {
@@ -19271,13 +19316,13 @@
         "supports_tool_choice": false
     },
     "deepinfra/meta-llama/Llama-3.3-70B-Instruct": {
-        "input_cost_per_token": 2.3e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
+        "input_cost_per_token": 2.3e-07,
         "output_cost_per_token": 4e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/microsoft/Phi-4-multimodal-instruct": {
@@ -19321,35 +19366,34 @@
         "supports_tool_choice": false
     },
     "deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506": {
-        "input_cost_per_token": 5e-08,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 128000,
         "max_input_tokens": 128000,
         "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "input_cost_per_token": 7.5e-08,
+        "output_cost_per_token": 2e-07,
+        "litellm_provider": "deepinfra",
         "mode": "chat",
-        "output_cost_per_token": 1e-07,
         "supports_tool_choice": true
     },
     "deepinfra/deepseek-ai/DeepSeek-V3-0324": {
-        "cache_read_input_token_cost": 2.24e-07,
-        "input_cost_per_token": 2.8e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 163840,
         "max_input_tokens": 163840,
         "max_output_tokens": 163840,
-        "max_tokens": 163840,
-        "mode": "chat",
+        "input_cost_per_token": 2.5e-07,
         "output_cost_per_token": 8.8e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/anthropic/claude-3-7-sonnet-latest": {
-        "cache_read_input_token_cost": 3.3e-07,
-        "input_cost_per_token": 3.3e-06,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 200000,
         "max_input_tokens": 200000,
         "max_output_tokens": 200000,
-        "max_tokens": 200000,
-        "mode": "chat",
+        "input_cost_per_token": 3.3e-06,
         "output_cost_per_token": 1.65e-05,
+        "cache_read_input_token_cost": 3.3e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/cognitivecomputations/dolphin-2.9.1-llama-3-70b": {
@@ -19373,13 +19417,13 @@
         "supports_tool_choice": false
     },
     "deepinfra/Qwen/Qwen3-235B-A22B": {
-        "input_cost_per_token": 1.3e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 40960,
         "max_input_tokens": 40960,
         "max_output_tokens": 40960,
-        "max_tokens": 40960,
+        "input_cost_per_token": 1.8e-07,
+        "output_cost_per_token": 5.4e-07,
+        "litellm_provider": "deepinfra",
         "mode": "chat",
-        "output_cost_per_token": 6e-07,
         "supports_tool_choice": true
     },
     "deepinfra/deepseek-ai/DeepSeek-V3-0324-Turbo": {
@@ -19394,33 +19438,33 @@
         "supports_reasoning": true
     },
     "deepinfra/microsoft/WizardLM-2-8x22B": {
-        "input_cost_per_token": 4.8e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 65536,
         "max_input_tokens": 65536,
         "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
+        "input_cost_per_token": 4.8e-07,
         "output_cost_per_token": 4.8e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": false
     },
     "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo": {
-        "input_cost_per_token": 2e-08,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 8192,
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
+        "input_cost_per_token": 4e-08,
         "output_cost_per_token": 5e-08,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": false
     },
     "deepinfra/meta-llama/Llama-Guard-4-12B": {
-        "input_cost_per_token": 1.8e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 163840,
         "max_input_tokens": 163840,
         "max_output_tokens": 163840,
-        "max_tokens": 163840,
-        "mode": "chat",
+        "input_cost_per_token": 1.8e-07,
         "output_cost_per_token": 1.8e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": false
     },
     "deepinfra/meta-llama/Llama-3.2-1B-Instruct": {
@@ -19444,23 +19488,24 @@
         "supports_tool_choice": false
     },
     "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct": {
-        "input_cost_per_token": 2e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 128000,
         "max_input_tokens": 128000,
         "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
+        "input_cost_per_token": 2e-07,
         "output_cost_per_token": 6e-07,
-        "supports_tool_choice": true
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
+        "supports_tool_choice": true,
+        "supports_vision": true
     },
     "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct": {
-        "input_cost_per_token": 1.2e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
+        "input_cost_per_token": 6e-07,
+        "output_cost_per_token": 6e-07,
+        "litellm_provider": "deepinfra",
         "mode": "chat",
-        "output_cost_per_token": 3e-07,
         "supports_tool_choice": true
     },
     "deepinfra/mistralai/Mixtral-8x22B-Instruct-v0.1": {
@@ -19474,13 +19519,13 @@
         "supports_tool_choice": true
     },
     "deepinfra/Qwen/Qwen2.5-7B-Instruct": {
-        "input_cost_per_token": 4e-08,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 32768,
         "max_input_tokens": 32768,
         "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
+        "input_cost_per_token": 4e-08,
         "output_cost_per_token": 1e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": false
     },
     "deepinfra/google/gemini-1.5-flash-8b": {
@@ -19494,53 +19539,53 @@
         "supports_tool_choice": true
     },
     "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B": {
-        "input_cost_per_token": 1e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
+        "input_cost_per_token": 3e-07,
+        "output_cost_per_token": 3e-07,
+        "litellm_provider": "deepinfra",
         "mode": "chat",
-        "output_cost_per_token": 2.8e-07,
         "supports_tool_choice": false
     },
     "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
-        "input_cost_per_token": 1e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
+        "input_cost_per_token": 2e-07,
+        "output_cost_per_token": 6e-07,
+        "litellm_provider": "deepinfra",
         "mode": "chat",
-        "output_cost_per_token": 4e-07,
         "supports_tool_choice": false
     },
     "deepinfra/meta-llama/Llama-Guard-3-8B": {
-        "input_cost_per_token": 5.5e-08,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
+        "input_cost_per_token": 5.5e-08,
         "output_cost_per_token": 5.5e-08,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": false
     },
     "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501": {
-        "input_cost_per_token": 5e-08,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 32768,
         "max_input_tokens": 32768,
         "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
+        "input_cost_per_token": 5e-08,
         "output_cost_per_token": 8e-08,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/anthropic/claude-4-opus": {
-        "input_cost_per_token": 1.65e-05,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 200000,
         "max_input_tokens": 200000,
         "max_output_tokens": 200000,
-        "max_tokens": 200000,
-        "mode": "chat",
+        "input_cost_per_token": 1.65e-05,
         "output_cost_per_token": 8.25e-05,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/openchat/openchat-3.6-8b": {
@@ -19554,13 +19599,13 @@
         "supports_tool_choice": false
     },
     "deepinfra/google/gemma-3-27b-it": {
-        "input_cost_per_token": 9e-08,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
+        "input_cost_per_token": 9e-08,
+        "output_cost_per_token": 1.6e-07,
+        "litellm_provider": "deepinfra",
         "mode": "chat",
-        "output_cost_per_token": 1.7e-07,
         "supports_tool_choice": true
     },
     "deepinfra/Austism/chronos-hermes-13b-v2": {
@@ -19574,13 +19619,13 @@
         "supports_tool_choice": true
     },
     "deepinfra/Sao10K/L3.1-70B-Euryale-v2.2": {
-        "input_cost_per_token": 6.5e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
+        "input_cost_per_token": 6.5e-07,
         "output_cost_per_token": 7.5e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": false
     },
     "deepinfra/Qwen/QwQ-32B-Preview": {
@@ -19594,13 +19639,13 @@
         "supports_tool_choice": false
     },
     "deepinfra/anthropic/claude-4-sonnet": {
-        "input_cost_per_token": 3.3e-06,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 200000,
         "max_input_tokens": 200000,
         "max_output_tokens": 200000,
-        "max_tokens": 200000,
-        "mode": "chat",
+        "input_cost_per_token": 3.3e-06,
         "output_cost_per_token": 1.65e-05,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/microsoft/Phi-3-medium-4k-instruct": {
@@ -19624,36 +19669,36 @@
         "supports_tool_choice": false
     },
     "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3": {
-        "input_cost_per_token": 6.5e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
+        "input_cost_per_token": 6.5e-07,
         "output_cost_per_token": 7.5e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": false
     },
     "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct": {
-        "input_cost_per_token": 2.3e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
+        "input_cost_per_token": 4e-07,
         "output_cost_per_token": 4e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/deepseek-ai/DeepSeek-V3.1": {
-        "cache_read_input_token_cost": 2.16e-07,
-        "input_cost_per_token": 2.7e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 163840,
         "max_input_tokens": 163840,
         "max_output_tokens": 163840,
-        "max_tokens": 163840,
-        "mode": "chat",
+        "input_cost_per_token": 2.7e-07,
         "output_cost_per_token": 1e-06,
-        "supports_reasoning": true,
-        "supports_tool_choice": true
+        "cache_read_input_token_cost": 2.16e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
+        "supports_tool_choice": true,
+        "supports_reasoning": true
     },
     "deepinfra/Qwen/Qwen2.5-Coder-7B": {
         "max_tokens": 32768,
@@ -19677,23 +19722,23 @@
         "supports_reasoning": true
     },
     "deepinfra/zai-org/GLM-4.5": {
-        "input_cost_per_token": 5.5e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
+        "input_cost_per_token": 4e-07,
+        "output_cost_per_token": 1.6e-06,
+        "litellm_provider": "deepinfra",
         "mode": "chat",
-        "output_cost_per_token": 2e-06,
         "supports_tool_choice": true
     },
     "deepinfra/meta-llama/Llama-3.2-3B-Instruct": {
-        "input_cost_per_token": 1.2e-08,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
+        "input_cost_per_token": 2e-08,
+        "output_cost_per_token": 2e-08,
+        "litellm_provider": "deepinfra",
         "mode": "chat",
-        "output_cost_per_token": 2.4e-08,
         "supports_tool_choice": true
     },
     "deepinfra/google/gemini-1.5-flash": {
@@ -19717,43 +19762,43 @@
         "supports_tool_choice": true
     },
     "deepinfra/google/gemini-2.5-pro": {
-        "input_cost_per_token": 8.75e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 1000000,
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
-        "max_tokens": 1000000,
+        "input_cost_per_token": 1.25e-06,
+        "output_cost_per_token": 1e-05,
+        "litellm_provider": "deepinfra",
         "mode": "chat",
-        "output_cost_per_token": 7e-06,
         "supports_tool_choice": true
     },
     "deepinfra/Qwen/Qwen3-30B-A3B": {
-        "input_cost_per_token": 8e-08,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 40960,
         "max_input_tokens": 40960,
         "max_output_tokens": 40960,
-        "max_tokens": 40960,
-        "mode": "chat",
+        "input_cost_per_token": 8e-08,
         "output_cost_per_token": 2.9e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/Qwen/QwQ-32B": {
-        "input_cost_per_token": 1.5e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
+        "input_cost_per_token": 1.5e-07,
         "output_cost_per_token": 4e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/moonshotai/Kimi-K2-Instruct": {
-        "input_cost_per_token": 5e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
+        "input_cost_per_token": 5e-07,
         "output_cost_per_token": 2e-06,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/Sao10K/L3-70B-Euryale-v2.1": {
@@ -19777,33 +19822,33 @@
         "supports_tool_choice": false
     },
     "deepinfra/google/gemma-3-12b-it": {
-        "input_cost_per_token": 5e-08,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
+        "input_cost_per_token": 5e-08,
         "output_cost_per_token": 1e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/google/gemini-2.5-flash": {
-        "input_cost_per_token": 2.1e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 1000000,
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
-        "max_tokens": 1000000,
+        "input_cost_per_token": 3e-07,
+        "output_cost_per_token": 2.5e-06,
+        "litellm_provider": "deepinfra",
         "mode": "chat",
-        "output_cost_per_token": 1.75e-06,
         "supports_tool_choice": true
     },
     "deepinfra/deepseek-ai/DeepSeek-R1": {
-        "input_cost_per_token": 7e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 163840,
         "max_input_tokens": 163840,
         "max_output_tokens": 163840,
-        "max_tokens": 163840,
-        "mode": "chat",
+        "input_cost_per_token": 7e-07,
         "output_cost_per_token": 2.4e-06,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/mistralai/Mistral-7B-Instruct-v0.3": {
@@ -19817,63 +19862,63 @@
         "supports_tool_choice": true
     },
     "deepinfra/Qwen/Qwen2.5-72B-Instruct": {
-        "input_cost_per_token": 1.2e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 32768,
         "max_input_tokens": 32768,
         "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
+        "input_cost_per_token": 1.2e-07,
         "output_cost_per_token": 3.9e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/Qwen/Qwen3-14B": {
-        "input_cost_per_token": 6e-08,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 40960,
         "max_input_tokens": 40960,
         "max_output_tokens": 40960,
-        "max_tokens": 40960,
-        "mode": "chat",
+        "input_cost_per_token": 6e-08,
         "output_cost_per_token": 2.4e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/allenai/olmOCR-7B-0725-FP8": {
-        "input_cost_per_token": 2.7e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 16384,
         "max_input_tokens": 16384,
         "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
+        "input_cost_per_token": 2.7e-07,
         "output_cost_per_token": 1.5e-06,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": false
     },
     "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct": {
-        "input_cost_per_token": 4e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 262144,
         "max_input_tokens": 262144,
         "max_output_tokens": 262144,
-        "max_tokens": 262144,
-        "mode": "chat",
+        "input_cost_per_token": 4e-07,
         "output_cost_per_token": 1.6e-06,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/microsoft/phi-4": {
-        "input_cost_per_token": 7e-08,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 16384,
         "max_input_tokens": 16384,
         "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
+        "input_cost_per_token": 7e-08,
         "output_cost_per_token": 1.4e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B": {
-        "input_cost_per_token": 7e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
+        "input_cost_per_token": 1e-06,
+        "output_cost_per_token": 1e-06,
+        "litellm_provider": "deepinfra",
         "mode": "chat",
-        "output_cost_per_token": 8e-07,
         "supports_tool_choice": true
     },
     "deepinfra/zai-org/GLM-4.5-Air": {
@@ -19887,23 +19932,23 @@
         "supports_tool_choice": true
     },
     "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
-        "input_cost_per_token": 7.5e-08,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
+        "input_cost_per_token": 2.7e-07,
+        "output_cost_per_token": 2.7e-07,
+        "litellm_provider": "deepinfra",
         "mode": "chat",
-        "output_cost_per_token": 1.5e-07,
         "supports_tool_choice": true
     },
     "deepinfra/openai/gpt-oss-120b": {
-        "input_cost_per_token": 9e-08,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
+        "input_cost_per_token": 5e-08,
         "output_cost_per_token": 4.5e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/google/codegemma-7b-it": {
@@ -19917,24 +19962,23 @@
         "supports_tool_choice": false
     },
     "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo": {
-        "cache_read_input_token_cost": 2.4e-07,
-        "input_cost_per_token": 3e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 262144,
         "max_input_tokens": 262144,
         "max_output_tokens": 262144,
-        "max_tokens": 262144,
-        "mode": "chat",
+        "input_cost_per_token": 2.9e-07,
         "output_cost_per_token": 1.2e-06,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/mistralai/Mistral-Nemo-Instruct-2407": {
-        "input_cost_per_token": 2e-08,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
+        "input_cost_per_token": 2e-08,
         "output_cost_per_token": 4e-08,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/openbmb/MiniCPM-Llama3-V-2_5": {
@@ -19958,33 +20002,33 @@
         "supports_tool_choice": false
     },
     "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": {
-        "input_cost_per_token": 1.5e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 1048576,
         "max_input_tokens": 1048576,
         "max_output_tokens": 1048576,
-        "max_tokens": 1048576,
-        "mode": "chat",
+        "input_cost_per_token": 1.5e-07,
         "output_cost_per_token": 6e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct": {
-        "input_cost_per_token": 8e-08,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 327680,
         "max_input_tokens": 327680,
         "max_output_tokens": 327680,
-        "max_tokens": 327680,
-        "mode": "chat",
+        "input_cost_per_token": 8e-08,
         "output_cost_per_token": 3e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/google/gemini-2.0-flash-001": {
-        "input_cost_per_token": 1e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 1000000,
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
-        "max_tokens": 1000000,
-        "mode": "chat",
+        "input_cost_per_token": 1e-07,
         "output_cost_per_token": 4e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/Gryphe/MythoMax-L2-13b-turbo": {
@@ -20008,43 +20052,43 @@
         "supports_tool_choice": true
     },
     "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": {
-        "input_cost_per_token": 1e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
+        "input_cost_per_token": 1e-07,
         "output_cost_per_token": 2.8e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct": {
-        "input_cost_per_token": 3e-08,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
+        "input_cost_per_token": 3e-08,
         "output_cost_per_token": 5e-08,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/Qwen/Qwen3-32B": {
-        "input_cost_per_token": 1e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 40960,
         "max_input_tokens": 40960,
         "max_output_tokens": 40960,
-        "max_tokens": 40960,
+        "input_cost_per_token": 1e-07,
+        "output_cost_per_token": 2.8e-07,
+        "litellm_provider": "deepinfra",
         "mode": "chat",
-        "output_cost_per_token": 3e-07,
         "supports_tool_choice": true
     },
     "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507": {
-        "input_cost_per_token": 1.3e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 262144,
         "max_input_tokens": 262144,
         "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "input_cost_per_token": 3e-07,
+        "output_cost_per_token": 2.9e-06,
+        "litellm_provider": "deepinfra",
         "mode": "chat",
-        "output_cost_per_token": 6e-07,
         "supports_tool_choice": true
     },
     "deepinfra/nvidia/Nemotron-4-340B-Instruct": {
@@ -20058,24 +20102,24 @@
         "supports_tool_choice": true
     },
     "deepinfra/deepseek-ai/DeepSeek-R1-0528": {
-        "cache_read_input_token_cost": 4e-07,
-        "input_cost_per_token": 5e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 163840,
         "max_input_tokens": 163840,
         "max_output_tokens": 163840,
-        "max_tokens": 163840,
-        "mode": "chat",
+        "input_cost_per_token": 5e-07,
         "output_cost_per_token": 2.15e-06,
+        "cache_read_input_token_cost": 4e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/deepseek-ai/DeepSeek-R1-Turbo": {
-        "input_cost_per_token": 1e-06,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 40960,
         "max_input_tokens": 40960,
         "max_output_tokens": 40960,
-        "max_tokens": 40960,
-        "mode": "chat",
+        "input_cost_per_token": 1e-06,
         "output_cost_per_token": 3e-06,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/NovaSky-AI/Sky-T1-32B-Preview": {
@@ -20089,13 +20133,13 @@
         "supports_tool_choice": false
     },
     "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507": {
-        "input_cost_per_token": 1.3e-07,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 262144,
         "max_input_tokens": 262144,
         "max_output_tokens": 262144,
-        "max_tokens": 262144,
-        "mode": "chat",
+        "input_cost_per_token": 9e-08,
         "output_cost_per_token": 6e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/mistralai/Mistral-Small-3.1-24B-Instruct-2503": {
@@ -20139,13 +20183,13 @@
         "supports_tool_choice": false
     },
     "deepinfra/google/gemma-3-4b-it": {
-        "input_cost_per_token": 4e-08,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
+        "input_cost_per_token": 4e-08,
         "output_cost_per_token": 8e-08,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": true
     },
     "deepinfra/mistralai/Mistral-7B-Instruct-v0.2": {
@@ -20159,13 +20203,13 @@
         "supports_tool_choice": false
     },
     "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo": {
-        "input_cost_per_token": 3.8e-08,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
+        "input_cost_per_token": 1.3e-07,
+        "output_cost_per_token": 3.9e-07,
+        "litellm_provider": "deepinfra",
         "mode": "chat",
-        "output_cost_per_token": 1.2e-07,
         "supports_tool_choice": true
     },
     "deepinfra/mistralai/Devstral-Small-2505": {
@@ -20179,23 +20223,23 @@
         "supports_tool_choice": true
     },
     "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct": {
-        "input_cost_per_token": 4.9e-08,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
+        "input_cost_per_token": 4.9e-08,
         "output_cost_per_token": 4.9e-08,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
         "supports_tool_choice": false
     },
     "deepinfra/openai/gpt-oss-20b": {
-        "input_cost_per_token": 4e-08,
-        "litellm_provider": "deepinfra",
+        "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "max_tokens": 131072,
+        "input_cost_per_token": 4e-08,
+        "output_cost_per_token": 1.5e-07,
+        "litellm_provider": "deepinfra",
         "mode": "chat",
-        "output_cost_per_token": 1.6e-07,
         "supports_tool_choice": true
     },
     "voyage/voyage-context-3": {
@@ -20431,6 +20475,8 @@
     },
     "openrouter/anthropic/claude-opus-4": {
         "input_cost_per_image": 0.0048,
+        "cache_creation_input_token_cost": 1.875e-05,
+        "cache_read_input_token_cost": 1.5e-06,
         "input_cost_per_token": 1.5e-05,
         "litellm_provider": "openrouter",
         "max_input_tokens": 200000,
@@ -20441,6 +20487,7 @@
         "supports_assistant_prefill": true,
         "supports_computer_use": true,
         "supports_function_calling": true,
+        "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
         "supports_vision": true,
@@ -20448,6 +20495,9 @@
     },
     "openrouter/anthropic/claude-opus-4.1": {
         "input_cost_per_image": 0.0048,
+        "cache_creation_input_token_cost": 1.875e-05,
+        "cache_creation_input_token_cost_above_1hr": 3e-05,
+        "cache_read_input_token_cost": 1.5e-06,
         "input_cost_per_token": 1.5e-05,
         "litellm_provider": "openrouter",
         "max_input_tokens": 200000,
@@ -20458,6 +20508,7 @@
         "supports_assistant_prefill": true,
         "supports_computer_use": true,
         "supports_function_calling": true,
+        "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
         "supports_vision": true,
@@ -22719,11 +22770,12 @@
         "max_tokens": 2000000.0,
         "mode": "chat",
         "input_cost_per_token": 2e-07,
+        "input_cost_per_token_above_128k_tokens": 4e-07,
         "output_cost_per_token": 5e-07,
+        "output_cost_per_token_above_128k_tokens": 1e-06,
         "cache_read_input_token_cost": 5e-08,
         "source": "https://docs.x.ai/docs/models",
         "supports_function_calling": true,
-        "supports_reasoning": true,
         "supports_tool_choice": true,
         "supports_web_search": true
     },
@@ -22735,7 +22787,9 @@
         "max_tokens": 2000000.0,
         "mode": "chat",
         "input_cost_per_token": 2e-07,
+        "input_cost_per_token_above_128k_tokens": 4e-07,
         "output_cost_per_token": 5e-07,
+        "output_cost_per_token_above_128k_tokens": 1e-06,
         "source": "https://docs.x.ai/docs/models",
         "supports_function_calling": true,
         "supports_tool_choice": true,
@@ -22825,11 +22879,11 @@
             "text"
         ],
         "supports_function_calling": true,
-        "supports_native_streaming": false,
+        "supports_native_streaming": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
-        "supports_reasoning": false,
+        "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_system_messages": false,
         "supports_tool_choice": true,
@@ -23363,10 +23417,14 @@
         "cache_creation_input_token_cost": 3.75e-06,
         "cache_read_input_token_cost": 3e-07,
         "input_cost_per_token": 3e-06,
+        "input_cost_per_token_above_200k_tokens": 6e-06,
+        "output_cost_per_token_above_200k_tokens": 2.25e-05,
+        "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "litellm_provider": "anthropic",
         "max_input_tokens": 200000,
         "max_output_tokens": 64000,
-        "max_tokens": 200000,
+        "max_tokens": 64000,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
         "search_context_cost_per_query": {
@@ -23383,6 +23441,7 @@
         "supports_response_schema": true,
         "supports_tool_choice": true,
         "supports_vision": true,
+        "supports_web_search": true,
         "tool_use_system_prompt_tokens": 346
     },
     "ollama/deepseek-v3.1:671b-cloud": {
@@ -23426,15 +23485,19 @@
         "supports_function_calling": true
     },
     "us.anthropic.claude-sonnet-4-5-20250929-v1:0": {
-        "cache_creation_input_token_cost": 3.75e-06,
-        "cache_read_input_token_cost": 3e-07,
-        "input_cost_per_token": 3e-06,
+        "cache_creation_input_token_cost": 4.125e-06,
+        "cache_read_input_token_cost": 3.3e-07,
+        "input_cost_per_token": 3.3e-06,
+        "input_cost_per_token_above_200k_tokens": 6.6e-06,
+        "output_cost_per_token_above_200k_tokens": 2.475e-05,
+        "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 6.6e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 200000,
         "max_output_tokens": 64000,
-        "max_tokens": 200000,
+        "max_tokens": 64000,
         "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
+        "output_cost_per_token": 1.65e-05,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
@@ -23455,11 +23518,15 @@
         "cache_creation_input_token_cost": 3.75e-06,
         "cache_read_input_token_cost": 3e-07,
         "input_cost_per_token": 3e-06,
+        "input_cost_per_token_above_200k_tokens": 6e-06,
+        "output_cost_per_token_above_200k_tokens": 2.25e-05,
+        "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "input_cost_per_token_batches": 1.5e-06,
         "litellm_provider": "vertex_ai-anthropic_models",
         "max_input_tokens": 200000,
         "max_output_tokens": 64000,
-        "max_tokens": 200000,
+        "max_tokens": 64000,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
         "output_cost_per_token_batches": 7.5e-06,
@@ -23477,11 +23544,15 @@
         "cache_creation_input_token_cost": 3.75e-06,
         "cache_read_input_token_cost": 3e-07,
         "input_cost_per_token": 3e-06,
+        "input_cost_per_token_above_200k_tokens": 6e-06,
+        "output_cost_per_token_above_200k_tokens": 2.25e-05,
+        "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "input_cost_per_token_batches": 1.5e-06,
         "litellm_provider": "vertex_ai-anthropic_models",
         "max_input_tokens": 200000,
         "max_output_tokens": 64000,
-        "max_tokens": 200000,
+        "max_tokens": 64000,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
         "output_cost_per_token_batches": 7.5e-06,
@@ -23499,10 +23570,14 @@
         "cache_creation_input_token_cost": 3.75e-06,
         "cache_read_input_token_cost": 3e-07,
         "input_cost_per_token": 3e-06,
+        "input_cost_per_token_above_200k_tokens": 6e-06,
+        "output_cost_per_token_above_200k_tokens": 2.25e-05,
+        "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "litellm_provider": "anthropic",
         "max_input_tokens": 200000,
         "max_output_tokens": 64000,
-        "max_tokens": 200000,
+        "max_tokens": 64000,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
         "search_context_cost_per_query": {
@@ -23524,8 +23599,8 @@
     "lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF": {
         "input_cost_per_token": 0,
         "litellm_provider": "lemonade",
-        "max_tokens": 32768,
-        "max_input_tokens": 32768,
+        "max_tokens": 262144,
+        "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 0,
@@ -23545,5 +23620,2094 @@
         "supports_function_calling": true,
         "supports_response_schema": true,
         "supports_tool_choice": true
+    },
+    "azure_ai/grok-4": {
+        "input_cost_per_token": 5.5e-06,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 2.75e-05,
+        "source": "https://azure.microsoft.com/en-us/blog/grok-4-is-now-available-in-azure-ai-foundry-unlock-frontier-intelligence-and-business-ready-capabilities/",
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_web_search": true
+    },
+    "azure_ai/grok-4-fast-non-reasoning": {
+        "input_cost_per_token": 4.3e-07,
+        "output_cost_per_token": 1.73e-06,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_web_search": true
+    },
+    "azure_ai/grok-4-fast-reasoning": {
+        "input_cost_per_token": 4.3e-07,
+        "output_cost_per_token": 1.73e-06,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/announcing-the-grok-4-fast-models-from-xai-now-available-in-azure-ai-foundry/4456701",
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_web_search": true
+    },
+    "azure_ai/grok-code-fast-1": {
+        "input_cost_per_token": 3.5e-06,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 1.75e-05,
+        "source": "https://azure.microsoft.com/en-us/blog/grok-4-is-now-available-in-azure-ai-foundry-unlock-frontier-intelligence-and-business-ready-capabilities/",
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_web_search": true
+    },
+    "eu.anthropic.claude-sonnet-4-5-20250929-v1:0": {
+        "cache_creation_input_token_cost": 4.125e-06,
+        "cache_read_input_token_cost": 3.3e-07,
+        "input_cost_per_token": 3.3e-06,
+        "input_cost_per_token_above_200k_tokens": 6.6e-06,
+        "output_cost_per_token_above_200k_tokens": 2.475e-05,
+        "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 6.6e-07,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 1.65e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_assistant_prefill": true,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "tool_use_system_prompt_tokens": 346
+    },
+    "nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3": {
+        "input_cost_per_query": 0.0,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "nvidia_nim",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0
+    },
+    "nvidia_nim/nvidia/llama-3_2-nv-rerankqa-1b-v2": {
+        "input_cost_per_query": 0.0,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "nvidia_nim",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0
+    },
+    "deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct": {
+        "max_tokens": 262144,
+        "max_input_tokens": 262144,
+        "max_output_tokens": 262144,
+        "input_cost_per_token": 1.4e-07,
+        "output_cost_per_token": 1.4e-06,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
+        "supports_tool_choice": true
+    },
+    "deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking": {
+        "max_tokens": 262144,
+        "max_input_tokens": 262144,
+        "max_output_tokens": 262144,
+        "input_cost_per_token": 1.4e-07,
+        "output_cost_per_token": 1.4e-06,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
+        "supports_tool_choice": true
+    },
+    "deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus": {
+        "max_tokens": 163840,
+        "max_input_tokens": 163840,
+        "max_output_tokens": 163840,
+        "input_cost_per_token": 2.7e-07,
+        "output_cost_per_token": 1e-06,
+        "cache_read_input_token_cost": 2.16e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
+        "supports_tool_choice": true
+    },
+    "deepinfra/moonshotai/Kimi-K2-Instruct-0905": {
+        "max_tokens": 262144,
+        "max_input_tokens": 262144,
+        "max_output_tokens": 262144,
+        "input_cost_per_token": 5e-07,
+        "output_cost_per_token": 2e-06,
+        "cache_read_input_token_cost": 4e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
+        "supports_tool_choice": true
+    },
+    "deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 1e-07,
+        "output_cost_per_token": 4e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
+        "supports_tool_choice": true
+    },
+    "deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 4e-08,
+        "output_cost_per_token": 1.6e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
+        "supports_tool_choice": true
+    },
+    "jp.anthropic.claude-sonnet-4-5-20250929-v1:0": {
+        "cache_creation_input_token_cost": 4.125e-06,
+        "cache_read_input_token_cost": 3.3e-07,
+        "input_cost_per_token": 3.3e-06,
+        "input_cost_per_token_above_200k_tokens": 6.6e-06,
+        "output_cost_per_token_above_200k_tokens": 2.475e-05,
+        "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 6.6e-07,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 1.65e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_assistant_prefill": true,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "tool_use_system_prompt_tokens": 346
+    },
+    "watsonx/bigscience/mt0-xxl-13b": {
+        "max_tokens": 8192,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.0005,
+        "output_cost_per_token": 0.002,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": false,
+        "supports_parallel_function_calling": false,
+        "supports_vision": false
+    },
+    "watsonx/core42/jais-13b-chat": {
+        "max_tokens": 8192,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.0005,
+        "output_cost_per_token": 0.002,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": false,
+        "supports_parallel_function_calling": false,
+        "supports_vision": false
+    },
+    "watsonx/google/flan-t5-xl-3b": {
+        "max_tokens": 8192,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 6e-07,
+        "output_cost_per_token": 6e-07,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": false,
+        "supports_parallel_function_calling": false,
+        "supports_vision": false
+    },
+    "watsonx/ibm/granite-13b-chat-v2": {
+        "max_tokens": 8192,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 6e-07,
+        "output_cost_per_token": 6e-07,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": false,
+        "supports_parallel_function_calling": false,
+        "supports_vision": false
+    },
+    "watsonx/ibm/granite-13b-instruct-v2": {
+        "max_tokens": 8192,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 6e-07,
+        "output_cost_per_token": 6e-07,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": false,
+        "supports_parallel_function_calling": false,
+        "supports_vision": false
+    },
+    "watsonx/ibm/granite-3-3-8b-instruct": {
+        "max_tokens": 8192,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 2e-07,
+        "output_cost_per_token": 2e-07,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_vision": false
+    },
+    "watsonx/ibm/granite-4-h-small": {
+        "max_tokens": 20480,
+        "max_input_tokens": 20480,
+        "max_output_tokens": 20480,
+        "input_cost_per_token": 6e-08,
+        "output_cost_per_token": 2.5e-07,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_vision": false
+    },
+    "watsonx/ibm/granite-guardian-3-2-2b": {
+        "max_tokens": 8192,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 1e-07,
+        "output_cost_per_token": 1e-07,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": false,
+        "supports_parallel_function_calling": false,
+        "supports_vision": false
+    },
+    "watsonx/ibm/granite-guardian-3-3-8b": {
+        "max_tokens": 8192,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 2e-07,
+        "output_cost_per_token": 2e-07,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": false,
+        "supports_parallel_function_calling": false,
+        "supports_vision": false
+    },
+    "watsonx/ibm/granite-ttm-1024-96-r2": {
+        "max_tokens": 512,
+        "max_input_tokens": 512,
+        "max_output_tokens": 512,
+        "input_cost_per_token": 3.8e-07,
+        "output_cost_per_token": 3.8e-07,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": false,
+        "supports_parallel_function_calling": false,
+        "supports_vision": false
+    },
+    "watsonx/ibm/granite-ttm-1536-96-r2": {
+        "max_tokens": 512,
+        "max_input_tokens": 512,
+        "max_output_tokens": 512,
+        "input_cost_per_token": 3.8e-07,
+        "output_cost_per_token": 3.8e-07,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": false,
+        "supports_parallel_function_calling": false,
+        "supports_vision": false
+    },
+    "watsonx/ibm/granite-ttm-512-96-r2": {
+        "max_tokens": 512,
+        "max_input_tokens": 512,
+        "max_output_tokens": 512,
+        "input_cost_per_token": 3.8e-07,
+        "output_cost_per_token": 3.8e-07,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": false,
+        "supports_parallel_function_calling": false,
+        "supports_vision": false
+    },
+    "watsonx/ibm/granite-vision-3-2-2b": {
+        "max_tokens": 8192,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 1e-07,
+        "output_cost_per_token": 1e-07,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": false,
+        "supports_parallel_function_calling": false,
+        "supports_vision": true
+    },
+    "watsonx/meta-llama/llama-3-2-11b-vision-instruct": {
+        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "input_cost_per_token": 3.5e-07,
+        "output_cost_per_token": 3.5e-07,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_vision": true
+    },
+    "watsonx/meta-llama/llama-3-2-1b-instruct": {
+        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "input_cost_per_token": 1e-07,
+        "output_cost_per_token": 1e-07,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_vision": false
+    },
+    "watsonx/meta-llama/llama-3-2-3b-instruct": {
+        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "input_cost_per_token": 1.5e-07,
+        "output_cost_per_token": 1.5e-07,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_vision": false
+    },
+    "watsonx/meta-llama/llama-3-2-90b-vision-instruct": {
+        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "input_cost_per_token": 2e-06,
+        "output_cost_per_token": 2e-06,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_vision": true
+    },
+    "watsonx/meta-llama/llama-3-3-70b-instruct": {
+        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "input_cost_per_token": 7.1e-07,
+        "output_cost_per_token": 7.1e-07,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_vision": false
+    },
+    "watsonx/meta-llama/llama-4-maverick-17b": {
+        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "input_cost_per_token": 3.5e-07,
+        "output_cost_per_token": 1.4e-06,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_vision": false
+    },
+    "watsonx/meta-llama/llama-guard-3-11b-vision": {
+        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "input_cost_per_token": 3.5e-07,
+        "output_cost_per_token": 3.5e-07,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": false,
+        "supports_parallel_function_calling": false,
+        "supports_vision": true
+    },
+    "watsonx/mistralai/mistral-medium-2505": {
+        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "input_cost_per_token": 3e-06,
+        "output_cost_per_token": 1e-05,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_vision": false
+    },
+    "watsonx/mistralai/mistral-small-2503": {
+        "max_tokens": 32000,
+        "max_input_tokens": 32000,
+        "max_output_tokens": 32000,
+        "input_cost_per_token": 1e-07,
+        "output_cost_per_token": 3e-07,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_vision": false
+    },
+    "watsonx/mistralai/pixtral-12b-2409": {
+        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "input_cost_per_token": 3.5e-07,
+        "output_cost_per_token": 3.5e-07,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": false,
+        "supports_parallel_function_calling": false,
+        "supports_vision": true
+    },
+    "watsonx/openai/gpt-oss-120b": {
+        "max_tokens": 8192,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 1.5e-07,
+        "output_cost_per_token": 6e-07,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": false,
+        "supports_parallel_function_calling": false,
+        "supports_vision": false
+    },
+    "watsonx/sdaia/allam-1-13b-instruct": {
+        "max_tokens": 8192,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 1.8e-06,
+        "output_cost_per_token": 1.8e-06,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": false,
+        "supports_parallel_function_calling": false,
+        "supports_vision": false
+    },
+    "global.anthropic.claude-sonnet-4-5-20250929-v1:0": {
+        "cache_creation_input_token_cost": 3.75e-06,
+        "cache_read_input_token_cost": 3e-07,
+        "input_cost_per_token": 3e-06,
+        "input_cost_per_token_above_200k_tokens": 6e-06,
+        "output_cost_per_token_above_200k_tokens": 2.25e-05,
+        "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 1.5e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_assistant_prefill": true,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "tool_use_system_prompt_tokens": 346
+    },
+    "global.anthropic.claude-sonnet-4-20250514-v1:0": {
+        "cache_creation_input_token_cost": 3.75e-06,
+        "cache_read_input_token_cost": 3e-07,
+        "input_cost_per_token": 3e-06,
+        "input_cost_per_token_above_200k_tokens": 6e-06,
+        "output_cost_per_token_above_200k_tokens": 2.25e-05,
+        "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 1.5e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_assistant_prefill": true,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "tool_use_system_prompt_tokens": 159
+    },
+    "gpt-5-pro": {
+        "input_cost_per_token": 1.5e-05,
+        "input_cost_per_token_batches": 7.5e-06,
+        "litellm_provider": "openai",
+        "max_input_tokens": 400000,
+        "max_output_tokens": 272000,
+        "max_tokens": 272000,
+        "mode": "responses",
+        "output_cost_per_token": 0.00012,
+        "output_cost_per_token_batches": 6e-05,
+        "supported_endpoints": [
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": false,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true
+    },
+    "gpt-image-1-mini": {
+        "cache_read_input_image_token_cost": 2.5e-07,
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_image_token": 2.5e-06,
+        "input_cost_per_token": 2e-06,
+        "litellm_provider": "openai",
+        "mode": "chat",
+        "output_cost_per_image_token": 8e-06,
+        "supported_endpoints": [
+            "/v1/images/generations",
+            "/v1/images/edits"
+        ]
+    },
+    "gpt-realtime-mini": {
+        "cache_creation_input_audio_token_cost": 3e-07,
+        "cache_read_input_audio_token_cost": 3e-07,
+        "input_cost_per_audio_token": 1e-05,
+        "input_cost_per_token": 6e-07,
+        "litellm_provider": "openai",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
+        "mode": "chat",
+        "output_cost_per_audio_token": 2e-05,
+        "output_cost_per_token": 2.4e-06,
+        "supported_endpoints": [
+            "/v1/realtime"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "audio"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true
+    },
+    "low/1024-x-1024/gpt-image-1-mini": {
+        "input_cost_per_image": 0.005,
+        "litellm_provider": "openai",
+        "mode": "image_generation",
+        "supported_endpoints": [
+            "/v1/images/generations"
+        ]
+    },
+    "low/1024-x-1536/gpt-image-1-mini": {
+        "input_cost_per_image": 0.006,
+        "litellm_provider": "openai",
+        "mode": "image_generation",
+        "supported_endpoints": [
+            "/v1/images/generations"
+        ]
+    },
+    "low/1536-x-1024/gpt-image-1-mini": {
+        "input_cost_per_image": 0.006,
+        "litellm_provider": "openai",
+        "mode": "image_generation",
+        "supported_endpoints": [
+            "/v1/images/generations"
+        ]
+    },
+    "medium/1024-x-1024/gpt-image-1-mini": {
+        "input_cost_per_image": 0.011,
+        "litellm_provider": "openai",
+        "mode": "image_generation",
+        "supported_endpoints": [
+            "/v1/images/generations"
+        ]
+    },
+    "medium/1024-x-1536/gpt-image-1-mini": {
+        "input_cost_per_image": 0.015,
+        "litellm_provider": "openai",
+        "mode": "image_generation",
+        "supported_endpoints": [
+            "/v1/images/generations"
+        ]
+    },
+    "medium/1536-x-1024/gpt-image-1-mini": {
+        "input_cost_per_image": 0.015,
+        "litellm_provider": "openai",
+        "mode": "image_generation",
+        "supported_endpoints": [
+            "/v1/images/generations"
+        ]
+    },
+    "cohere.embed-v4:0": {
+        "input_cost_per_token": 1.2e-07,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "embedding",
+        "output_cost_per_token": 0.0,
+        "output_vector_size": 1536,
+        "supports_embedding_image_input": true
+    },
+    "gpt-5-pro-2025-10-06": {
+        "input_cost_per_token": 1.5e-05,
+        "input_cost_per_token_batches": 7.5e-06,
+        "litellm_provider": "openai",
+        "max_input_tokens": 400000,
+        "max_output_tokens": 272000,
+        "max_tokens": 272000,
+        "mode": "responses",
+        "output_cost_per_token": 0.00012,
+        "output_cost_per_token_batches": 6e-05,
+        "supported_endpoints": [
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": false,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true
+    },
+    "azure_ai/Phi-4-mini-reasoning": {
+        "input_cost_per_token": 8e-08,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
+        "mode": "chat",
+        "output_cost_per_token": 3.2e-07,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/",
+        "supports_function_calling": true
+    },
+    "azure_ai/Phi-4-reasoning": {
+        "input_cost_per_token": 1.25e-07,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 32768,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_reasoning": true
+    },
+    "azure_ai/MAI-DS-R1": {
+        "input_cost_per_token": 1.35e-06,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "chat",
+        "output_cost_per_token": 5.4e-06,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/",
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
+    "au.anthropic.claude-sonnet-4-5-20250929-v1:0": {
+        "cache_creation_input_token_cost": 4.125e-06,
+        "cache_read_input_token_cost": 3.3e-07,
+        "input_cost_per_token": 3.3e-06,
+        "input_cost_per_token_above_200k_tokens": 6.6e-06,
+        "output_cost_per_token_above_200k_tokens": 2.475e-05,
+        "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 6.6e-07,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 1.65e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_assistant_prefill": true,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "tool_use_system_prompt_tokens": 346
+    },
+    "oci/cohere.command-latest": {
+        "input_cost_per_token": 1.56e-06,
+        "litellm_provider": "oci",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.56e-06,
+        "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
+        "supports_function_calling": true,
+        "supports_response_schema": false
+    },
+    "oci/cohere.command-a-03-2025": {
+        "input_cost_per_token": 1.56e-06,
+        "litellm_provider": "oci",
+        "max_input_tokens": 256000,
+        "max_output_tokens": 4000,
+        "max_tokens": 256000,
+        "mode": "chat",
+        "output_cost_per_token": 1.56e-06,
+        "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
+        "supports_function_calling": true,
+        "supports_response_schema": false
+    },
+    "oci/cohere.command-plus-latest": {
+        "input_cost_per_token": 1.56e-06,
+        "litellm_provider": "oci",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.56e-06,
+        "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
+        "supports_function_calling": true,
+        "supports_response_schema": false
+    },
+    "together_ai/moonshotai/Kimi-K2-Instruct-0905": {
+        "input_cost_per_token": 1e-06,
+        "litellm_provider": "together_ai",
+        "max_input_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 3e-06,
+        "source": "https://www.together.ai/models/kimi-k2-0905",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true
+    },
+    "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct": {
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "together_ai",
+        "max_input_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 1.5e-06,
+        "source": "https://www.together.ai/models/qwen3-next-80b-a3b-instruct",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true
+    },
+    "together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking": {
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "together_ai",
+        "max_input_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 1.5e-06,
+        "source": "https://www.together.ai/models/qwen3-next-80b-a3b-thinking",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true
+    },
+    "together_ai/baai/bge-base-en-v1.5": {
+        "input_cost_per_token": 8e-09,
+        "litellm_provider": "together_ai",
+        "max_input_tokens": 512,
+        "mode": "embedding",
+        "output_cost_per_token": 0.0,
+        "output_vector_size": 768
+    },
+    "together_ai/BAAI/bge-base-en-v1.5": {
+        "input_cost_per_token": 8e-09,
+        "litellm_provider": "together_ai",
+        "max_input_tokens": 512,
+        "mode": "embedding",
+        "output_cost_per_token": 0.0,
+        "output_vector_size": 768
+    },
+    "openrouter/anthropic/claude-sonnet-4.5": {
+        "input_cost_per_image": 0.0048,
+        "cache_creation_input_token_cost": 3.75e-06,
+        "cache_read_input_token_cost": 3e-07,
+        "input_cost_per_token": 3e-06,
+        "input_cost_per_token_above_200k_tokens": 6e-06,
+        "output_cost_per_token_above_200k_tokens": 2.25e-05,
+        "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
+        "litellm_provider": "openrouter",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
+        "mode": "chat",
+        "output_cost_per_token": 1.5e-05,
+        "supports_assistant_prefill": true,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "tool_use_system_prompt_tokens": 159
+    },
+    "anthropic.claude-haiku-4-5-20251001-v1:0": {
+        "cache_creation_input_token_cost": 1.25e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "input_cost_per_token": 1e-06,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "chat",
+        "output_cost_per_token": 5e-06,
+        "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock",
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "anthropic.claude-haiku-4-5@20251001": {
+        "cache_creation_input_token_cost": 1.25e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "input_cost_per_token": 1e-06,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "chat",
+        "output_cost_per_token": 5e-06,
+        "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock",
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "apac.anthropic.claude-haiku-4-5-20251001-v1:0": {
+        "cache_creation_input_token_cost": 1.375e-06,
+        "cache_read_input_token_cost": 1.1e-07,
+        "input_cost_per_token": 1.1e-06,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "chat",
+        "output_cost_per_token": 5.5e-06,
+        "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock",
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "claude-haiku-4-5-20251001": {
+        "cache_creation_input_token_cost": 1.25e-06,
+        "cache_creation_input_token_cost_above_1hr": 2e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "input_cost_per_token": 1e-06,
+        "litellm_provider": "anthropic",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-06,
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_computer_use": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "claude-haiku-4-5": {
+        "cache_creation_input_token_cost": 1.25e-06,
+        "cache_creation_input_token_cost_above_1hr": 2e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "input_cost_per_token": 1e-06,
+        "litellm_provider": "anthropic",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-06,
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_computer_use": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "eu.anthropic.claude-haiku-4-5-20251001-v1:0": {
+        "cache_creation_input_token_cost": 1.375e-06,
+        "cache_read_input_token_cost": 1.1e-07,
+        "input_cost_per_token": 1.1e-06,
+        "deprecation_date": "2026-10-15",
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "chat",
+        "output_cost_per_token": 5.5e-06,
+        "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock",
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "gemini-2.5-flash-image": {
+        "cache_read_input_token_cost": 3e-08,
+        "input_cost_per_audio_token": 1e-06,
+        "input_cost_per_token": 3e-07,
+        "litellm_provider": "vertex_ai-language-models",
+        "max_audio_length_hours": 8.4,
+        "max_audio_per_prompt": 1,
+        "max_images_per_prompt": 3000,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "max_pdf_size_mb": 30,
+        "max_video_length": 1,
+        "max_videos_per_prompt": 10,
+        "mode": "image_generation",
+        "output_cost_per_image": 0.039,
+        "output_cost_per_reasoning_token": 2.5e-06,
+        "output_cost_per_token": 2.5e-06,
+        "rpm": 100000,
+        "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "supports_audio_output": false,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_url_context": true,
+        "supports_vision": true,
+        "supports_web_search": false,
+        "tpm": 8000000
+    },
+    "gemini/gemini-2.5-flash-image": {
+        "cache_read_input_token_cost": 3e-08,
+        "input_cost_per_audio_token": 1e-06,
+        "input_cost_per_token": 3e-07,
+        "litellm_provider": "vertex_ai-language-models",
+        "max_audio_length_hours": 8.4,
+        "max_audio_per_prompt": 1,
+        "max_images_per_prompt": 3000,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "max_pdf_size_mb": 30,
+        "max_video_length": 1,
+        "max_videos_per_prompt": 10,
+        "mode": "image_generation",
+        "output_cost_per_image": 0.039,
+        "output_cost_per_reasoning_token": 2.5e-06,
+        "output_cost_per_token": 2.5e-06,
+        "rpm": 100000,
+        "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "supports_audio_output": false,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_url_context": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "tpm": 8000000
+    },
+    "lemonade/gpt-oss-20b-mxfp4-GGUF": {
+        "input_cost_per_token": 0,
+        "litellm_provider": "lemonade",
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 32768,
+        "mode": "chat",
+        "output_cost_per_token": 0,
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "lemonade/gpt-oss-120b-mxfp-GGUF": {
+        "input_cost_per_token": 0,
+        "litellm_provider": "lemonade",
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 32768,
+        "mode": "chat",
+        "output_cost_per_token": 0,
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "lemonade/Gemma-3-4b-it-GGUF": {
+        "input_cost_per_token": 0,
+        "litellm_provider": "lemonade",
+        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 8192,
+        "mode": "chat",
+        "output_cost_per_token": 0,
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "lemonade/Qwen3-4B-Instruct-2507-GGUF": {
+        "input_cost_per_token": 0,
+        "litellm_provider": "lemonade",
+        "max_tokens": 262144,
+        "max_input_tokens": 262144,
+        "max_output_tokens": 32768,
+        "mode": "chat",
+        "output_cost_per_token": 0,
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "jp.anthropic.claude-haiku-4-5-20251001-v1:0": {
+        "cache_creation_input_token_cost": 1.375e-06,
+        "cache_read_input_token_cost": 1.1e-07,
+        "input_cost_per_token": 1.1e-06,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "chat",
+        "output_cost_per_token": 5.5e-06,
+        "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock",
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "us.anthropic.claude-haiku-4-5-20251001-v1:0": {
+        "cache_creation_input_token_cost": 1.375e-06,
+        "cache_read_input_token_cost": 1.1e-07,
+        "input_cost_per_token": 1.1e-06,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "chat",
+        "output_cost_per_token": 5.5e-06,
+        "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock",
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "vertex_ai/claude-haiku-4-5@20251001": {
+        "cache_creation_input_token_cost": 1.25e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "input_cost_per_token": 1e-06,
+        "litellm_provider": "vertex_ai-anthropic_models",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "chat",
+        "output_cost_per_token": 5e-06,
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5",
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "azure_ai/mistral-document-ai-2505": {
+        "litellm_provider": "azure_ai",
+        "ocr_cost_per_page": 0.003,
+        "mode": "ocr",
+        "supported_endpoints": [
+            "/v1/ocr"
+        ],
+        "source": "https://devblogs.microsoft.com/foundry/whats-new-in-azure-ai-foundry-august-2025/#mistral-document-ai-(ocr)-%E2%80%94-serverless-in-foundry"
+    },
+    "mistral/mistral-ocr-latest": {
+        "litellm_provider": "mistral",
+        "ocr_cost_per_page": 0.001,
+        "annotation_cost_per_page": 0.003,
+        "mode": "ocr",
+        "supported_endpoints": [
+            "/v1/ocr"
+        ],
+        "source": "https://mistral.ai/pricing#api-pricing"
+    },
+    "mistral/mistral-ocr-2505-completion": {
+        "litellm_provider": "mistral",
+        "ocr_cost_per_page": 0.001,
+        "annotation_cost_per_page": 0.003,
+        "mode": "ocr",
+        "supported_endpoints": [
+            "/v1/ocr"
+        ],
+        "source": "https://mistral.ai/pricing#api-pricing"
+    },
+    "watsonx/mistralai/mistral-small-3-1-24b-instruct-2503": {
+        "max_tokens": 32000,
+        "max_input_tokens": 32000,
+        "max_output_tokens": 32000,
+        "input_cost_per_token": 1e-07,
+        "output_cost_per_token": 3e-07,
+        "litellm_provider": "watsonx",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_vision": false
+    },
+    "global.anthropic.claude-haiku-4-5-20251001-v1:0": {
+        "cache_creation_input_token_cost": 1.375e-06,
+        "cache_read_input_token_cost": 1.1e-07,
+        "input_cost_per_token": 1.1e-06,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "chat",
+        "output_cost_per_token": 5.5e-06,
+        "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock",
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "tool_use_system_prompt_tokens": 346
+    },
+    "au.anthropic.claude-haiku-4-5-20251001-v1:0": {
+        "cache_creation_input_token_cost": 1.375e-06,
+        "cache_read_input_token_cost": 1.1e-07,
+        "input_cost_per_token": 1.1e-06,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "chat",
+        "output_cost_per_token": 5.5e-06,
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "tool_use_system_prompt_tokens": 346
+    },
+    "vercel_ai_gateway/glm-4.6": {
+        "litellm_provider": "vercel_ai_gateway",
+        "cache_read_input_token_cost": 1.1e-07,
+        "input_cost_per_token": 6e-07,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 200000,
+        "max_tokens": 200000,
+        "mode": "chat",
+        "output_cost_per_token": 2.2e-06
+    },
+    "azure/speech/azure-tts": {
+        "input_cost_per_character": 1.5e-05,
+        "litellm_provider": "azure",
+        "mode": "audio_speech",
+        "source": "https://azure.microsoft.com/en-us/pricing/calculator/"
+    },
+    "azure/speech/azure-tts-hd": {
+        "input_cost_per_character": 3e-05,
+        "litellm_provider": "azure",
+        "mode": "audio_speech",
+        "source": "https://azure.microsoft.com/en-us/pricing/calculator/"
+    },
+    "bedrock/us-gov-west-1/anthropic.claude-3-7-sonnet-20240620-v1:0": {
+        "cache_creation_input_token_cost": 4.5e-06,
+        "cache_read_input_token_cost": 3.6e-07,
+        "input_cost_per_token": 3.6e-06,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "chat",
+        "output_cost_per_token": 1.8e-05,
+        "supports_assistant_prefill": true,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "anthropic.claude-3-7-sonnet-20240620-v1:0": {
+        "cache_creation_input_token_cost": 4.5e-06,
+        "cache_read_input_token_cost": 3.6e-07,
+        "input_cost_per_token": 3.6e-06,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "chat",
+        "output_cost_per_token": 1.8e-05,
+        "supports_assistant_prefill": true,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "bedrock/us-gov-west-1/anthropic.claude-3-7-sonnet-20250219-v1:0": {
+        "cache_creation_input_token_cost": 4.5e-06,
+        "cache_read_input_token_cost": 3.6e-07,
+        "input_cost_per_token": 3.6e-06,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "chat",
+        "output_cost_per_token": 1.8e-05,
+        "supports_assistant_prefill": true,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "dataforseo/search": {
+        "input_cost_per_query": 0.003,
+        "litellm_provider": "dataforseo",
+        "mode": "search"
+    },
+    "exa_ai/search": {
+        "litellm_provider": "exa_ai",
+        "mode": "search",
+        "tiered_pricing": [
+            {
+                "input_cost_per_query": 0.005,
+                "max_results_range": [
+                    0,
+                    25
+                ]
+            },
+            {
+                "input_cost_per_query": 0.025,
+                "max_results_range": [
+                    26,
+                    100
+                ]
+            }
+        ]
+    },
+    "perplexity/search": {
+        "input_cost_per_query": 0.005,
+        "litellm_provider": "perplexity",
+        "mode": "search"
+    },
+    "google_pse/search": {
+        "input_cost_per_query": 0.005,
+        "litellm_provider": "google_pse",
+        "mode": "search"
+    },
+    "parallel_ai/search": {
+        "input_cost_per_query": 0.004,
+        "litellm_provider": "parallel_ai",
+        "mode": "search"
+    },
+    "parallel_ai/search-pro": {
+        "input_cost_per_query": 0.009,
+        "litellm_provider": "parallel_ai",
+        "mode": "search"
+    },
+    "tavily/search": {
+        "input_cost_per_query": 0.008,
+        "litellm_provider": "tavily",
+        "mode": "search"
+    },
+    "tavily/search-advanced": {
+        "input_cost_per_query": 0.016,
+        "litellm_provider": "tavily",
+        "mode": "search"
+    },
+    "vertex_ai/mistralai/codestral-2@001": {
+        "input_cost_per_token": 3e-07,
+        "litellm_provider": "vertex_ai-mistral_models",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 9e-07,
+        "supports_function_calling": true,
+        "supports_tool_choice": true
+    },
+    "vertex_ai/codestral-2": {
+        "input_cost_per_token": 3e-07,
+        "litellm_provider": "vertex_ai-mistral_models",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 9e-07,
+        "supports_function_calling": true,
+        "supports_tool_choice": true
+    },
+    "vertex_ai/codestral-2@001": {
+        "input_cost_per_token": 3e-07,
+        "litellm_provider": "vertex_ai-mistral_models",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 9e-07,
+        "supports_function_calling": true,
+        "supports_tool_choice": true
+    },
+    "vertex_ai/mistralai/codestral-2": {
+        "input_cost_per_token": 3e-07,
+        "litellm_provider": "vertex_ai-mistral_models",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 9e-07,
+        "supports_function_calling": true,
+        "supports_tool_choice": true
+    },
+    "vertex_ai/mistral-medium-3": {
+        "input_cost_per_token": 4e-07,
+        "litellm_provider": "vertex_ai-mistral_models",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 8191,
+        "max_tokens": 8191,
+        "mode": "chat",
+        "output_cost_per_token": 2e-06,
+        "supports_function_calling": true,
+        "supports_tool_choice": true
+    },
+    "vertex_ai/mistral-medium-3@001": {
+        "input_cost_per_token": 4e-07,
+        "litellm_provider": "vertex_ai-mistral_models",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 8191,
+        "max_tokens": 8191,
+        "mode": "chat",
+        "output_cost_per_token": 2e-06,
+        "supports_function_calling": true,
+        "supports_tool_choice": true
+    },
+    "vertex_ai/mistralai/mistral-medium-3": {
+        "input_cost_per_token": 4e-07,
+        "litellm_provider": "vertex_ai-mistral_models",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 8191,
+        "max_tokens": 8191,
+        "mode": "chat",
+        "output_cost_per_token": 2e-06,
+        "supports_function_calling": true,
+        "supports_tool_choice": true
+    },
+    "vertex_ai/mistralai/mistral-medium-3@001": {
+        "input_cost_per_token": 4e-07,
+        "litellm_provider": "vertex_ai-mistral_models",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 8191,
+        "max_tokens": 8191,
+        "mode": "chat",
+        "output_cost_per_token": 2e-06,
+        "supports_function_calling": true,
+        "supports_tool_choice": true
+    },
+    "openai/sora-2": {
+        "litellm_provider": "openai",
+        "mode": "video_generation",
+        "output_cost_per_video_per_second": 0.1,
+        "source": "https://platform.openai.com/docs/api-reference/videos",
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_resolutions": [
+            "720x1280",
+            "1280x720"
+        ]
+    },
+    "azure/sora-2": {
+        "litellm_provider": "azure",
+        "mode": "video_generation",
+        "output_cost_per_video_per_second": 0.1,
+        "source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation",
+        "supported_modalities": [
+            "text"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_resolutions": [
+            "720x1280",
+            "1280x720"
+        ]
+    },
+    "azure/sora-2-pro": {
+        "litellm_provider": "azure",
+        "mode": "video_generation",
+        "output_cost_per_video_per_second": 0.3,
+        "source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation",
+        "supported_modalities": [
+            "text"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_resolutions": [
+            "720x1280",
+            "1280x720"
+        ]
+    },
+    "azure/sora-2-pro-high-res": {
+        "litellm_provider": "azure",
+        "mode": "video_generation",
+        "output_cost_per_video_per_second": 0.5,
+        "source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation",
+        "supported_modalities": [
+            "text"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_resolutions": [
+            "1024x1792",
+            "1792x1024"
+        ]
+    },
+    "amazon.titan-image-generator-v1": {
+        "input_cost_per_image": 0.0,
+        "output_cost_per_image": 0.008,
+        "output_cost_per_image_premium_image": 0.01,
+        "output_cost_per_image_above_512_and_512_pixels": 0.01,
+        "output_cost_per_image_above_512_and_512_pixels_and_premium_image": 0.012,
+        "litellm_provider": "bedrock",
+        "mode": "image_generation"
+    },
+    "amazon.titan-image-generator-v2": {
+        "input_cost_per_image": 0.0,
+        "output_cost_per_image": 0.008,
+        "output_cost_per_image_premium_image": 0.01,
+        "output_cost_per_image_above_1024_and_1024_pixels": 0.01,
+        "output_cost_per_image_above_1024_and_1024_pixels_and_premium_image": 0.012,
+        "litellm_provider": "bedrock",
+        "mode": "image_generation"
+    },
+    "vertex_ai/search_api": {
+        "input_cost_per_query": 0.0015,
+        "litellm_provider": "vertex_ai",
+        "mode": "vector_store"
+    },
+    "openai/sora-2-pro": {
+        "litellm_provider": "openai",
+        "mode": "video_generation",
+        "output_cost_per_video_per_second": 0.3,
+        "source": "https://platform.openai.com/docs/api-reference/videos",
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_resolutions": [
+            "720x1280",
+            "1280x720"
+        ]
+    },
+    "openrouter/anthropic/claude-haiku-4.5": {
+        "cache_creation_input_token_cost": 1.25e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "input_cost_per_token": 1e-06,
+        "litellm_provider": "openrouter",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 200000,
+        "max_tokens": 200000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-06,
+        "supports_assistant_prefill": true,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "tool_use_system_prompt_tokens": 346
+    },
+    "fal_ai/bria/text-to-image/3.2": {
+        "litellm_provider": "fal_ai",
+        "mode": "image_generation",
+        "output_cost_per_image": 0.0398,
+        "supported_endpoints": [
+            "/v1/images/generations"
+        ]
+    },
+    "fal_ai/fal-ai/flux-pro/v1.1-ultra": {
+        "litellm_provider": "fal_ai",
+        "mode": "image_generation",
+        "output_cost_per_image": 0.0398,
+        "supported_endpoints": [
+            "/v1/images/generations"
+        ]
+    },
+    "fal_ai/fal-ai/imagen4/preview": {
+        "litellm_provider": "fal_ai",
+        "mode": "image_generation",
+        "output_cost_per_image": 0.0398,
+        "supported_endpoints": [
+            "/v1/images/generations"
+        ]
+    },
+    "fal_ai/fal-ai/recraft/v3/text-to-image": {
+        "litellm_provider": "fal_ai",
+        "mode": "image_generation",
+        "output_cost_per_image": 0.0398,
+        "supported_endpoints": [
+            "/v1/images/generations"
+        ]
+    },
+    "fal_ai/fal-ai/stable-diffusion-v35-medium": {
+        "litellm_provider": "fal_ai",
+        "mode": "image_generation",
+        "output_cost_per_image": 0.0398,
+        "supported_endpoints": [
+            "/v1/images/generations"
+        ]
+    },
+    "mistral/codestral-embed": {
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "mistral",
+        "max_input_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "embedding"
+    },
+    "mistral/codestral-embed-2505": {
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "mistral",
+        "max_input_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "embedding"
+    },
+    "gemini/gemini-embedding-001": {
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "gemini",
+        "max_input_tokens": 2048,
+        "max_tokens": 2048,
+        "mode": "embedding",
+        "output_cost_per_token": 0,
+        "output_vector_size": 3072,
+        "rpm": 10000,
+        "source": "https://ai.google.dev/gemini-api/docs/embeddings#model-versions",
+        "tpm": 10000000
+    },
+    "vercel_ai_gateway/zai/glm-4.6": {
+        "litellm_provider": "vercel_ai_gateway",
+        "cache_read_input_token_cost": 1.1e-07,
+        "input_cost_per_token": 4.5e-07,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 200000,
+        "max_tokens": 200000,
+        "mode": "chat",
+        "output_cost_per_token": 1.8e-06,
+        "source": "https://vercel.com/ai-gateway/models/glm-4.6",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true
+    },
+    "openrouter/nvidia/nemotron-nano-9b-v2:free": {
+        "input_cost_per_token": 0,
+        "litellm_provider": "openrouter",
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 0,
+        "source": "https://openrouter.ai/nvidia/nemotron-nano-9b-v2:free",
+        "supports_tool_choice": true
+    },
+    "openai/container": {
+        "code_interpreter_cost_per_session": 0.03,
+        "litellm_provider": "openai",
+        "mode": "chat"
+    },
+    "azure/container": {
+        "code_interpreter_cost_per_session": 0.03,
+        "litellm_provider": "azure",
+        "mode": "chat"
+    },
+    "vertex_ai/mistral-ocr-2505": {
+        "litellm_provider": "vertex_ai",
+        "mode": "ocr",
+        "ocr_cost_per_page": 0.0005,
+        "supported_endpoints": [
+            "/v1/ocr"
+        ],
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "azure_ai/doc-intelligence/prebuilt-read": {
+        "litellm_provider": "azure_ai",
+        "ocr_cost_per_page": 0.0015,
+        "mode": "ocr",
+        "supported_endpoints": [
+            "/v1/ocr"
+        ],
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/"
+    },
+    "azure_ai/doc-intelligence/prebuilt-layout": {
+        "litellm_provider": "azure_ai",
+        "ocr_cost_per_page": 0.01,
+        "mode": "ocr",
+        "supported_endpoints": [
+            "/v1/ocr"
+        ],
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/"
+    },
+    "azure_ai/doc-intelligence/prebuilt-document": {
+        "litellm_provider": "azure_ai",
+        "ocr_cost_per_page": 0.01,
+        "mode": "ocr",
+        "supported_endpoints": [
+            "/v1/ocr"
+        ],
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/"
+    },
+    "gemini-live-2.5-flash-preview-native-audio-09-2025": {
+        "cache_read_input_token_cost": 7.5e-08,
+        "input_cost_per_audio_token": 3e-06,
+        "input_cost_per_token": 3e-07,
+        "litellm_provider": "vertex_ai-language-models",
+        "max_audio_length_hours": 8.4,
+        "max_audio_per_prompt": 1,
+        "max_images_per_prompt": 3000,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 65535,
+        "max_pdf_size_mb": 30,
+        "max_tokens": 65535,
+        "max_video_length": 1,
+        "max_videos_per_prompt": 10,
+        "mode": "chat",
+        "output_cost_per_audio_token": 1.2e-05,
+        "output_cost_per_token": 2e-06,
+        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "audio"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_url_context": true,
+        "supports_vision": true,
+        "supports_web_search": true
+    },
+    "gemini/gemini-live-2.5-flash-preview-native-audio-09-2025": {
+        "cache_read_input_token_cost": 7.5e-08,
+        "input_cost_per_audio_token": 3e-06,
+        "input_cost_per_token": 3e-07,
+        "litellm_provider": "gemini",
+        "max_audio_length_hours": 8.4,
+        "max_audio_per_prompt": 1,
+        "max_images_per_prompt": 3000,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 65535,
+        "max_pdf_size_mb": 30,
+        "max_tokens": 65535,
+        "max_video_length": 1,
+        "max_videos_per_prompt": 10,
+        "mode": "chat",
+        "output_cost_per_audio_token": 1.2e-05,
+        "output_cost_per_token": 2e-06,
+        "rpm": 100000,
+        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "audio"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_url_context": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "tpm": 8000000
+    },
+    "azure/gpt-image-1-mini": {
+        "input_cost_per_pixel": 8.0566406e-09,
+        "litellm_provider": "azure",
+        "mode": "image_generation",
+        "output_cost_per_pixel": 0.0,
+        "supported_endpoints": [
+            "/v1/images/generations"
+        ]
+    },
+    "azure/low/1024-x-1024/gpt-image-1-mini": {
+        "input_cost_per_pixel": 2.0751953125e-09,
+        "litellm_provider": "azure",
+        "mode": "image_generation",
+        "output_cost_per_pixel": 0.0,
+        "supported_endpoints": [
+            "/v1/images/generations"
+        ]
+    },
+    "azure/low/1024-x-1536/gpt-image-1-mini": {
+        "input_cost_per_pixel": 2.0751953125e-09,
+        "litellm_provider": "azure",
+        "mode": "image_generation",
+        "output_cost_per_pixel": 0.0,
+        "supported_endpoints": [
+            "/v1/images/generations"
+        ]
+    },
+    "azure/low/1536-x-1024/gpt-image-1-mini": {
+        "input_cost_per_pixel": 2.0345052083e-09,
+        "litellm_provider": "azure",
+        "mode": "image_generation",
+        "output_cost_per_pixel": 0.0,
+        "supported_endpoints": [
+            "/v1/images/generations"
+        ]
+    },
+    "azure/medium/1024-x-1024/gpt-image-1-mini": {
+        "input_cost_per_pixel": 8.056640625e-09,
+        "litellm_provider": "azure",
+        "mode": "image_generation",
+        "output_cost_per_pixel": 0.0,
+        "supported_endpoints": [
+            "/v1/images/generations"
+        ]
+    },
+    "azure/medium/1024-x-1536/gpt-image-1-mini": {
+        "input_cost_per_pixel": 8.056640625e-09,
+        "litellm_provider": "azure",
+        "mode": "image_generation",
+        "output_cost_per_pixel": 0.0,
+        "supported_endpoints": [
+            "/v1/images/generations"
+        ]
+    },
+    "azure/medium/1536-x-1024/gpt-image-1-mini": {
+        "input_cost_per_pixel": 7.9752604167e-09,
+        "litellm_provider": "azure",
+        "mode": "image_generation",
+        "output_cost_per_pixel": 0.0,
+        "supported_endpoints": [
+            "/v1/images/generations"
+        ]
+    },
+    "azure/high/1024-x-1024/gpt-image-1-mini": {
+        "input_cost_per_pixel": 3.173828125e-08,
+        "litellm_provider": "azure",
+        "mode": "image_generation",
+        "output_cost_per_pixel": 0.0,
+        "supported_endpoints": [
+            "/v1/images/generations"
+        ]
+    },
+    "azure/high/1024-x-1536/gpt-image-1-mini": {
+        "input_cost_per_pixel": 3.173828125e-08,
+        "litellm_provider": "azure",
+        "mode": "image_generation",
+        "output_cost_per_pixel": 0.0,
+        "supported_endpoints": [
+            "/v1/images/generations"
+        ]
+    },
+    "azure/high/1536-x-1024/gpt-image-1-mini": {
+        "input_cost_per_pixel": 3.1575520833e-08,
+        "litellm_provider": "azure",
+        "mode": "image_generation",
+        "output_cost_per_pixel": 0.0,
+        "supported_endpoints": [
+            "/v1/images/generations"
+        ]
+    },
+    "firecrawl/search": {
+        "litellm_provider": "firecrawl",
+        "mode": "search",
+        "tiered_pricing": [
+            {
+                "input_cost_per_query": 0.00166,
+                "max_results_range": [
+                    1,
+                    10
+                ]
+            },
+            {
+                "input_cost_per_query": 0.00332,
+                "max_results_range": [
+                    11,
+                    20
+                ]
+            },
+            {
+                "input_cost_per_query": 0.00498,
+                "max_results_range": [
+                    21,
+                    30
+                ]
+            },
+            {
+                "input_cost_per_query": 0.00664,
+                "max_results_range": [
+                    31,
+                    40
+                ]
+            },
+            {
+                "input_cost_per_query": 0.0083,
+                "max_results_range": [
+                    41,
+                    50
+                ]
+            },
+            {
+                "input_cost_per_query": 0.00996,
+                "max_results_range": [
+                    51,
+                    60
+                ]
+            },
+            {
+                "input_cost_per_query": 0.01162,
+                "max_results_range": [
+                    61,
+                    70
+                ]
+            },
+            {
+                "input_cost_per_query": 0.01328,
+                "max_results_range": [
+                    71,
+                    80
+                ]
+            },
+            {
+                "input_cost_per_query": 0.01494,
+                "max_results_range": [
+                    81,
+                    90
+                ]
+            },
+            {
+                "input_cost_per_query": 0.0166,
+                "max_results_range": [
+                    91,
+                    100
+                ]
+            }
+        ],
+        "metadata": {
+            "notes": "Firecrawl search pricing: $83 for 100,000 credits, 2 credits per 10 results. Cost = ceiling(limit/10) * 2 * $0.00083"
+        }
+    },
+    "searxng/search": {
+        "litellm_provider": "searxng",
+        "mode": "search",
+        "input_cost_per_query": 0.0,
+        "metadata": {
+            "notes": "SearXNG is an open-source metasearch engine. Free to use when self-hosted or using public instances."
+        }
+    },
+    "azure/gpt-5-pro": {
+        "input_cost_per_token": 1.5e-05,
+        "litellm_provider": "azure",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 400000,
+        "mode": "responses",
+        "output_cost_per_token": 0.00012,
+        "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?pivots=azure-openai&tabs=global-standard-aoai%2Cstandard-chat-completions%2Cglobal-standard#gpt-5",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "vertex_ai/minimaxai/minimax-m2-maas": {
+        "input_cost_per_token": 3e-07,
+        "litellm_provider": "vertex_ai-minimax_models",
+        "max_input_tokens": 196608,
+        "max_output_tokens": 196608,
+        "max_tokens": 196608,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
+        "supports_function_calling": true,
+        "supports_tool_choice": true
     }
 }