tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-12 20:22:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update model_prices (#9768)

Browse Source
This commit is contained in:
Michael Clark
2025-04-05 09:20:01 -07:00
committed by GitHub
parent d4d3c4f697
commit cd0a1e6000
1 changed files with 63 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
model_prices_and_context_window.json
+63 -2
View File
@@ -4847,6 +4847,33 @@
"supports_tool_choice": true,
"source": "https://ai.google.dev/pricing#2_0flash"
},
"gemini/gemini-2.5-pro-preview-03-25": {
"max_tokens": 65536,
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_images_per_prompt": 3000,
"max_videos_per_prompt": 10,
"max_video_length": 1,
"max_audio_length_hours": 8.4,
"max_audio_per_prompt": 1,
"max_pdf_size_mb": 30,
"input_cost_per_audio_token": 0.0000007,
"input_cost_per_token": 0.00000125,
"input_cost_per_token_above_128k_tokens": 0.0000025,
"output_cost_per_token": 0.0000010,
"output_cost_per_token_above_128k_tokens": 0.000015,
"litellm_provider": "gemini",
"mode": "chat",
"rpm": 10000,
"tpm": 10000000,
"supports_system_messages": true,
"supports_function_calling": true,
"supports_vision": true,
"supports_response_schema": true,
"supports_audio_output": false,
"supports_tool_choice": true,
"source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview"
},
"gemini/gemini-2.0-flash-exp": {
"max_tokens": 8192,
"max_input_tokens": 1048576,
@@ -6665,6 +6692,14 @@
"mode": "chat",
"supports_tool_choice": true
},
"mistralai/mistral-small-3.1-24b-instruct": {
"max_tokens": 32000,
"input_cost_per_token": 0.0000001,
"output_cost_per_token": 0.0000003,
"litellm_provider": "openrouter",
"mode": "chat",
"supports_tool_choice": true
},
"openrouter/cognitivecomputations/dolphin-mixtral-8x7b": {
"max_tokens": 32769,
"input_cost_per_token": 0.0000005,
@@ -6793,12 +6828,38 @@
"supports_vision": false,
"supports_tool_choice": true
},
"openrouter/openai/o3-mini": {
"max_tokens": 65536,
"max_input_tokens": 128000,
"max_output_tokens": 65536,
"input_cost_per_token": 0.0000011,
"output_cost_per_token": 0.0000044,
"litellm_provider": "openrouter",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": false,
"supports_tool_choice": true
},
"openrouter/openai/o3-mini-high": {
"max_tokens": 65536,
"max_input_tokens": 128000,
"max_output_tokens": 65536,
"input_cost_per_token": 0.0000011,
"output_cost_per_token": 0.0000044,
"litellm_provider": "openrouter",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": false,
"supports_tool_choice": true
},
"openrouter/openai/gpt-4o": {
"max_tokens": 4096,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000005,
"output_cost_per_token": 0.000015,
"input_cost_per_token": 0.0000025,
"output_cost_per_token": 0.000010,
"litellm_provider": "openrouter",
"mode": "chat",
"supports_function_calling": true,