tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-06 20:25:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

build: update local model cost map

Browse Source
This commit is contained in:
Krrish Dholakia
2025-08-09 16:31:41 -07:00
parent 9f6f96d76c
commit 0eedf7c447
1 changed files with 124 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
litellm/model_prices_and_context_window_backup.json
+124
View File
@@ -17098,6 +17098,130 @@
"litellm_provider": "snowflake",
"mode": "chat"
},
"gradient_ai/anthropic-claude-3.7-sonnet": {
"input_cost_per_token": 3e-06,
"output_cost_per_token": 15e-06,
"litellm_provider": "gradient_ai",
"mode": "chat",
"max_tokens": 1024,
"supported_endpoints": ["/v1/chat/completions"],
"supported_modalities": ["text"],
"supports_tool_choice": false
},
"gradient_ai/anthropic-claude-3.5-sonnet": {
"input_cost_per_token": 3e-06,
"output_cost_per_token": 15e-06,
"litellm_provider": "gradient_ai",
"mode": "chat",
"max_tokens": 1024,
"supported_endpoints": ["/v1/chat/completions"],
"supported_modalities": ["text"],
"supports_tool_choice": false
},
"gradient_ai/anthropic-claude-3.5-haiku": {
"input_cost_per_token": 8e-07,
"output_cost_per_token": 4e-06,
"litellm_provider": "gradient_ai",
"mode": "chat",
"max_tokens": 1024,
"supported_endpoints": ["/v1/chat/completions"],
"supported_modalities": ["text"],
"supports_tool_choice": false
},
"gradient_ai/anthropic-claude-3-opus": {
"input_cost_per_token": 15e-06,
"output_cost_per_token": 75e-06,
"litellm_provider": "gradient_ai",
"mode": "chat",
"max_tokens": 1024,
"supported_endpoints": ["/v1/chat/completions"],
"supported_modalities": ["text"],
"supports_tool_choice": false
},
"gradient_ai/deepseek-r1-distill-llama-70b": {
"input_cost_per_token": 99e-08,
"output_cost_per_token": 99e-08,
"litellm_provider": "gradient_ai",
"mode": "chat",
"max_tokens": 8000,
"supported_endpoints": ["/v1/chat/completions"],
"supported_modalities": ["text"],
"supports_tool_choice": false
},
"gradient_ai/llama3.3-70b-instruct": {
"input_cost_per_token": 65e-08,
"output_cost_per_token": 65e-08,
"litellm_provider": "gradient_ai",
"mode": "chat",
"max_tokens": 2048,
"supported_endpoints": ["/v1/chat/completions"],
"supported_modalities": ["text"],
"supports_tool_choice": false
},
"gradient_ai/llama3-8b-instruct": {
"input_cost_per_token": 2e-07,
"output_cost_per_token": 2e-07,
"litellm_provider": "gradient_ai",
"mode": "chat",
"max_tokens": 512,
"supported_endpoints": ["/v1/chat/completions"],
"supported_modalities": ["text"],
"supports_tool_choice": false
},
"gradient_ai/mistral-nemo-instruct-2407": {
"input_cost_per_token": 3e-07,
"output_cost_per_token": 3e-07,
"litellm_provider": "gradient_ai",
"mode": "chat",
"max_tokens": 512,
"supported_endpoints": ["/v1/chat/completions"],
"supported_modalities": ["text"],
"supports_tool_choice": false
},
"gradient_ai/openai-o3": {
"input_cost_per_token": 2e-06,
"output_cost_per_token": 8e-06,
"litellm_provider": "gradient_ai",
"mode": "chat",
"max_tokens": 100000,
"supported_endpoints": ["/v1/chat/completions"],
"supported_modalities": ["text"],
"supports_tool_choice": false
},
"gradient_ai/openai-o3-mini": {
"input_cost_per_token": 11e-07,
"output_cost_per_token": 44e-07,
"litellm_provider": "gradient_ai",
"mode": "chat",
"max_tokens": 100000,
"supported_endpoints": ["/v1/chat/completions"],
"supported_modalities": ["text"],
"supports_tool_choice": false
},
"gradient_ai/openai-gpt-4o": {
"litellm_provider": "gradient_ai",
"mode": "chat",
"max_tokens": 16384,
"supported_endpoints": ["/v1/chat/completions"],
"supported_modalities": ["text"],
"supports_tool_choice": false
},
"gradient_ai/openai-gpt-4o-mini": {
"litellm_provider": "gradient_ai",
"mode": "chat",
"max_tokens": 16384,
"supported_endpoints": ["/v1/chat/completions"],
"supported_modalities": ["text"],
"supports_tool_choice": false
},
"gradient_ai/alibaba-qwen3-32b": {
"litellm_provider": "gradient_ai",
"mode": "chat",
"max_tokens": 2048,
"supported_endpoints": ["/v1/chat/completions"],
"supported_modalities": ["text"],
"supports_tool_choice": false
},
"nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct": {
"input_cost_per_token": 9e-08,
"output_cost_per_token": 2.9e-07,