scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-10 22:41:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 83

fix: correct wandb model prices (off by ~100,000x)

Browse source 
All 13 wandb model entries (except Kimi-K2-Instruct which was already
correct) had input_cost_per_token and output_cost_per_token values
that were ~100,000x too high. The prices appeared to be in
per-1M-token format rather than per-token format.

For example, Llama-3.3-70B-Instruct was listed at 0.071 per token
instead of 7.1e-07 per token ($0.71 per 1M tokens).

Fixes BerriAI/litellm#23503
This commit is contained in:
Ethan T. 2026-03-13 13:44:25 +08:00
parent 9cd7ad2634
commit 52cde5c0c1
1 changed files with 31 additions and 44 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

75
litellm/model_prices_and_context_window_backup.json
View file

@ -14527,17 +14527,14 @@
"uses_embed_content": true
},
"vertex_ai/gemini-embedding-2-preview": {
"input_cost_per_audio_per_second": 0.00016,
"input_cost_per_image": 0.00012,
"input_cost_per_token": 2e-07,
"input_cost_per_video_per_second": 0.00079,
"input_cost_per_token": 1.5e-07,
"litellm_provider": "vertex_ai",
"max_input_tokens": 8192,
"max_tokens": 8192,
"mode": "embedding",
"output_cost_per_token": 0,
"output_vector_size": 3072,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
"source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal",
"supports_multimodal": true,
"uses_embed_content": true
},
@ -14554,18 +14551,6 @@
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
"uses_embed_content": true
},
"vertex_ai/gemini-embedding-2-preview": {
"input_cost_per_token": 1.5e-07,
"litellm_provider": "vertex_ai",
"max_input_tokens": 8192,
"max_tokens": 8192,
"mode": "embedding",
"output_cost_per_token": 0,
"output_vector_size": 3072,
"source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal",
"supports_multimodal": true,
"uses_embed_content": true
},
"gemini/gemini-embedding-001": {
"input_cost_per_token": 1.5e-07,
"litellm_provider": "gemini",
@ -30938,7 +30923,9 @@
"mode": "chat",
"output_cost_per_token": 3.2e-06,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#glm-models",
"supported_regions": ["global"],
"supported_regions": [
"global"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
@ -31438,8 +31425,8 @@
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 0.015,
"output_cost_per_token": 0.06,
"input_cost_per_token": 1.5e-07,
"output_cost_per_token": 6e-07,
"litellm_provider": "wandb",
"mode": "chat"
},
@ -31447,8 +31434,8 @@
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 0.005,
"output_cost_per_token": 0.02,
"input_cost_per_token": 5e-08,
"output_cost_per_token": 2e-07,
"litellm_provider": "wandb",
"mode": "chat"
},
@ -31456,8 +31443,8 @@
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 0.055,
"output_cost_per_token": 0.2,
"input_cost_per_token": 5.5e-07,
"output_cost_per_token": 2e-06,
"litellm_provider": "wandb",
"mode": "chat"
},
@ -31465,8 +31452,8 @@
"max_tokens": 262144,
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"input_cost_per_token": 0.01,
"output_cost_per_token": 0.01,
"input_cost_per_token": 1e-07,
"output_cost_per_token": 1e-07,
"litellm_provider": "wandb",
"mode": "chat"
},
@ -31474,8 +31461,8 @@
"max_tokens": 262144,
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"input_cost_per_token": 0.1,
"output_cost_per_token": 0.15,
"input_cost_per_token": 1e-06,
"output_cost_per_token": 1.5e-06,
"litellm_provider": "wandb",
"mode": "chat"
},
@ -31483,8 +31470,8 @@
"max_tokens": 262144,
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"input_cost_per_token": 0.01,
"output_cost_per_token": 0.01,
"input_cost_per_token": 1e-07,
"output_cost_per_token": 1e-07,
"litellm_provider": "wandb",
"mode": "chat"
},
@ -31501,8 +31488,8 @@
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.022,
"output_cost_per_token": 0.022,
"input_cost_per_token": 2.2e-07,
"output_cost_per_token": 2.2e-07,
"litellm_provider": "wandb",
"mode": "chat"
},
@ -31510,8 +31497,8 @@
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.055,
"output_cost_per_token": 0.165,
"input_cost_per_token": 5.5e-07,
"output_cost_per_token": 1.65e-06,
"litellm_provider": "wandb",
"mode": "chat"
},
@ -31519,8 +31506,8 @@
"max_tokens": 161000,
"max_input_tokens": 161000,
"max_output_tokens": 161000,
"input_cost_per_token": 0.135,
"output_cost_per_token": 0.54,
"input_cost_per_token": 1.35e-06,
"output_cost_per_token": 5.4e-06,
"litellm_provider": "wandb",
"mode": "chat"
},
@ -31528,8 +31515,8 @@
"max_tokens": 161000,
"max_input_tokens": 161000,
"max_output_tokens": 161000,
"input_cost_per_token": 0.114,
"output_cost_per_token": 0.275,
"input_cost_per_token": 1.14e-06,
"output_cost_per_token": 2.75e-06,
"litellm_provider": "wandb",
"mode": "chat"
},
@ -31537,8 +31524,8 @@
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.071,
"output_cost_per_token": 0.071,
"input_cost_per_token": 7.1e-07,
"output_cost_per_token": 7.1e-07,
"litellm_provider": "wandb",
"mode": "chat"
},
@ -31546,8 +31533,8 @@
"max_tokens": 64000,
"max_input_tokens": 64000,
"max_output_tokens": 64000,
"input_cost_per_token": 0.017,
"output_cost_per_token": 0.066,
"input_cost_per_token": 1.7e-07,
"output_cost_per_token": 6.6e-07,
"litellm_provider": "wandb",
"mode": "chat"
},
@ -31555,8 +31542,8 @@
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.008,
"output_cost_per_token": 0.035,
"input_cost_per_token": 8e-08,
"output_cost_per_token": 3.5e-07,
"litellm_provider": "wandb",
"mode": "chat"
},