scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-11 08:38:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 280

fix(wandb): correct inference model pricing

Browse source
This commit is contained in:
arcticfly 2026-08-14 03:01:56 -07:00
parent 423b791ee0
commit 16c151f1ed
3 changed files with 712 additions and 220 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

437
litellm/model_prices_and_context_window_backup.json
View file

@ -40136,159 +40136,376 @@
"mode": "embedding",
"output_cost_per_token": 0.0
},
"wandb/openai/gpt-oss-120b": {
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 0.015,
"output_cost_per_token": 0.06,
"wandb/deepseek-ai/DeepSeek-R1-0528": {
"input_cost_per_token": 1.35e-06,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 161000,
"max_output_tokens": 161000,
"max_tokens": 161000,
"mode": "chat",
"output_cost_per_token": 5.4e-06
},
"wandb/openai/gpt-oss-20b": {
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 0.005,
"output_cost_per_token": 0.02,
"wandb/deepseek-ai/DeepSeek-V3-0324": {
"input_cost_per_token": 1.14e-06,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 161000,
"max_output_tokens": 161000,
"max_tokens": 161000,
"mode": "chat",
"output_cost_per_token": 2.75e-06
},
"wandb/zai-org/GLM-4.5": {
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 0.055,
"output_cost_per_token": 0.2,
"wandb/deepseek-ai/DeepSeek-V3.1": {
"input_cost_per_token": 5.5e-07,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 161000,
"max_output_tokens": 161000,
"max_tokens": 161000,
"mode": "chat",
"output_cost_per_token": 1.65e-06,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/Qwen/Qwen3-235B-A22B-Instruct-2507": {
"max_tokens": 262144,
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"input_cost_per_token": 0.01,
"output_cost_per_token": 0.01,
"wandb/deepseek-ai/DeepSeek-V4-Flash": {
"cache_read_input_token_cost": 7e-08,
"input_cost_per_token": 1.4e-07,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 1049000,
"max_output_tokens": 1049000,
"max_tokens": 1049000,
"mode": "chat",
"output_cost_per_token": 2.8e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct": {
"max_tokens": 262144,
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"input_cost_per_token": 0.1,
"output_cost_per_token": 0.15,
"wandb/deepseek-ai/DeepSeek-V4-Flash-0731": {
"cache_read_input_token_cost": 7e-08,
"input_cost_per_token": 1.3e-07,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 2.8e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/Qwen/Qwen3-235B-A22B-Thinking-2507": {
"max_tokens": 262144,
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"input_cost_per_token": 0.01,
"output_cost_per_token": 0.01,
"wandb/deepseek-ai/DeepSeek-V4-Pro": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 1.15e-06,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 1049000,
"max_output_tokens": 1049000,
"max_tokens": 1049000,
"mode": "chat",
"output_cost_per_token": 2.55e-06,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/moonshotai/Kimi-K2-Instruct": {
"max_tokens": 128000,
"wandb/google/gemma-4-31B-it": {
"input_cost_per_token": 1e-07,
"litellm_provider": "wandb",
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 3.4e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/ibm-granite/granite-4.1-8b": {
"input_cost_per_token": 5e-08,
"litellm_provider": "wandb",
"max_input_tokens": 131000,
"max_output_tokens": 131000,
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 1e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/JetBrains/Mellum2-12B-A2.5B-Instruct": {
"input_cost_per_token": 5e-08,
"litellm_provider": "wandb",
"max_input_tokens": 131000,
"max_output_tokens": 131000,
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 1e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/meta-llama/Llama-3.1-70B-Instruct": {
"input_cost_per_token": 8e-07,
"litellm_provider": "wandb",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 6e-07,
"output_cost_per_token": 2.5e-06,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 8e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/meta-llama/Llama-3.1-8B-Instruct": {
"input_cost_per_token": 2.2e-07,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2.2e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/meta-llama/Llama-3.3-70B-Instruct": {
"input_cost_per_token": 7.1e-07,
"litellm_provider": "wandb",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 7.1e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct": {
"input_cost_per_token": 1.7e-07,
"litellm_provider": "wandb",
"max_input_tokens": 64000,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 6.6e-07
},
"wandb/MiniMaxAI/MiniMax-M2.5": {
"input_cost_per_token": 3e-07,
"litellm_provider": "wandb",
"max_input_tokens": 197000,
"max_output_tokens": 197000,
"max_tokens": 197000,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"source": "https://wandb.ai/site/pricing/tokens/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true
},
"wandb/MiniMaxAI/MiniMax-M3": {
"cache_read_input_token_cost": 5e-08,
"input_cost_per_token": 2.3e-07,
"litellm_provider": "wandb",
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 9.6e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/microsoft/Phi-4-mini-instruct": {
"input_cost_per_token": 8e-08,
"litellm_provider": "wandb",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3.5e-07
},
"wandb/moonshotai/Kimi-K2-Instruct": {
"input_cost_per_token": 6e-07,
"litellm_provider": "wandb",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2.5e-06
},
"wandb/moonshotai/Kimi-K2.5": {
"max_tokens": 262144,
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"cache_read_input_token_cost": 1e-07,
"input_cost_per_token": 6e-07,
"output_cost_per_token": 3e-06,
"litellm_provider": "wandb",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 3e-06,
"source": "https://wandb.ai/inference/coreweave/cw_moonshotai_Kimi-K2.5",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_vision": true
},
"wandb/MiniMaxAI/MiniMax-M2.5": {
"max_tokens": 197000,
"max_input_tokens": 197000,
"max_output_tokens": 197000,
"input_cost_per_token": 3e-07,
"output_cost_per_token": 1.2e-06,
"wandb/moonshotai/Kimi-K2.6": {
"cache_read_input_token_cost": 1.5e-07,
"input_cost_per_token": 6.5e-07,
"litellm_provider": "wandb",
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"source": "https://wandb.ai/inference/coreweave/cw_MiniMaxAI_MiniMax-M2.5",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true
"output_cost_per_token": 3.41e-06,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/meta-llama/Llama-3.1-8B-Instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.022,
"output_cost_per_token": 0.022,
"wandb/moonshotai/Kimi-K2.7-Code": {
"cache_read_input_token_cost": 1.5e-07,
"input_cost_per_token": 7.1e-07,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 3.5e-06,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/deepseek-ai/DeepSeek-V3.1": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.055,
"output_cost_per_token": 0.165,
"wandb/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8": {
"input_cost_per_token": 2e-07,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 8e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/deepseek-ai/DeepSeek-R1-0528": {
"max_tokens": 161000,
"max_input_tokens": 161000,
"max_output_tokens": 161000,
"input_cost_per_token": 0.135,
"output_cost_per_token": 0.54,
"wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": {
"cache_read_input_token_cost": 1.5e-07,
"input_cost_per_token": 7.5e-07,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 2.75e-06,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/deepseek-ai/DeepSeek-V3-0324": {
"max_tokens": 161000,
"max_input_tokens": 161000,
"max_output_tokens": 161000,
"input_cost_per_token": 0.114,
"output_cost_per_token": 0.275,
"wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B": {
"cache_read_input_token_cost": 5e-08,
"input_cost_per_token": 1e-07,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 2.5e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/meta-llama/Llama-3.3-70B-Instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.071,
"output_cost_per_token": 0.071,
"wandb/openai/gpt-oss-120b": {
"input_cost_per_token": 3e-08,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 131000,
"max_output_tokens": 131000,
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 1.7e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct": {
"max_tokens": 64000,
"max_input_tokens": 64000,
"max_output_tokens": 64000,
"input_cost_per_token": 0.017,
"output_cost_per_token": 0.066,
"wandb/openai/gpt-oss-20b": {
"input_cost_per_token": 3e-08,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 131000,
"max_output_tokens": 131000,
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 1.3e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/microsoft/Phi-4-mini-instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.008,
"output_cost_per_token": 0.035,
"wandb/OpenPipe/Qwen3-14B-Instruct": {
"input_cost_per_token": 5e-08,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 32800,
"max_output_tokens": 32800,
"max_tokens": 32800,
"mode": "chat",
"output_cost_per_token": 2.2e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/Qwen/Qwen3-235B-A22B-Instruct-2507": {
"input_cost_per_token": 1e-07,
"litellm_provider": "wandb",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 1e-07
},
"wandb/Qwen/Qwen3-235B-A22B-Thinking-2507": {
"input_cost_per_token": 1e-07,
"litellm_provider": "wandb",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 1e-07
},
"wandb/Qwen/Qwen3-30B-A3B-Instruct-2507": {
"input_cost_per_token": 1e-07,
"litellm_provider": "wandb",
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 3e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct": {
"input_cost_per_token": 1e-06,
"litellm_provider": "wandb",
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 1.5e-06,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/Qwen/Qwen3.5-35B-A3B": {
"input_cost_per_token": 2.5e-07,
"litellm_provider": "wandb",
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 1.25e-06,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/Qwen/Qwen3.6-27B": {
"cache_read_input_token_cost": 1.2e-07,
"input_cost_per_token": 6e-07,
"litellm_provider": "wandb",
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 3.6e-06,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/Qwen/Qwen3.6-35B-A3B": {
"input_cost_per_token": 2.5e-07,
"litellm_provider": "wandb",
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 1.25e-06,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/zai-org/GLM-4.5": {
"input_cost_per_token": 5.5e-07,
"litellm_provider": "wandb",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 2e-06
},
"wandb/zai-org/GLM-5.1": {
"cache_read_input_token_cost": 2.6e-07,
"input_cost_per_token": 1.4e-06,
"litellm_provider": "wandb",
"max_input_tokens": 203000,
"max_output_tokens": 203000,
"max_tokens": 203000,
"mode": "chat",
"output_cost_per_token": 4.4e-06,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/zai-org/GLM-5.2": {
"cache_read_input_token_cost": 1.4e-07,
"input_cost_per_token": 7.6e-07,
"litellm_provider": "wandb",
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 2.42e-06,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"watsonx/ibm/granite-3-8b-instruct": {
"input_cost_per_token": 2e-07,

437
model_prices_and_context_window.json
View file

@ -40136,159 +40136,376 @@
"mode": "embedding",
"output_cost_per_token": 0.0
},
"wandb/openai/gpt-oss-120b": {
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 0.015,
"output_cost_per_token": 0.06,
"wandb/deepseek-ai/DeepSeek-R1-0528": {
"input_cost_per_token": 1.35e-06,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 161000,
"max_output_tokens": 161000,
"max_tokens": 161000,
"mode": "chat",
"output_cost_per_token": 5.4e-06
},
"wandb/openai/gpt-oss-20b": {
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 0.005,
"output_cost_per_token": 0.02,
"wandb/deepseek-ai/DeepSeek-V3-0324": {
"input_cost_per_token": 1.14e-06,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 161000,
"max_output_tokens": 161000,
"max_tokens": 161000,
"mode": "chat",
"output_cost_per_token": 2.75e-06
},
"wandb/zai-org/GLM-4.5": {
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 0.055,
"output_cost_per_token": 0.2,
"wandb/deepseek-ai/DeepSeek-V3.1": {
"input_cost_per_token": 5.5e-07,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 161000,
"max_output_tokens": 161000,
"max_tokens": 161000,
"mode": "chat",
"output_cost_per_token": 1.65e-06,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/Qwen/Qwen3-235B-A22B-Instruct-2507": {
"max_tokens": 262144,
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"input_cost_per_token": 0.01,
"output_cost_per_token": 0.01,
"wandb/deepseek-ai/DeepSeek-V4-Flash": {
"cache_read_input_token_cost": 7e-08,
"input_cost_per_token": 1.4e-07,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 1049000,
"max_output_tokens": 1049000,
"max_tokens": 1049000,
"mode": "chat",
"output_cost_per_token": 2.8e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct": {
"max_tokens": 262144,
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"input_cost_per_token": 0.1,
"output_cost_per_token": 0.15,
"wandb/deepseek-ai/DeepSeek-V4-Flash-0731": {
"cache_read_input_token_cost": 7e-08,
"input_cost_per_token": 1.3e-07,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 2.8e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/Qwen/Qwen3-235B-A22B-Thinking-2507": {
"max_tokens": 262144,
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"input_cost_per_token": 0.01,
"output_cost_per_token": 0.01,
"wandb/deepseek-ai/DeepSeek-V4-Pro": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 1.15e-06,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 1049000,
"max_output_tokens": 1049000,
"max_tokens": 1049000,
"mode": "chat",
"output_cost_per_token": 2.55e-06,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/moonshotai/Kimi-K2-Instruct": {
"max_tokens": 128000,
"wandb/google/gemma-4-31B-it": {
"input_cost_per_token": 1e-07,
"litellm_provider": "wandb",
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 3.4e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/ibm-granite/granite-4.1-8b": {
"input_cost_per_token": 5e-08,
"litellm_provider": "wandb",
"max_input_tokens": 131000,
"max_output_tokens": 131000,
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 1e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/JetBrains/Mellum2-12B-A2.5B-Instruct": {
"input_cost_per_token": 5e-08,
"litellm_provider": "wandb",
"max_input_tokens": 131000,
"max_output_tokens": 131000,
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 1e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/meta-llama/Llama-3.1-70B-Instruct": {
"input_cost_per_token": 8e-07,
"litellm_provider": "wandb",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 6e-07,
"output_cost_per_token": 2.5e-06,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 8e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/meta-llama/Llama-3.1-8B-Instruct": {
"input_cost_per_token": 2.2e-07,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2.2e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/meta-llama/Llama-3.3-70B-Instruct": {
"input_cost_per_token": 7.1e-07,
"litellm_provider": "wandb",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 7.1e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct": {
"input_cost_per_token": 1.7e-07,
"litellm_provider": "wandb",
"max_input_tokens": 64000,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 6.6e-07
},
"wandb/MiniMaxAI/MiniMax-M2.5": {
"input_cost_per_token": 3e-07,
"litellm_provider": "wandb",
"max_input_tokens": 197000,
"max_output_tokens": 197000,
"max_tokens": 197000,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"source": "https://wandb.ai/site/pricing/tokens/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true
},
"wandb/MiniMaxAI/MiniMax-M3": {
"cache_read_input_token_cost": 5e-08,
"input_cost_per_token": 2.3e-07,
"litellm_provider": "wandb",
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 9.6e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/microsoft/Phi-4-mini-instruct": {
"input_cost_per_token": 8e-08,
"litellm_provider": "wandb",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3.5e-07
},
"wandb/moonshotai/Kimi-K2-Instruct": {
"input_cost_per_token": 6e-07,
"litellm_provider": "wandb",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2.5e-06
},
"wandb/moonshotai/Kimi-K2.5": {
"max_tokens": 262144,
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"cache_read_input_token_cost": 1e-07,
"input_cost_per_token": 6e-07,
"output_cost_per_token": 3e-06,
"litellm_provider": "wandb",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 3e-06,
"source": "https://wandb.ai/inference/coreweave/cw_moonshotai_Kimi-K2.5",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_vision": true
},
"wandb/MiniMaxAI/MiniMax-M2.5": {
"max_tokens": 197000,
"max_input_tokens": 197000,
"max_output_tokens": 197000,
"input_cost_per_token": 3e-07,
"output_cost_per_token": 1.2e-06,
"wandb/moonshotai/Kimi-K2.6": {
"cache_read_input_token_cost": 1.5e-07,
"input_cost_per_token": 6.5e-07,
"litellm_provider": "wandb",
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"source": "https://wandb.ai/inference/coreweave/cw_MiniMaxAI_MiniMax-M2.5",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true
"output_cost_per_token": 3.41e-06,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/meta-llama/Llama-3.1-8B-Instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.022,
"output_cost_per_token": 0.022,
"wandb/moonshotai/Kimi-K2.7-Code": {
"cache_read_input_token_cost": 1.5e-07,
"input_cost_per_token": 7.1e-07,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 3.5e-06,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/deepseek-ai/DeepSeek-V3.1": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.055,
"output_cost_per_token": 0.165,
"wandb/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8": {
"input_cost_per_token": 2e-07,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 8e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/deepseek-ai/DeepSeek-R1-0528": {
"max_tokens": 161000,
"max_input_tokens": 161000,
"max_output_tokens": 161000,
"input_cost_per_token": 0.135,
"output_cost_per_token": 0.54,
"wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": {
"cache_read_input_token_cost": 1.5e-07,
"input_cost_per_token": 7.5e-07,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 2.75e-06,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/deepseek-ai/DeepSeek-V3-0324": {
"max_tokens": 161000,
"max_input_tokens": 161000,
"max_output_tokens": 161000,
"input_cost_per_token": 0.114,
"output_cost_per_token": 0.275,
"wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B": {
"cache_read_input_token_cost": 5e-08,
"input_cost_per_token": 1e-07,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 2.5e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/meta-llama/Llama-3.3-70B-Instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.071,
"output_cost_per_token": 0.071,
"wandb/openai/gpt-oss-120b": {
"input_cost_per_token": 3e-08,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 131000,
"max_output_tokens": 131000,
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 1.7e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct": {
"max_tokens": 64000,
"max_input_tokens": 64000,
"max_output_tokens": 64000,
"input_cost_per_token": 0.017,
"output_cost_per_token": 0.066,
"wandb/openai/gpt-oss-20b": {
"input_cost_per_token": 3e-08,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 131000,
"max_output_tokens": 131000,
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 1.3e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/microsoft/Phi-4-mini-instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.008,
"output_cost_per_token": 0.035,
"wandb/OpenPipe/Qwen3-14B-Instruct": {
"input_cost_per_token": 5e-08,
"litellm_provider": "wandb",
"mode": "chat"
"max_input_tokens": 32800,
"max_output_tokens": 32800,
"max_tokens": 32800,
"mode": "chat",
"output_cost_per_token": 2.2e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/Qwen/Qwen3-235B-A22B-Instruct-2507": {
"input_cost_per_token": 1e-07,
"litellm_provider": "wandb",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 1e-07
},
"wandb/Qwen/Qwen3-235B-A22B-Thinking-2507": {
"input_cost_per_token": 1e-07,
"litellm_provider": "wandb",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 1e-07
},
"wandb/Qwen/Qwen3-30B-A3B-Instruct-2507": {
"input_cost_per_token": 1e-07,
"litellm_provider": "wandb",
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 3e-07,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct": {
"input_cost_per_token": 1e-06,
"litellm_provider": "wandb",
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 1.5e-06,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/Qwen/Qwen3.5-35B-A3B": {
"input_cost_per_token": 2.5e-07,
"litellm_provider": "wandb",
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 1.25e-06,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/Qwen/Qwen3.6-27B": {
"cache_read_input_token_cost": 1.2e-07,
"input_cost_per_token": 6e-07,
"litellm_provider": "wandb",
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 3.6e-06,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/Qwen/Qwen3.6-35B-A3B": {
"input_cost_per_token": 2.5e-07,
"litellm_provider": "wandb",
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 1.25e-06,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/zai-org/GLM-4.5": {
"input_cost_per_token": 5.5e-07,
"litellm_provider": "wandb",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 2e-06
},
"wandb/zai-org/GLM-5.1": {
"cache_read_input_token_cost": 2.6e-07,
"input_cost_per_token": 1.4e-06,
"litellm_provider": "wandb",
"max_input_tokens": 203000,
"max_output_tokens": 203000,
"max_tokens": 203000,
"mode": "chat",
"output_cost_per_token": 4.4e-06,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"wandb/zai-org/GLM-5.2": {
"cache_read_input_token_cost": 1.4e-07,
"input_cost_per_token": 7.6e-07,
"litellm_provider": "wandb",
"max_input_tokens": 262000,
"max_output_tokens": 262000,
"max_tokens": 262000,
"mode": "chat",
"output_cost_per_token": 2.42e-06,
"source": "https://wandb.ai/site/pricing/tokens/"
},
"watsonx/ibm/granite-3-8b-instruct": {
"input_cost_per_token": 2e-07,

58
tests/test_litellm/test_wandb_model_metadata.py Normal file
View file

@ -0,0 +1,58 @@
import json
from pathlib import Path
from types import MappingProxyType
from typing import Final
import pytest
REPO_ROOT: Final = Path(__file__).parents[2]
PRICE_FILES: Final = (
REPO_ROOT / "model_prices_and_context_window.json",
REPO_ROOT / "litellm" / "model_prices_and_context_window_backup.json",
)
SOURCE: Final = "https://wandb.ai/site/pricing/tokens/"
CURRENT_PRICES_PER_MILLION_TOKENS: Final = MappingProxyType(
{
"wandb/deepseek-ai/DeepSeek-V3.1": (0.55, 1.65, None),
"wandb/deepseek-ai/DeepSeek-V4-Flash": (0.14, 0.28, 0.07),
"wandb/deepseek-ai/DeepSeek-V4-Flash-0731": (0.13, 0.28, 0.07),
"wandb/deepseek-ai/DeepSeek-V4-Pro": (1.15, 2.55, 0.20),
"wandb/google/gemma-4-31B-it": (0.10, 0.34, None),
"wandb/ibm-granite/granite-4.1-8b": (0.05, 0.10, None),
"wandb/JetBrains/Mellum2-12B-A2.5B-Instruct": (0.05, 0.10, None),
"wandb/meta-llama/Llama-3.1-70B-Instruct": (0.80, 0.80, None),
"wandb/meta-llama/Llama-3.1-8B-Instruct": (0.22, 0.22, None),
"wandb/meta-llama/Llama-3.3-70B-Instruct": (0.71, 0.71, None),
"wandb/MiniMaxAI/MiniMax-M2.5": (0.30, 1.20, None),
"wandb/MiniMaxAI/MiniMax-M3": (0.23, 0.96, 0.05),
"wandb/moonshotai/Kimi-K2.6": (0.65, 3.41, 0.15),
"wandb/moonshotai/Kimi-K2.7-Code": (0.71, 3.50, 0.15),
"wandb/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8": (0.20, 0.80, None),
"wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": (0.75, 2.75, 0.15),
"wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B": (0.10, 0.25, 0.05),
"wandb/openai/gpt-oss-120b": (0.03, 0.17, None),
"wandb/openai/gpt-oss-20b": (0.03, 0.13, None),
"wandb/OpenPipe/Qwen3-14B-Instruct": (0.05, 0.22, None),
"wandb/Qwen/Qwen3-30B-A3B-Instruct-2507": (0.10, 0.30, None),
"wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct": (1.00, 1.50, None),
"wandb/Qwen/Qwen3.5-35B-A3B": (0.25, 1.25, None),
"wandb/Qwen/Qwen3.6-27B": (0.60, 3.60, 0.12),
"wandb/Qwen/Qwen3.6-35B-A3B": (0.25, 1.25, None),
"wandb/zai-org/GLM-5.1": (1.40, 4.40, 0.26),
"wandb/zai-org/GLM-5.2": (0.76, 2.42, 0.14),
}
)
@pytest.mark.parametrize("price_file", PRICE_FILES)
def test_current_wandb_pricing(price_file: Path) -> None:
prices: Final = json.loads(price_file.read_text())
for model, (input_price, output_price, cache_price) in CURRENT_PRICES_PER_MILLION_TOKENS.items():
metadata: Final = prices[model]
assert metadata["input_cost_per_token"] == pytest.approx(input_price / 1_000_000)
assert metadata["output_cost_per_token"] == pytest.approx(output_price / 1_000_000)
assert metadata.get("cache_read_input_token_cost") == (
pytest.approx(cache_price / 1_000_000) if cache_price is not None else None
)
assert metadata["source"] == SOURCE