scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-13 23:11:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 100

fix(pricing): correct four Vertex AI MaaS per-token rates

Browse source 
qwen3-coder-480b, deepseek-v3.1, gpt-oss-120b and qwen3-235b-instruct-2507 carried rates well above what Google charges, so LiteLLM overstated spend for these Vertex MaaS models. Verified per-token rates against Google's docs and independent trackers and corrected both the root map and the bundled backup
This commit is contained in:
devin-ai-integration[bot] 2026-08-05 05:07:46 +00:00 • committed by GitHub
parent bbc6e3feea
commit 138798ea49
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 16 additions and 16 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
litellm/model_prices_and_context_window_backup.json
View file

@ -37752,13 +37752,13 @@
"supports_tool_choice": true
},
"vertex_ai/deepseek-ai/deepseek-v3.1-maas": {
"input_cost_per_token": 1.35e-06,
"input_cost_per_token": 6e-07,
"litellm_provider": "vertex_ai-deepseek_models",
"max_input_tokens": 163840,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 5.4e-06,
"output_cost_per_token": 1.7e-06,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
"supported_regions": [
"us-central1"
@ -38585,13 +38585,13 @@
"supports_vision": true
},
"vertex_ai/openai/gpt-oss-120b-maas": {
"input_cost_per_token": 1.5e-07,
"input_cost_per_token": 9e-08,
"litellm_provider": "vertex_ai-openai_models",
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 6e-07,
"output_cost_per_token": 3.6e-07,
"source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas",
"supports_reasoning": true
},
@ -38673,13 +38673,13 @@
"supports_web_search": true
},
"vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": {
"input_cost_per_token": 2.5e-07,
"input_cost_per_token": 2.2e-07,
"litellm_provider": "vertex_ai-qwen_models",
"max_input_tokens": 262144,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 1e-06,
"output_cost_per_token": 8.8e-07,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
"supported_regions": [
"global",
@ -38689,13 +38689,13 @@
"supports_tool_choice": true
},
"vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas": {
"input_cost_per_token": 1e-06,
"input_cost_per_token": 2.2e-07,
"litellm_provider": "vertex_ai-qwen_models",
"max_input_tokens": 262144,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 4e-06,
"output_cost_per_token": 1.8e-06,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
"supported_regions": [
"global"

16
model_prices_and_context_window.json
View file

@ -37843,13 +37843,13 @@
"supports_tool_choice": true
},
"vertex_ai/deepseek-ai/deepseek-v3.1-maas": {
"input_cost_per_token": 1.35e-06,
"input_cost_per_token": 6e-07,
"litellm_provider": "vertex_ai-deepseek_models",
"max_input_tokens": 163840,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 5.4e-06,
"output_cost_per_token": 1.7e-06,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
"supported_regions": [
"us-central1"
@ -38676,13 +38676,13 @@
"supports_vision": true
},
"vertex_ai/openai/gpt-oss-120b-maas": {
"input_cost_per_token": 1.5e-07,
"input_cost_per_token": 9e-08,
"litellm_provider": "vertex_ai-openai_models",
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 6e-07,
"output_cost_per_token": 3.6e-07,
"source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas",
"supports_reasoning": true
},
@ -38764,13 +38764,13 @@
"supports_web_search": true
},
"vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": {
"input_cost_per_token": 2.5e-07,
"input_cost_per_token": 2.2e-07,
"litellm_provider": "vertex_ai-qwen_models",
"max_input_tokens": 262144,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 1e-06,
"output_cost_per_token": 8.8e-07,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
"supported_regions": [
"global",
@ -38780,13 +38780,13 @@
"supports_tool_choice": true
},
"vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas": {
"input_cost_per_token": 1e-06,
"input_cost_per_token": 2.2e-07,
"litellm_provider": "vertex_ai-qwen_models",
"max_input_tokens": 262144,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 4e-06,
"output_cost_per_token": 1.8e-06,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
"supported_regions": [
"global"