scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-07 08:26:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 36

fix(pricing): correct Vertex Haiku 4.5 output limit, Bedrock Mantle gpt-oss rates, add Scaleway deprecation dates

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
mateo 2026-09-05 13:29:38 +00:00
parent 3b191384d1
commit bbf51146ca
3 changed files with 40 additions and 28 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

32
litellm/model_prices_and_context_window_backup.json
View file

@ -45421,8 +45421,8 @@
"input_cost_per_token": 1e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 200000,
"max_output_tokens": 8192,
"max_tokens": 8192,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 5e-06,
"regional_endpoint_uplift_multiplier": 1.1,
@ -45446,8 +45446,8 @@
"input_cost_per_token": 1e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 200000,
"max_output_tokens": 8192,
"max_tokens": 8192,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 5e-06,
"regional_endpoint_uplift_multiplier": 1.1,
@ -51727,7 +51727,8 @@
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 8e-07,
"supports_function_calling": true
"supports_function_calling": true,
"deprecation_date": "2026-10-01"
},
"scaleway/openai/gpt-oss-120b": {
"input_cost_per_token": 1.5e-07,
@ -51766,7 +51767,8 @@
"mode": "chat",
"output_cost_per_token": 5e-07,
"supports_function_calling": true,
"supports_vision": true
"supports_vision": true,
"deprecation_date": "2026-08-01"
},
"scaleway/hcompany/holo2-30b-a3b": {
"input_cost_per_token": 3e-07,
@ -51777,7 +51779,8 @@
"mode": "chat",
"output_cost_per_token": 7e-07,
"supports_reasoning": true,
"supports_vision": true
"supports_vision": true,
"deprecation_date": "2026-08-09"
},
"scaleway/mistralai/mistral-medium-3.5-128b": {
"input_cost_per_token": 1.5e-06,
@ -51800,7 +51803,8 @@
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 2e-06,
"supports_function_calling": true
"supports_function_calling": true,
"deprecation_date": "2026-08-01"
},
"scaleway/mistralai/voxtral-small-24b-2507": {
"input_cost_per_audio_token": 1.5e-07,
@ -51811,7 +51815,8 @@
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 3.5e-07,
"supports_audio_input": true
"supports_audio_input": true,
"deprecation_date": "2026-08-01"
},
"scaleway/mistralai/mistral-small-3.2-24b-instruct-2506": {
"input_cost_per_token": 1.5e-07,
@ -51833,7 +51838,8 @@
"mode": "chat",
"output_cost_per_token": 2e-07,
"supports_vision": true,
"supports_function_calling": true
"supports_function_calling": true,
"deprecation_date": "2026-10-01"
},
"scaleway/BAAI/bge-multilingual-gemma2": {
"input_cost_per_token": 1e-07,
@ -54283,7 +54289,7 @@
"supports_tool_choice": true
},
"bedrock_mantle/openai.gpt-oss-20b": {
"input_cost_per_token": 7.5e-08,
"input_cost_per_token": 7e-08,
"output_cost_per_token": 3e-07,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 131072,
@ -54317,8 +54323,8 @@
"supports_tool_choice": true
},
"bedrock_mantle/openai.gpt-oss-safeguard-20b": {
"input_cost_per_token": 7.5e-08,
"output_cost_per_token": 3e-07,
"input_cost_per_token": 7e-08,
"output_cost_per_token": 2e-07,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 131072,
"max_output_tokens": 65536,

32
model_prices_and_context_window.json
View file

@ -45421,8 +45421,8 @@
"input_cost_per_token": 1e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 200000,
"max_output_tokens": 8192,
"max_tokens": 8192,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 5e-06,
"regional_endpoint_uplift_multiplier": 1.1,
@ -45446,8 +45446,8 @@
"input_cost_per_token": 1e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 200000,
"max_output_tokens": 8192,
"max_tokens": 8192,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 5e-06,
"regional_endpoint_uplift_multiplier": 1.1,
@ -51727,7 +51727,8 @@
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 8e-07,
"supports_function_calling": true
"supports_function_calling": true,
"deprecation_date": "2026-10-01"
},
"scaleway/openai/gpt-oss-120b": {
"input_cost_per_token": 1.5e-07,
@ -51766,7 +51767,8 @@
"mode": "chat",
"output_cost_per_token": 5e-07,
"supports_function_calling": true,
"supports_vision": true
"supports_vision": true,
"deprecation_date": "2026-08-01"
},
"scaleway/hcompany/holo2-30b-a3b": {
"input_cost_per_token": 3e-07,
@ -51777,7 +51779,8 @@
"mode": "chat",
"output_cost_per_token": 7e-07,
"supports_reasoning": true,
"supports_vision": true
"supports_vision": true,
"deprecation_date": "2026-08-09"
},
"scaleway/mistralai/mistral-medium-3.5-128b": {
"input_cost_per_token": 1.5e-06,
@ -51800,7 +51803,8 @@
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 2e-06,
"supports_function_calling": true
"supports_function_calling": true,
"deprecation_date": "2026-08-01"
},
"scaleway/mistralai/voxtral-small-24b-2507": {
"input_cost_per_audio_token": 1.5e-07,
@ -51811,7 +51815,8 @@
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 3.5e-07,
"supports_audio_input": true
"supports_audio_input": true,
"deprecation_date": "2026-08-01"
},
"scaleway/mistralai/mistral-small-3.2-24b-instruct-2506": {
"input_cost_per_token": 1.5e-07,
@ -51833,7 +51838,8 @@
"mode": "chat",
"output_cost_per_token": 2e-07,
"supports_vision": true,
"supports_function_calling": true
"supports_function_calling": true,
"deprecation_date": "2026-10-01"
},
"scaleway/BAAI/bge-multilingual-gemma2": {
"input_cost_per_token": 1e-07,
@ -54283,7 +54289,7 @@
"supports_tool_choice": true
},
"bedrock_mantle/openai.gpt-oss-20b": {
"input_cost_per_token": 7.5e-08,
"input_cost_per_token": 7e-08,
"output_cost_per_token": 3e-07,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 131072,
@ -54317,8 +54323,8 @@
"supports_tool_choice": true
},
"bedrock_mantle/openai.gpt-oss-safeguard-20b": {
"input_cost_per_token": 7.5e-08,
"output_cost_per_token": 3e-07,
"input_cost_per_token": 7e-08,
"output_cost_per_token": 2e-07,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 131072,
"max_output_tokens": 65536,

4
tests/test_litellm/llms/bedrock_mantle/test_bedrock_mantle_transformation.py
View file

@ -696,8 +696,8 @@ class TestBedrockMantlePricing:
monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "true")
litellm.add_known_models()
info = litellm.get_model_info("bedrock_mantle/openai.gpt-oss-20b")
# Bedrock pricing: $0.075/M input, $0.30/M output
assert info["input_cost_per_token"] == pytest.approx(7.5e-8)
# Bedrock pricing: $0.07/M input, $0.30/M output
assert info["input_cost_per_token"] == pytest.approx(7e-8)
assert info["output_cost_per_token"] == pytest.approx(3e-7)
def test_pricing_significantly_cheaper_than_openai_native(self, monkeypatch):