Skip to content

Prices fix #15129

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
+26 −26
Open

Prices fix #15129

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cf7aedf
Azure gpt-5 price update.
okutrup Oct 2, 2025
abde54b
Some outdated Azure, Gemini, Bedrock prices updated.
okutrup Oct 2, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
52 changes: 26 additions & 26 deletions model_prices_and_context_window.json
View file
Open in desktop
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can you cite the sources? @oytunkutrup1

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/
https://ai.google.dev/gemini-api/docs/pricing
https://aws.amazon.com/bedrock/pricing/
These are the sources I used as references.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@krrishdholakia Are these sources okay?

Original file line number Diff line number Diff line change
Expand Up @@ -1205,13 +1205,13 @@
},
"azure/gpt-3.5-turbo-0125": {
"deprecation_date": "2025-03-31",
"input_cost_per_token": 5e-07,
"input_cost_per_token": 5.5e-07,
"litellm_provider": "azure",
"max_input_tokens": 16384,
"max_output_tokens": 4096,
"max_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 1.5e-06,
"output_cost_per_token": 1.65e-06,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_tool_choice": true
Expand Down Expand Up @@ -1391,25 +1391,25 @@
"supports_tool_choice": true
},
"azure/gpt-4-turbo": {
"input_cost_per_token": 1e-05,
"input_cost_per_token": 1.1e-05,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"max_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 3e-05,
"output_cost_per_token": 3.3e-05,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_tool_choice": true
},
"azure/gpt-4-turbo-2024-04-09": {
"input_cost_per_token": 1e-05,
"input_cost_per_token": 1.1e-05,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"max_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 3e-05,
"output_cost_per_token": 3.3e-05,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_tool_choice": true,
Expand Down Expand Up @@ -1559,7 +1559,7 @@
"supports_web_search": false
},
"azure/gpt-4.1-nano": {
"cache_read_input_token_cost": 2.5e-08,
"cache_read_input_token_cost": 3e-08,
"input_cost_per_token": 1e-07,
"input_cost_per_token_batches": 5e-08,
"litellm_provider": "azure",
Expand Down Expand Up @@ -1591,7 +1591,7 @@
"supports_vision": true
},
"azure/gpt-4.1-nano-2025-04-14": {
"cache_read_input_token_cost": 2.5e-08,
"cache_read_input_token_cost": 3e-08,
"input_cost_per_token": 1e-07,
"input_cost_per_token_batches": 5e-08,
"litellm_provider": "azure",
Expand Down Expand Up @@ -1904,7 +1904,7 @@
]
},
"azure/gpt-5": {
"cache_read_input_token_cost": 1.25e-07,
"cache_read_input_token_cost": 1.3e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
Expand Down Expand Up @@ -1936,7 +1936,7 @@
"supports_vision": true
},
"azure/gpt-5-2025-08-07": {
"cache_read_input_token_cost": 1.25e-07,
"cache_read_input_token_cost": 1.3e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
Expand Down Expand Up @@ -2001,7 +2001,7 @@
"supports_vision": true
},
"azure/gpt-5-chat-latest": {
"cache_read_input_token_cost": 1.25e-07,
"cache_read_input_token_cost": 1.3e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
Expand Down Expand Up @@ -2033,7 +2033,7 @@
"supports_vision": true
},
"azure/gpt-5-mini": {
"cache_read_input_token_cost": 2.5e-08,
"cache_read_input_token_cost": 3e-08,
"input_cost_per_token": 2.5e-07,
"litellm_provider": "azure",
"max_input_tokens": 272000,
Expand Down Expand Up @@ -2065,7 +2065,7 @@
"supports_vision": true
},
"azure/gpt-5-mini-2025-08-07": {
"cache_read_input_token_cost": 2.5e-08,
"cache_read_input_token_cost": 3e-08,
"input_cost_per_token": 2.5e-07,
"litellm_provider": "azure",
"max_input_tokens": 272000,
Expand Down Expand Up @@ -2097,7 +2097,7 @@
"supports_vision": true
},
"azure/gpt-5-nano": {
"cache_read_input_token_cost": 5e-09,
"cache_read_input_token_cost": 1e-08,
"input_cost_per_token": 5e-08,
"litellm_provider": "azure",
"max_input_tokens": 272000,
Expand Down Expand Up @@ -2129,7 +2129,7 @@
"supports_vision": true
},
"azure/gpt-5-nano-2025-08-07": {
"cache_read_input_token_cost": 5e-09,
"cache_read_input_token_cost": 1e-08,
"input_cost_per_token": 5e-08,
"litellm_provider": "azure",
"max_input_tokens": 272000,
Expand Down Expand Up @@ -2559,7 +2559,7 @@
"supports_vision": true
},
"azure/o4-mini": {
"cache_read_input_token_cost": 2.75e-07,
"cache_read_input_token_cost": 2.8e-07,
"input_cost_per_token": 1.1e-06,
"litellm_provider": "azure",
"max_input_tokens": 200000,
Expand Down Expand Up @@ -2588,7 +2588,7 @@
"supports_vision": true
},
"azure/o4-mini-2025-04-16": {
"cache_read_input_token_cost": 2.75e-07,
"cache_read_input_token_cost": 2.8e-07,
"input_cost_per_token": 1.1e-06,
"litellm_provider": "azure",
"max_input_tokens": 200000,
Expand Down Expand Up @@ -14002,13 +14002,13 @@
"supports_tool_choice": false
},
"meta.llama3-1-70b-instruct-v1:0": {
"input_cost_per_token": 9.9e-07,
"input_cost_per_token": 7.2e-07,
"litellm_provider": "bedrock",
"max_input_tokens": 128000,
"max_output_tokens": 2048,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 9.9e-07,
"output_cost_per_token": 7.2e-07,
"supports_function_calling": true,
"supports_tool_choice": false
},
Expand All @@ -14024,13 +14024,13 @@
"supports_tool_choice": false
},
"meta.llama3-2-11b-instruct-v1:0": {
"input_cost_per_token": 3.5e-07,
"input_cost_per_token": 1.6e-07,
"litellm_provider": "bedrock",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3.5e-07,
"output_cost_per_token": 1.6e-07,
"supports_function_calling": true,
"supports_tool_choice": false,
"supports_vision": true
Expand Down Expand Up @@ -14058,13 +14058,13 @@
"supports_tool_choice": false
},
"meta.llama3-2-90b-instruct-v1:0": {
"input_cost_per_token": 2e-06,
"input_cost_per_token": 7.2e-07,
"litellm_provider": "bedrock",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2e-06,
"output_cost_per_token": 7.2e-07,
"supports_function_calling": true,
"supports_tool_choice": false,
"supports_vision": true
Expand Down Expand Up @@ -14217,13 +14217,13 @@
"supports_tool_choice": true
},
"mistral.mistral-large-2402-v1:0": {
"input_cost_per_token": 8e-06,
"input_cost_per_token": 4e-06,
"litellm_provider": "bedrock",
"max_input_tokens": 32000,
"max_output_tokens": 8191,
"max_tokens": 8191,
"mode": "chat",
"output_cost_per_token": 2.4e-05,
"output_cost_per_token": 1.2e-05,
"supports_function_calling": true
},
"mistral.mistral-large-2407-v1:0": {
Expand Down Expand Up @@ -18292,7 +18292,7 @@
},
"text-embedding-004": {
"input_cost_per_character": 2.5e-08,
"input_cost_per_token": 1e-07,
"input_cost_per_token": 1.5e-07,
"litellm_provider": "vertex_ai-embedding-models",
"max_input_tokens": 2048,
"max_tokens": 2048,
Expand Down
Loading