Skip to content

Add Azure AI Foundry DeepSeek V3.1 and V4 Pro/Flash global pricing to cost map #30134

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

Merged
Sameerlite merged 1 commit into from
Jun 11, 2026
Merged

Add Azure AI Foundry DeepSeek V3.1 and V4 Pro/Flash global pricing to cost map #30134

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
39 changes: 39 additions & 0 deletions litellm/model_prices_and_context_window_backup.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7557,6 +7557,45 @@
"supports_function_calling": true,
"supports_tool_choice": true
},
"azure_ai/deepseek-v3.1": {
"input_cost_per_token": 1.23e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 4.94e-06,
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"azure_ai/deepseek-v4-pro": {
"input_cost_per_token": 1.74e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 3.48e-06,
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"azure_ai/deepseek-v4-flash": {
"input_cost_per_token": 1.9e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
"max_output_tokens": 384000,
"max_tokens": 384000,
Comment on lines +7573 to +7591

@greptile-apps greptile-apps Bot Jun 10, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

P1 Same max_output_tokens/max_tokens discrepancy in the backup copy — both V4 Pro and V4 Flash show 384,000 but the Azure catalog specifies 128k (131,072) output tokens for each model.

Suggested change
"azure_ai/deepseek-v4-pro": {
"input_cost_per_token": 1.74e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 3.48e-06,
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"azure_ai/deepseek-v4-flash": {
"input_cost_per_token": 1.9e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
"max_output_tokens": 384000,
"max_tokens": 384000,
"azure_ai/deepseek-v4-pro": {
"input_cost_per_token": 1.74e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 3.48e-06,
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"azure_ai/deepseek-v4-flash": {
"input_cost_per_token": 1.9e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
"max_output_tokens": 131072,
"max_tokens": 131072,

"mode": "chat",
"output_cost_per_token": 5.1e-07,
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"azure_ai/embed-v-4-0": {
"input_cost_per_token": 1.2e-07,
"litellm_provider": "azure_ai",
Expand Down
39 changes: 39 additions & 0 deletions model_prices_and_context_window.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7557,6 +7557,45 @@
"supports_function_calling": true,
"supports_tool_choice": true
},
"azure_ai/deepseek-v3.1": {
"input_cost_per_token": 1.23e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 4.94e-06,
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
Comment on lines +7560 to +7572

@greptile-apps greptile-apps Bot Jun 10, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

P2 supports_reasoning for V3.1 needs verification — The existing azure_ai/deepseek-v3 and azure_ai/deepseek-v3-0324 entries do not set supports_reasoning: true; only deepseek-v3.2 (and its Speciale variant) gained that flag. V3.1 sits between V3 0324 and V3.2 in the timeline, so it's worth confirming whether Azure's V3.1 deployment actually emits chain-of-thought/reasoning tokens before enabling this flag, since setting it incorrectly will affect how LiteLLM parses and prices model responses.

Note: If this suggestion doesn't match your team's coding style, reply to this and let me know. I'll remember it for next time!

"azure_ai/deepseek-v4-pro": {
"input_cost_per_token": 1.74e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 3.48e-06,
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"azure_ai/deepseek-v4-flash": {
"input_cost_per_token": 1.9e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
"max_output_tokens": 384000,
"max_tokens": 384000,
Comment thread
greptile-apps[bot] marked this conversation as resolved.
"mode": "chat",
"output_cost_per_token": 5.1e-07,
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"azure_ai/embed-v-4-0": {
"input_cost_per_token": 1.2e-07,
"litellm_provider": "azure_ai",
Expand Down
Loading