scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-04 02:31:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 71

feat(cost): add cost mapping for deepseek-v4-flash and deepseek-v4-pro

Browse source 
Adds pricing entries for the two new DeepSeek V4 models released on
2026-04-24, for both bare model names and the deepseek/ provider prefix.

Prices sourced from https://api-docs.deepseek.com/quick_start/pricing:
- deepseek-v4-flash: $0.14/M input, $0.28/M output
- deepseek-v4-pro:   $1.74/M input, $3.48/M output

Cache hit price set to 1/10 of input (per DeepSeek docs).
Context window: 1M tokens for both models.

Closes #26709
This commit is contained in:
Dushyant Acharya 2026-05-03 00:03:52 +05:30 • committed by Dotify71
parent d011d0e4fc
commit 9482e771ad
No known key found for this signature in database
1 changed files with 48 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

48
model_prices_and_context_window.json
View file

@ -12573,6 +12573,54 @@
"supports_system_messages": true,
"supports_tool_choice": false
},
"deepseek/deepseek-v4-flash": {
"cache_creation_input_token_cost": 0.0,
"cache_read_input_token_cost": 1.4e-08,
"input_cost_per_token": 1.4e-07,
"input_cost_per_token_cache_hit": 1.4e-08,
"litellm_provider": "deepseek",
"max_input_tokens": 1000000,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 2.8e-07,
"source": "https://api-docs.deepseek.com/quick_start/pricing",
"supported_endpoints": [
"/v1/chat/completions"
],
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"deepseek/deepseek-v4-pro": {
"cache_creation_input_token_cost": 0.0,
"cache_read_input_token_cost": 1.74e-07,
"input_cost_per_token": 1.74e-06,
"input_cost_per_token_cache_hit": 1.74e-07,
"litellm_provider": "deepseek",
"max_input_tokens": 1000000,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 3.48e-06,
"source": "https://api-docs.deepseek.com/quick_start/pricing",
"supported_endpoints": [
"/v1/chat/completions"
],
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"deepseek/deepseek-v3": {
"cache_creation_input_token_cost": 0.0,
"cache_read_input_token_cost": 7e-08,