Models & Pricing | DeepSeek API Docs

The prices listed below are in units of per 1M tokens. A token, the smallest unit of text that the model recognizes, can be a word, a number, or even a punctuation mark. We will bill based on the total number of input and output tokens by the model.Model Details​MODELdeepseek-v4-flash(1)deepseek-v4-proBASE URL (OpenAI Format)https://api.deepseek.comBASE URL (Anthropic Format)https://api.deepseek.com/anthropicMODEL VERSIONDeepSeek-V4-FlashDeepSeek-V4-ProTHINKING MODESupports both non-thinking and thinking (default) modesSee Thinking Mode for how to switchCONTEXT LENGTH1MMAX OUTPUTMAXIMUM: 384KFEATURESJson Output✓✓Tool Calls✓✓Chat Prefix Completion（Beta）✓✓FIM Completion（Beta）Non-thinking mode onlyNon-thinking mode onlyPRICING1M INPUT TOKENS (CACHE HIT)(2)$0.0028$0.003625 (75% off(3))$0.01451M INPUT TOKENS (CACHE MISS)$0.14$0.435 (75% off(3))$1.741M OUTPUT TOKENS$0.28$0.87 (75% off(3))$3.48(1) The model names deepseek-chat and deepseek-reasoner will be deprecated in the future. For compatibility, they correspond to the non-thinking mode and thinking mode of deepseek-v4-flash, respectively. (2) For all models, the input cache hit price has been reduced to 1/10 of the launch price. This price adjustment takes effect from 2026/4/26 12:15 UTC. (3) The deepseek-v4-pro model is currently offered at a 75% discount, extended until 2026/05/31 15:59 UTC.Deduction Rules​The expense = number of tokens × price.

The corresponding fees will be directly deducted from your topped-up balance or granted balance, with a preference for using the granted balance first when both balances are available.Product prices may vary and DeepSeek reserves the right to adjust them. We recommend topping up based on your actual usage and regularly checking this page for the most recent pricing information.