This model is over 2 years old. A newer version of it has since shipped: DeepSeek V4 Flash Vision Exp (2026-08-21). The details below are still accurate for this model — it just is not what we would recommend today.

DeepSeek Coder V2

DeepSeek🇨🇳 China
deprecated

Open-source code model matching GPT-4 Turbo on coding benchmarks. Superseded by V3.

Context window128K tokens
Input / 1M tokens$0.14
Output / 1M tokens$0.28

Version History

DeepSeek-Coder-V2-Instructmajor

DeepSeek Coder V2 beats GPT-4 Turbo on code benchmarks as an open-weights model. 236B MoE with 64K context.