DeepSeek-Coder-V2
DeepSeek's open code specialist — strong benchmark results on HumanEval and coding tasks.
Pricing
InputOpen weights
OutputSelf-hosted cost profile
Cost bandFree/open
Free tierOpen weights (DeepSeek license).
Limits
Context window128k
Max outputRuntime-dependent
Knowledge cutoffQ1 2024
DeploymentSelf-hosted, Hugging Face
OpenAI-compatible APIYes
ModalitiesText
Where it fits
Best forCoding pipelines that want an open model specialized for code completion and generation.
Business fitGood open code model choice; DeepSeek Chat V3.2 now exceeds it for general code tasks.
Capabilities
Open weightsCode specialistFIM support
Benchmark scores
Composite72 / 100
Coding82 / 100 (HumanEval)
Reasoning66 / 100 (MMLU-Pro)
Long context66 / 100
Instruction following70 / 100 (MT-Bench)
Editorial aggregate of published benchmark results as of Aug 1, 2024. These are not independent measurements run by this site.
Change history
No recorded changes for this model yet. Pricing and context are checked daily; changes appear here with dates and sources.
Data
Last checkedJan 10, 2026
Verify with provider documentation before committing spend. Report an error and it gets fixed with a logged correction.