DeepSeek-V2
DeepSeek's MoE predecessor with 128k context — still competitive for self-hosted use.
Pricing
InputOpen weights
OutputSelf-hosted cost profile
Cost bandFree/open
Free tierOpen weights (DeepSeek license).
Limits
Context window128k
Max outputRuntime-dependent
Knowledge cutoffQ4 2023
DeploymentSelf-hosted, Hugging Face
OpenAI-compatible APIYes
ModalitiesText
Where it fits
Best forLegacy DeepSeek integrations and self-hosted MoE stacks.
Business fitMigrate to DeepSeek Chat V3.2 for better quality; V2 remains useful for constrained hardware.
Capabilities
Open weightsMoE architectureFunction calling
Benchmark scores
Composite70 / 100
Coding74 / 100 (HumanEval)
Reasoning70 / 100 (MMLU-Pro)
Long context66 / 100 (RULER 128K)
Instruction following72 / 100 (MT-Bench)
Editorial aggregate of published benchmark results as of Jul 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.