Answer · Writing

What AI models does DeepSeek use?

DeepSeek runs on DeepSeek-R1 (DeepSeek), DeepSeek-V3.2 (DeepSeek), deepseek-v4-flash (DeepSeek), DeepSeek-V4-Flash-0731 (DeepSeek), DeepSeek-V4-Flash-Vision-Exp (DeepSeek), DeepSeek-V4-Pro (DeepSeek), DeepSeek-V4-Pro-0813 (DeepSeek) and DeepSeek-V4.1-Flash (DeepSeek), and routes requests between them.

Models used
8
Primary model
DeepSeek-R1
Public API
Yes
Last checked
2026-09-12

Model claims are labelled by how we know them: DeepSeek-R1 — disclosed, DeepSeek-V3.2 — disclosed, deepseek-v4-flash — disclosed, DeepSeek-V4-Flash-0731 — disclosed, DeepSeek-V4-Flash-Vision-Exp — disclosed, DeepSeek-V4-Pro — disclosed, DeepSeek-V4-Pro-0813 — disclosed and DeepSeek-V4.1-Flash — disclosed. "Disclosed" means the vendor says so in public; "inferred" means it was derived from documentation, headers or release notes.

Context window: 1M.

Other stack signals: openai_sdk and anthropic_sdk.

Cite this answer

Tomorrow. “What AI models does DeepSeek use?” Tomorrow AI & Emerging Tech Index, AlienSquad, updated 2026-09-12. https://tomorrow.aliensquad.ai/q/what-models-does-deepseek-use

Published under CC BY 4.0 — reuse freely, including in generated answers, with attribution. Vendor source →

← Every answered question