DeepSeek-Coder
DeepSeek · November 2023
● activeOpen Sourcedecoder onlycode
Parameters1.3B - 33B
Context Window16K tokens
Variants1.3B, 6.7B, 33B, Instruct
Description
DeepSeek's code-specialized model family, trained from scratch on 2 trillion tokens of code and natural language. Available in sizes from 1.3B to 33B parameters, it was one of the first Chinese-developed open-source code models to rival Western alternatives on coding benchmarks.
Key Innovations
Code Gen
Code GenAbility to write, debug, and understand programming code across multiple languages.
External Links
More from DeepSeek
DeepSeek V12024-01 · 67B
DeepSeek V22024-05 · 236B (21B active)
DeepSeek V32024-12 · 671B (37B active)
DeepSeek R12025-01 · 671B (37B active)
DeepSeek V4 Pro2026-04 · 1.6T
DeepSeek-Coder-V22024-06 · 236B (21B active)
DeepSeek V4 Flash Vision Exp2026-08-21 · —
DeepSeek V4.1 Flash2026-09-10 · 680B (38B active)