DeepSeek Coder
DeepSeek-Coder: Open-source, project-aware code models with SOTA performance and massive context.
DeepSeek Coder is a freemium AI tool. DeepSeek-Coder: Open-source, project-aware code models with SOTA performance and massive context. Editors list 12 strengths on this page, next to the published price.
Quick facts
- Best for
- DeepSeek-Coder: Open-source, project-aware code models with SOTA performance and massive context.
- Pricing
- Freemium
- Editor rating
- 4.5 / 5
- Community saves
- 0
About DeepSeek Coder
DeepSeek-Coder is an open-source code language model series from DeepSeek-AI, trained from scratch on 2T tokens (87% code, 13% natural language in English and Chinese) that delivers state-of-the-art performance on coding benchmarks like HumanEval, MultiPL-E, MBPP, DS-1000, and APPS, supports project-level code completion and infilling with a 16K context window (extended to 128K in V2), covers 86+ programming languages (up to 338 in V2), and is available in multiple sizes from 1B to 33B parameters plus a Mixture-of-Experts V2 comparable to GPT-4-Turbo in coding and math tasks.
Pros
- Open-source series of code language models by DeepSeek-AI
- Trained from scratch on 2T tokens (87% code, 13% English/Chinese text)
- State-of-the-art results on HumanEval, MultiPL-E, MBPP, DS-1000, and APPS
- Project-level code completion and repository-aware infilling
- 16K context window, extended to 128K in DeepSeek-Coder-V2
- Supports 86+ languages (up to 338 in V2)
- Multiple parameter sizes: 1B, 5.7B, 6.7B, 33B
- Mixture-of-Experts DeepSeek-Coder-V2 comparable to GPT-4-Turbo on coding/math tasks
- Pre-trained on project-level code corpora for multi-file understanding
- Fill-in-the-blank (FIM) capability for in-place code edits
- Flexible, scalable architecture suitable for varied deployment scenarios
- Backed by DeepSeek-AI’s open-source ecosystem and infrastructure tooling
Pricing
- • Free to download and use
- • Open-source, self-hostable
- • Models available (e.g., 1B, 5.7B, 6.7B, 33B)
- • Includes training code and benchmarks
- • Optional hosted, OpenAI-compatible API
- • Described as pay-as-you-go
- • Specific pricing not listed on the GitHub repo; check platform.deepseek.com
- • Enterprise/contact for details