Skip to main content
DeepSeek ↗Released June 17, 2024

DeepSeek Coder V2

Open Source236B (21B active) parameters

DeepSeek Coder V2 is DeepSeek's entry in a crowded field. Context window: 0.128K tokens.

Context

128K

Input

$0.14

Key Specifications

🏆

Arena Rank

Not disclosed

📐

Context Window

128K

📥

Input Price

per 1M tokens

$0.14

📤

Output Price

per 1M tokens

$0.28

🧠

Parameters

236B (21B active)

🔓

Open Source

Yes

Best For

Code generationdebuggingcode review

About DeepSeek Coder V2

DeepSeek Coder V2, developed by DeepSeek, is a specialized code model with 236 billion total parameters (21 billion active) and a 128K token context window. The model uses a Mixture-of-Experts architecture optimized for software development, excelling at code generation, debugging, code review, and technical documentation across multiple programming languages. It supports 338 programming languages and achieves competitive scores on HumanEval and MBPP coding benchmarks. As an open-source model, it can be deployed on-premise for organizations with strict code security requirements. Priced at $0.14 per million input tokens and $0.28 per million output tokens through the API, or free to self-host, DeepSeek Coder V2 offers professional-grade code assistance at substantially lower cost than proprietary alternatives. Its MoE architecture enables efficient inference despite the large total parameter count.

Built byDeepSeek↗

Pricing per 1M tokens

Input Tokens

$0.14

Output Tokens

$0.28

Compare DeepSeek Coder V2

See how DeepSeek Coder V2 stacks up against other leading AI models

DeepSeek Coder V2 vs DeepSeek R1Compare →DeepSeek Coder V2 vs DeepSeek V3Compare →DeepSeek Coder V2 vs Claude Opus 4Compare →DeepSeek Coder V2 vs GPT-o3Compare →DeepSeek Coder V2 vs GPT-4oCompare →

Other DeepSeek Models

DeepSeek R1
128K#3
DeepSeek V3
128K#5

Other Top Models

Claude Opus 4Anthropic
#1
GPT-o3OpenAI
#2
GPT-4oOpenAI
#2
Claude Sonnet 4Anthropic
#3
GPT-o1OpenAI
#3
Gemini 2.5 ProGoogle DeepMind
#4

Explore More

Model Benchmarks →All Models →DeepSeek Company Profile →

Frequently Asked Questions

What is DeepSeek Coder V2?▾
DeepSeek Coder V2, developed by DeepSeek, is a specialized code model with 236 billion total parameters (21 billion active) and a 128K token context window. The model uses a Mixture-of-Experts architecture optimized for software development, excelling at code generation, debugging, code review, and technical documentation across multiple programming languages. It supports 338 programming languages and achieves competitive scores on HumanEval and MBPP coding benchmarks. As an open-source model, it can be deployed on-premise for organizations with strict code security requirements. Priced at $0.14 per million input tokens and $0.28 per million output tokens through the API, or free to self-host, DeepSeek Coder V2 offers professional-grade code assistance at substantially lower cost than proprietary alternatives. Its MoE architecture enables efficient inference despite the large total parameter count.
How much does DeepSeek Coder V2 cost?▾
DeepSeek charges $0.14 per 1M input tokens for DeepSeek Coder V2, with output at $0.28. Competitive with other models in its tier.
What is DeepSeek Coder V2's context window?▾
DeepSeek Coder V2 supports up to 128K tokens per request. A larger context window allows the model to reason over longer inputs, which matters for document analysis, code review, and multi-turn conversations.
Is DeepSeek Coder V2 open source?▾
Yes — DeepSeek released DeepSeek Coder V2 as open source. That means you're free to deploy it however you want: cloud, on-prem, edge. No API lock-in.
What is DeepSeek Coder V2 best for?▾
DeepSeek positions DeepSeek Coder V2 for: Code generation, debugging, code review. Real-world performance will depend on your specific prompts and data, but these are the intended strengths.