← Back to all tools
DeepSeek Coder logo

DeepSeek Coder

✓ Verified

Open-source MoE coding model (V2) with 128K context

Updated Dec 7, 2025
Open Source ModelOpen SourceAll platforms via API
Last reviewed: Dec 7, 2025Details verified against vendor changelogs and hands-on usage.
Visit Website →

Pricing and features change frequently—confirm on the vendor site.

About

DeepSeek Coder V2 is an open Mixture-of-Experts coding model (16B Lite and 236B) with a 128K context window and support for 338 programming languages. Weights are published on Hugging Face for self-hosting; code is MIT-licensed and the model weights use the DeepSeek Model License. Hosted inference is available through the DeepSeek API using OpenAI-compatible endpoints.

Key Features

  • ✓DeepSeek-Coder-V2 Mixture-of-Experts models (236B total / 21B active, plus 16B Lite / 2.4B active)
  • ✓128K context window with fill-in-the-middle support
  • ✓Supports 338 programming languages
  • ✓Open weights for self-hosting with MIT code and DeepSeek Model License
  • ✓OpenAI-compatible API access via the DeepSeek platform

Use Cases

  • →Budget-friendly AI coding at scale
  • →Self-hosted AI coding solutions
  • →Open-source development
  • →Cost-sensitive production deployments

Technical Details

Languages

338 programming languages

AI Models

DeepSeek-Coder-V2-Instruct (236B / 21B active)DeepSeek-Coder-V2-Lite-Instruct (16B / 2.4B active)

Integrations

Self-hostedHugging FaceOpenAI-compatible API clients

Frequently Asked Questions

What is DeepSeek Coder?

DeepSeek Coder V2 is an open Mixture-of-Experts coding model (16B Lite and 236B) with a 128K context window and support for 338 programming languages. Weights are published on Hugging Face for self-hosting; code is MIT-licensed and the model weights use the DeepSeek Model License. Hosted inference is available through the DeepSeek API using OpenAI-compatible endpoints.

Is DeepSeek Coder free?

Yes, DeepSeek Coder is open source and free to use. Weights on Hugging Face (16B Lite, 236B Base/Instruct), Code under MIT license; weights under DeepSeek Model License, Run on your own hardware or cloud

What programming languages does DeepSeek Coder support?

DeepSeek Coder supports 1+ programming languages including 338 programming languages.

What AI models does DeepSeek Coder use?

DeepSeek Coder is powered by DeepSeek-Coder-V2-Instruct (236B / 21B active), DeepSeek-Coder-V2-Lite-Instruct (16B / 2.4B active).

What platforms does DeepSeek Coder support?

DeepSeek Coder is available on All platforms via API.

What can DeepSeek Coder do?

DeepSeek Coder provides code completion, code generation, debugging, AI chat. Key features include: DeepSeek-Coder-V2 Mixture-of-Experts models (236B total / 21B active, plus 16B Lite / 2.4B active), 128K context window with fill-in-the-middle support, Supports 338 programming languages.

Related Articles

Guide

5 Grounded Observations on AI for Developers (Late 2025)

A short, sourced look at how AI is actually being used in dev workflows in late 2025—no fiction, just what’s real.

2025-12-07•3 min read
→

Pricing

Open weights (self-hosted)

$0
  • •Weights on Hugging Face (16B Lite, 236B Base/Instruct)
  • •Code under MIT license; weights under DeepSeek Model License
  • •Run on your own hardware or cloud

DeepSeek API (V3.2 chat/reasoner)

Pay-as-you-go
  • •Hosted access via DeepSeek platform
  • •OpenAI-compatible API with JSON, tool calls, FIM, and caching

Company

Name
DeepSeek
Founded
2023
Location
China
Users
Open-source community

Links

GitHub →Twitter →Discord →

Similar Tools

Compare DeepSeek Coder with these alternatives

Compare All
OpenAI API logo

OpenAI API

✓

API access to GPT-5.1, GPT-5, GPT-4o, images, audio, and tools

API/SDK Tool

OpenAI’s API gives developers pay-per-use access to the latest GPT models (GPT-5.1, GPT-5, GPT-4o, GPT-4.1, GPT-4.1 mini/nano, o-series), plus images (GPT-Image-1), speech (gpt-audio, Whisper), embeddings, and moderation. It supports tool calling, structured outputs, Assistants/Responses/Chat Completions, Batch, Realtime, prompt caching, fine-tuning, and file/image/audio endpoints. Pricing is metered per model; for example, GPT-5.1 Standard is $1.25 per 1M input ($0.125 cached) and $10 per 1M output, or $0.625 / $5 via Batch (see pricing page for all models).

Pay-per-use

Key Features:

  • •Access to GPT-5.1, GPT-5, GPT-4o, GPT-4.1, GPT-4.1 mini/nano, and o-series models
  • •Text and image inputs with text outputs; audio (TTS/STT) and image generation endpoints
  • •Tool calling, structured/JSON outputs, and Assistants/Responses/Chat Completions APIs
API
Learn more →
Anthropic Claude API logo

Anthropic Claude API

✓

Build with Claude Opus 4.5, Sonnet 4.5, and Haiku 4.5 via the Anthropic API

API/SDK Tool

The Anthropic Claude API provides pay-per-use access to Claude’s latest models: Opus 4.5 ($5/$25 MTok), Sonnet 4.5 ($3/$15 MTok for ≤200K prompts; $6/$22.5 MTok for >200K prompts), and Haiku 4.5 ($1/$5 MTok). The API supports 200K-token contexts, tool use/function calling, prompt caching (write/read discounts), and batch processing (50% savings). Available through the Claude Developer Platform with official SDKs, plus partner access on Amazon Bedrock, Google Cloud Vertex AI, and Microsoft Foundry.

Pay-per-use

Key Features:

  • •200K token context window with higher-tier pricing for >200K Sonnet prompts
  • •Opus 4.5 for frontier reasoning and coding; Sonnet 4.5 for balanced cost/speed; Haiku 4.5 for fast, low-cost tasks
  • •Tool use/function calling and structured outputs
APIWeb
Learn more →
View detailed comparison