CJackHwang / ds2api

2026-01-21 · Source: Github Trending: All languages · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Cloud Computing & IT Infrastructure · Depth: Intermediate, medium

Summary

DS2API is an open-source project that converts DeepSeek Web chat capabilities into an OpenAI, Claude, and Gemini-compatible API. The backend is fully implemented in Go, while the frontend is a React WebUI administration console. It supports various core functionalities, including OpenAI-compatible endpoints for chat, responses, embeddings, and files; Claude-compatible endpoints for messages; and Gemini-compatible endpoints for `generateContent` and `streamGenerateContent`. Key features include unified CORS compatibility, multi-account polling with automatic token refresh, concurrent queue control, a pure Go implementation of DeepSeek PoW, and Tool Calling with leakage prevention. DS2API also offers an Admin API for configuration management and a WebUI for server-side conversation history, supporting deployment via local binaries, Docker, Vercel Serverless, or Linux systemd.

Key takeaway

For Machine Learning Engineers or NLP Engineers aiming to integrate DeepSeek models into existing workflows, DS2API offers a robust solution. You can leverage its OpenAI, Claude, and Gemini API compatibility to seamlessly swap DeepSeek models into applications built for these platforms, avoiding extensive code refactoring. Consider deploying DS2API via Docker or Vercel to quickly establish a compatible DeepSeek inference endpoint, ensuring your applications can utilize DeepSeek's capabilities without direct DeepSeek API integration.

Key insights

DS2API unifies DeepSeek Web chat into OpenAI, Claude, and Gemini-compatible APIs via a Go backend.

Principles

• API compatibility simplifies integration.
• Modular architecture enhances maintainability.
• Concurrency control optimizes resource use.

Method

DS2API uses a Go backend with a `PromptCompat` kernel to translate DeepSeek Web chat into OpenAI, Claude, and Gemini API formats, managing authentication, account pooling, and tool call adaptation.

In practice

• Integrate DeepSeek models with existing OpenAI SDKs.
• Deploy via Docker for containerized environments.
• Use the WebUI for configuration and monitoring.

Topics

• DeepSeek API Integration
• OpenAI API Compatibility
• Claude API Compatibility
• Gemini API Compatibility
• Go Backend

Code references

• CJackHwang/ds2api
• CJackHwang/ds2api

Best for: Machine Learning Engineer, NLP Engineer, AI Engineer, Software Engineer, MLOps Engineer

Related on AIssential

• Getting Started with Gemini Deep Research API — The Gemini Deep Research agent enables complex, steerable research tasks and integrates with other Gemini models for visualization and translation.
• Migrating to GPT-5.x Without Breaking GPT-4: A Practical, Backward-Compatible Playbook — GPT-5.x's subtractive parameter changes necessitate a compatibility layer for seamless GPT-4 coexistence.
• Building a Natural Language Interface to the Spotify Ads API with Claude Code Plugins — Natural language interfaces grounded by detailed documentation and transparent execution simplify complex API interactions.
• Local LLMs Need More Than OpenAI-Compatible Endpoints — Local LLM platforms need a dedicated API gateway for stateful, OpenAI-compatible behavior beyond basic inference.
• DeepSeek V4 + Claude Code = BEST AI Coder! — Combine DeepSeek V4 with Claude Code for a cost-effective, hybrid AI coding workflow.
• OpenAI's Latest GPT 5.5 Features — Major tech companies are rapidly integrating advanced AI models while navigating significant privacy and revenue challenges.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Github Trending: All languages.