Skillget

FreeKimiQwenDeepseekApi

agent
Guvenlik Denetimi
Uyari
Health Uyari
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 6 GitHub stars
Code Uyari
  • process.env — Environment variable access in deepseek.ts
  • network request — Outbound network request in deepseek.ts
  • network request — Outbound network request in docker-compose.yml
  • network request — Outbound network request in examples/direct-api/fetch-example.ts
Permissions Gecti
  • Permissions — No dangerous permissions requested

Bu listing icin henuz AI raporu yok.

SUMMARY

Unified OpenAI-compatible gateway for Qwen Chat, Kimi Chat and DeepSeek Web with persistent sessions, tool calling, Docker support, and integrations for popular AI coding agents.

README.md

FreeQwenApi

Free API proxy for DeepSeek, Kimi, GLM, Sapiens, StepFun and NVIDIA models — OpenAI-compatible endpoint for OpenCode, Continue, Cline, Aider and any AI agent.

Bun
OpenAI compatible
License: MIT

Quick Start · Models · API · Docker

FreeQwenApi is a proxy for DeepSeek Web, Kimi, GLM, Sapiens, StepFun via ZenMux, and NVIDIA API models with an OpenAI-compatible API.

Quick Start

git clone https://github.com/kravchenski/FreeQwenApi.git
cd FreeQwenApi
bun install
bun run start

Server: http://localhost:3260

Models

Provider Models Key
DeepSeek deepseek-default, deepseek-expert, deepseek-search Browser auth
Kimi (ZenMux) kimi-k2.7-code-free ZENMUX_API_KEY
GLM (ZenMux) glm-5.2-free, glm-4.7-flash-free ZENMUX_API_KEY
Sapiens (ZenMux) sapiens-ai/agnes-2.0-flash ZENMUX_API_KEY
StepFun (ZenMux) stepfun/step-3.7-flash-free ZENMUX_API_KEY
NVIDIA deepseek-ai/deepseek-v4-pro, moonshotai/kimi-k2.6 NVIDIA_API_KEY

All models are free. ZenMux and NVIDIA require API keys.

curl http://localhost:3260/v1/models

First Request

curl http://localhost:3260/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-default",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": false
  }'

API Reference

Method Endpoint Description
GET /v1/models List models
POST /v1/chat/completions Chat Completions (streaming + non-streaming)
GET /health Server status

DeepSeek supports tool calls. Web providers (DeepSeek) work through browser (Puppeteer) and support streaming. ZenMux providers (Kimi, GLM, Sapiens, StepFun) use https://zenmux.ai/api/v1. NVIDIA providers use https://integrate.api.nvidia.com/v1.

Commands

Command Description
bun run start Start unified server (port 3260)
bun run dev Start with watch mode
bun run auth Manage DeepSeek accounts
bun run test Run tests
bun run check Validate build

Docker

docker build -t freeqwenapi .
docker run -d \
  -p 3260:3260 \
  -e ZENMUX_API_KEY=your_key \
  -e NVIDIA_API_KEY=your_key \
  freeqwenapi

Environment Variables

Variable Default Description
UNIFIED_PORT 3260 Server port
HOST 0.0.0.0 Bind address
ZENMUX_API_KEY - ZenMux API key (for Kimi, GLM, Sapiens, StepFun)
NVIDIA_API_KEY - NVIDIA API key (for DeepSeek V4 Pro, Kimi K2.6)

Project Structure

src/
  unified/server.ts      — main server (all providers)
  providers/             — provider clients (deepseek/, kimi/, glm/, sapiens/, stepfun/, nvidia/)
  api/                   — API routes and chat logic
  browser/               — Puppeteer browser
  web/server.ts          — web interface
session/                 — account tokens (gitignored)

License

MIT. Copyright (c) 2026 kravchenski.

Yorumlar (0)

Sonuc bulunamadi