Documentation

Connect in under two minutes

ProjectCOZY speaks the OpenAI chat-completions format. Point any compatible client at the base URL below, paste your key, and name a model alias. No SDK to install, no code to rewrite.

Your connection

All models live
Base URL
https://api.projectcozy.me/v1
Auth header
Authorization: Bearer cozy_…Get a key
Model field
"model": "kimi-k2.6"All aliases

Make your first request

Runs as written once you swap in your key.

cURL
curl https://api.projectcozy.me/v1/chat/completions \
  -H "Authorization: Bearer cozy_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2.6",
    "messages": [
      { "role": "user", "content": "Say hello in one line." }
    ]
  }'

Streaming works the same way: set "stream": true and read the server-sent event stream exactly as you would from OpenAI.

Model aliases

Every alias is included in every pass. Switching model is a one-word change.

AliasModelBest for
kimi-k3 Kimi K3Long-context agentic coding and deep tool use
kimi-k2.6 Kimi K2.6Fast general-purpose coding, large context
kimi-k2.5 Kimi K2.5Previous generation, kept for stability
claude-5-opus Claude 5 OpusHardest reasoning, refactors, architecture
claude-5-sonnet Claude 5 SonnetBalanced speed and quality, day to day
deepseek-v4-pro DeepSeek V4 ProReasoning and maths at high throughput
glm-5.2 GLM 5.2Instruction following, structured output
glm-5.1 GLM 5.1Previous generation, kept for stability
minimax-m3 MiniMax M3Long-horizon agent runs, batch work
minimax-m2.7 MiniMax M2.7Previous generation, kept for stability
qwen-3.5-coder Qwen-3.5-CoderCompletion, test generation, translation

Endpoints

Relative to the base URL above.

MethodPathReturns
POST/chat/completionsChat completion, or an SSE stream when "stream": true
GET/modelsEvery alias your pass can call

Editor and agent setup

Most tools read these two variables. Set them and restart the tool.

env
OPENAI_BASE_URL=https://api.projectcozy.me/v1
OPENAI_API_KEY=cozy_your_key_here
  • Claude Code ANTHROPIC_BASE_URL
  • Cline OpenAI Compatible
  • OpenClaw OPENAI_BASE_URL
  • OpenCode OPENAI_BASE_URL
  • Kilo Code OpenAI Compatible
  • Roo Code OpenAI Compatible
  • Cursor Override base URL
  • Aider OPENAI_API_BASE

If the first request fails

401
Key rejected. Check for a trailing space when pasting, and that the key starts with cozy_. Keys are shown once, so regenerate if unsure.
402
Pass expired or trial used up. Buy or renew a pass; the same key reactivates.
404
Wrong path. The base URL must end in /v1, and your client appends /chat/completions itself. A doubled /v1/v1 is the usual cause.
400
Unknown model. Use an alias exactly as listed above. Upstream model IDs are not accepted.