command-code-router

OpenAI-compatible API backed by the Command Code CLI.

Authentication

Send Authorization: Bearer <your key> with every request.

Endpoints

Method	Path	Description
POST	/v1/chat/completions	Chat — streaming & non-streaming
POST	/v1/completions	Legacy text completion
GET	/v1/models	List models (33 models available — see /v1/models.)
GET	/health	Health check

Chat completion

curl https://jdoeaga6dd8dey164cze7ein.coolify-server.xyz/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer YOUR_KEY' \
  -d '{
    "model": "deepseek/deepseek-v4-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Streaming

curl -N https://jdoeaga6dd8dey164cze7ein.coolify-server.xyz/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer YOUR_KEY' \
  -d '{"model": "deepseek/deepseek-v4-flash", "stream": true,
       "messages": [{"role": "user", "content": "Count to 5"}]}'

Stateful conversations

Command Code keeps real memory across turns. Reuse a conversation by sending the same x-ccr-session id (the response also returns one). A normal client that resends the full history is auto-detected — no header needed.

# Turn 1 — pin a conversation id
curl https://jdoeaga6dd8dey164cze7ein.coolify-server.xyz/v1/chat/completions \
  -H 'Content-Type: application/json' -H 'x-ccr-session: chat-1' \
  -H 'Authorization: Bearer YOUR_KEY' \
  -d '{"model": "deepseek/deepseek-v4-flash", "messages": [{"role": "user", "content": "My name is Sam."}]}'

# Turn 2 — same id, only the new message; the agent remembers
curl https://jdoeaga6dd8dey164cze7ein.coolify-server.xyz/v1/chat/completions \
  -H 'Content-Type: application/json' -H 'x-ccr-session: chat-1' \
  -H 'Authorization: Bearer YOUR_KEY' \
  -d '{"model": "deepseek/deepseek-v4-flash", "messages": [{"role": "user", "content": "What is my name?"}]}'

OpenAI Python SDK

from openai import OpenAI

client = OpenAI(
    base_url="https://jdoeaga6dd8dey164cze7ein.coolify-server.xyz/v1",
    api_key="YOUR_KEY",
)
resp = client.chat.completions.create(
    model="deepseek/deepseek-v4-flash",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)