Command Code API Proxy

OpenAI-compatible API proxy for Command Code. Use your Command Code subscription from any OpenAI-compatible client — OpenCode, Continue, the OpenAI SDK, or plain curl.

npx commandcode-api-proxy

Why?

Command Code exposes two API surfaces:

Surface	Protocol	Plan required
/provider/v1/chat/completions	OpenAI-compatible	Provider tier (paid add-on)
/alpha/generate	Custom (Vercel AI SDK stream)	Your standard subscription

This proxy talks /alpha/generate upstream and standard OpenAI downstream — so your existing plan works from any tool.

Quick start

# Run directly (no install)
npx commandcode-api-proxy

# Or install globally
npm install -g commandcode-api-proxy
commandcode-api-proxy

Authentication

The proxy loads your API key from (in order of priority):

1. --api-key CLI flag: npx commandcode-api-proxy --api-key user_xxx
2. CC_API_KEY environment variable
3. ~/.commandcode/auth.json (auto-generated by npx command-code)

If you've already run npx command-code to log in, no extra setup is needed.

CLI options

Option	Description	Default
--host	Bind address	127.0.0.1
--port	Port	8787
--api-key	Command Code API key	—

Endpoints

POST /v1/chat/completions (OpenAI)

curl http://127.0.0.1:8787/v1/chat/completions \
  -H "Authorization: Bearer user_xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-pro",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": true
  }'

Client configuration

OpenCode

Add to your opencode.json (project root or ~/.config/opencode/opencode.json):

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "commandcode": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Command Code",
      "options": {
        "baseURL": "http://127.0.0.1:8787/v1"
      },
      "models": {
        "deepseek/deepseek-v4-pro": { "name": "DeepSeek V4 Pro" },
        "deepseek/deepseek-v4-flash": { "name": "DeepSeek V4 Flash" },
        "MiniMaxAI/MiniMax-M2.7": { "name": "MiniMax M2.7" },
        "MiniMaxAI/MiniMax-M2.5": { "name": "MiniMax M2.5" },
        "zai-org/GLM-5.1": { "name": "GLM 5.1" },
        "zai-org/GLM-5": { "name": "GLM 5" },
        "moonshotai/Kimi-K2.6": { "name": "Kimi K2.6" },
        "moonshotai/Kimi-K2.5": { "name": "Kimi K2.5" },
        "Qwen/Qwen3.6-Max-Preview": { "name": "Qwen 3.6 Max" },
        "Qwen/Qwen3.6-Plus": { "name": "Qwen 3.6 Plus" },
        "Qwen/Qwen3.7-Max": { "name": "Qwen 3.7 Max" },
        "Qwen/Qwen3.7-Plus": { "name": "Qwen 3.7 Plus" },
        "stepfun/Step-3.5-Flash": { "name": "Step 3.5 Flash" },
        "google/gemini-3.1-flash-lite": { "name": "Gemini 3.1 Flash Lite" },
        "google/gemini-3.5-flash": { "name": "Gemini 3.5 Flash" },
        "xiaomi/mimo-v2.5": { "name": "MiMo v2.5" },
        "claude-sonnet-4-6": { "name": "Claude Sonnet 4.6" },
        "claude-opus-4-7": { "name": "Claude Opus 4.7" },
        "openai/gpt-5.5": { "name": "GPT 5.5" }
      }
    }
  }
}

OpenAI Python SDK

from openai import OpenAI

client = OpenAI(
    base_url="http://127.0.0.1:8787/v1",
    api_key="placeholder",
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v4-pro",
    messages=[{"role": "user", "content": "Hello!"}],
)

Continue

{
  "models": [
    {
      "title": "Command Code",
      "provider": "openai",
      "model": "deepseek/deepseek-v4-pro",
      "apiKey": "placeholder",
      "apiBase": "http://127.0.0.1:8787/v1"
    }
  ]
}

Model aliases

Short names work in addition to full model IDs:

Alias	Maps to
deepseek-v4-pro, deepseek-v4	deepseek/deepseek-v4-pro
deepseek-v4-flash, deepseek-flash	deepseek/deepseek-v4-flash
claude-sonnet-4-6, claude-opus-4-7	deepseek/deepseek-v4-pro
gpt-4, gpt-4o, gpt-5, gpt-5.5	deepseek/deepseek-v4-pro
kimi-k2.6, kimi-k2.5	moonshotai/Kimi-*
qwen-3.6-max, qwen-3.6-plus	Qwen/Qwen3.6-*
glm-5.1, glm-5	zai-org/GLM-*

License

MIT