OpenAI Compatible API

OpenMotoko exposes OpenAI-compatible endpoints so you can use it with any tool or library that supports the OpenAI API format.

Endpoints

Method	Path	Description
POST	/v1/chat/completions	Chat completions (streaming supported)
GET	/v1/models	List available models

These endpoints live at the root path (not under /api/).

Chat completions

Request

curl http://localhost:3457/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-session-token" \
  -d '{
    "model": "balanced",
    "messages": [
      { "role": "system", "content": "You are a helpful assistant" },
      { "role": "user", "content": "What is OpenMotoko?" }
    ],
    "stream": false
  }'

Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1700000000,
  "model": "claude-sonnet-4-6",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "OpenMotoko is a personal AI agent..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 150,
    "total_tokens": 175
  }
}

Streaming

Set "stream": true to receive Server-Sent Events:

curl http://localhost:3457/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-session-token" \
  -d '{
    "model": "fast",
    "messages": [
      { "role": "user", "content": "Hello" }
    ],
    "stream": true
  }'

Each SSE chunk:

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}

data: [DONE]

List models

curl http://localhost:3457/v1/models \
  -H "Authorization: Bearer your-session-token"

{
  "object": "list",
  "data": [
    {
      "id": "claude-sonnet-4-6",
      "object": "model",
      "owned_by": "anthropic"
    },
    {
      "id": "gpt-4o",
      "object": "model",
      "owned_by": "openai"
    }
  ]
}

Model aliases

You can use OpenMotoko’s model aliases (fast, balanced, smart) in the model field. The router resolves them to the configured provider and model.

Using with third-party tools

Python (openai library)

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:3457/v1",
    api_key="your-session-token",
)

response = client.chat.completions.create(
    model="balanced",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Continue.dev

In your Continue config:

{
  "models": [
    {
      "title": "OpenMotoko",
      "provider": "openai",
      "model": "balanced",
      "apiBase": "http://localhost:3457/v1",
      "apiKey": "your-session-token"
    }
  ]
}

Any OpenAI-compatible client

Point the base URL to http://localhost:3457/v1 and use your session token as the API key. OpenMotoko handles routing to the configured LLM provider transparently.