Skip to main content

AI APIs

The platform exposes its AI capabilities as HTTP APIs you can call straight from your own software. Two surfaces cover most integrations:

  • Model Gateway — one endpoint for the platform's supported OpenAI-compatible model operations. Whether a model runs in your own cluster or at an external provider, you call the same base URL and the gateway routes the request.
  • RAG — a deployable retrieval system that grounds answers in your own documents. Each RAG has its own API on its own deployment-specific URL, used to ingest and manage documents and retrieve relevant context.

Authentication​

Every request carries an API key as a bearer token:

Authorization: Bearer cm_api_…

The key's grants decide which models and RAGs it can reach. Each service's portal view shows its base URL alongside a Create API key link. The platform-wide gateway URL is also always at hand, as API URL at the bottom of the portal sidebar with a button to copy it. A RAG's URL is deployment-specific, so that one stays on the RAG's own view.

Calling a model​

The Model Gateway supports OpenAI clients for the documented operations. Point the client at the gateway and pass your key:

from openai import OpenAI

client = OpenAI(base_url="https://api.<your-domain>/v1", api_key="cm_api_…")

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

GET /v1/models lists the models your key can use. See Model Gateway for routing, model capabilities, filtering, and API compatibility.

For new integrations, see Responses API for copy-paste examples covering a single response, streaming, and conversations.

Agentic workflows and tools​

The gateway's Responses API (/v1/responses) runs a built-in tool loop — hand the model a task and a set of tools, and it drives the calls until it has a final answer, with no orchestration to host. Tools are provided over MCP, shared with the built-in chat: RAG is available out of the box, and you can add your own MCP servers.

Start with Responses API, then continue to Tools and Agents when you need RAG or MCP tools.