CueCloud

API & DOCUMENTATION

Connect your tools.

Use an OpenAI-compatible request format with CueCloud’s hosted endpoint. Choose a model and inspect the request before connecting.

CONNECT YOUR WORKFLOW

One endpoint. Your tools.

YOUR CLIENT → HOSTED INFERENCE

Make your first request.

  1. Get access.

    Request hosted access. Once enabled, get your API key from the console.

  2. Configure your client.

    Use the base URL and the model ID provided for your enabled workspace. Keep your key out of source control.

  3. Check the response.

    Try a small, approved coding task before connecting a repository or agent workflow.

Full quickstart ↗
REQUEST / CURL
curl https://api.cuecloud.io/v1/chat/completions \
  -H "Authorization: Bearer cue_••••••••" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "YOUR_ENABLED_MODEL_ID",
    "messages": [
      { "role": "user", "content": "fix the failing test" }
    ]
  }'

Example only. Replace the key and YOUR_ENABLED_MODEL_ID with your enabled workspace values.

ENDPOINT

OpenAI-compatible requests

https://api.cuecloud.io/v1

POST /chat/completions with the model ID provided for your enabled workspace and a bearer key. Client support depends on the features it requires.

RESPONSES

Stream or complete

Use stream: true for SSE token chunks. Non-streaming responses suit scripts and single requests. The examples above do not send a request.

ERROR HANDLING

Handle failures explicitly

401 Missing or invalid cue_… key

400 Bad request or unknown model id

503 Capacity path unavailable. Retry or check status.

Authentication, streaming, client setup, and errors.Full API quickstart ↗Coding agent workflows ↗

YOUR NEXT STEP

Ready to connect?

Request hosted access and tell us about your workload. We’ll follow up on availability and onboarding. Creating a console account is a separate step and does not itself grant inference access.

Read the quickstart ↗

Create a console account
Already have an account? Sign in ↗