Docs

1. Point at Cue Cloud

1. Base URL: https://api.cuecloud.io/v1
2. Auth: Authorization: Bearer cue_… from the console.
3. POST /chat/completions with the model ID supplied for your enabled workspace.

Keep API keys private and out of source control.

2. First request

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" }
    ]
  }'

3. Stream

Set stream: true for SSE token chunks. The normal path for IDE agents. Non-streaming completions work for scripts.

curl https://api.cuecloud.io/v1/chat/completions \
  -H "Authorization: Bearer cue_••••••••" \
  -H "Content-Type: application/json" \
  -N \
  -d '{
    "model": "YOUR_ENABLED_MODEL_ID",
    "stream": true,
    "messages": [
      { "role": "user", "content": "refactor this module" }
    ]
  }'

Models

Confirm available models and your API model ID during onboarding. Explore the hosted catalog.

Clients

Configure the base URL, API key and enabled model ID in a compatible client. Confirm support for the endpoint and features your workflow uses.

• Cursor. Configure a compatible provider with the CueCloud base URL, your API key and your enabled model ID.
• CueCode. Configure a compatible model provider in your CueCode build with your hosted endpoint and enabled model ID.
• Scripts & tools. Use an OpenAI-compatible client or HTTP request for supported endpoints. Confirm the request features required by your workflow.

Errors

Support

[email protected] · API overview · Pricing