Documentation

Quickstart preview

This documentation is an early-access preview. API availability depends on onboarding approval and provider availability.

Base URL

Use the following placeholder base URL during planning. Production access will be provided after onboarding approval.

https://api.yourdomain.com/v1

Authentication

API requests are expected to use bearer-token authentication. API keys should be stored securely and never exposed in client-side applications.

Authorization: Bearer YOUR_API_KEY

Chat completions example

Designed for OpenAI-compatible workflows. Final request and response behavior may vary by model.

Request previewEarly access

curl https://api.yourdomain.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen-plus",
    "messages": [
      { "role": "system", "content": "You are a concise SaaS product assistant." },
      { "role": "user", "content": "Draft a support reply for this customer issue." }
    ]
  }'

Model IDs

Example model IDs for planning and early-access documentation.

minimax-m2
hailuo-video
qwen-plus
kimi-latest
zhipu-glm
deepseek-chat

Error handling

The API should return structured error responses with a stable code, message, and request ID when available.

invalid_api_keymodel_not_availablerate_limit_exceededprovider_unavailableinvalid_request

Rate limits

Rate limits may vary by organization, model family, provider availability, and onboarding tier. Early-access accounts may receive conservative limits while usage patterns are reviewed.

Future async video jobs

Video generation workflows may use asynchronous job creation and webhook notifications in a future API version.

POST /v1/video/jobs
POST /v1/webhooks

Request early API access

API access is not automatically activated. We review each use case and follow up with next steps.

Request API Access View Docs