Documentation

The API is a small set of REST endpoints under https://api.fastgencloud.com/v1. Every generation is an asynchronous job: you submit a request, get a job id back immediately, then poll or receive a webhook when the output is ready. The interactive API reference is generated from the same schema the server validates against.

Authentication

Create an API key in the console and send it as a bearer token: Authorization: Bearer fgc_live_…. Keys are shown once at creation and can be revoked at any time. Every response carries an X-Request-Id header; quote it when contacting support.

Jobs

Submit with a POST, then poll GET /v1/jobs/{id} or provide a webhook_url to receive a signed callback when it finishes. Output URLs are signed and valid for up to 7 days (never past your account’s retention window).

curl

curl https://api.fastgencloud.com/v1/images/generations \
  -H "Authorization: Bearer $FASTGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"flux-schnell","prompt":"a watercolor map of Lisbon","size":"1024x1024"}'

# → 202 { "id": "…", "status": "queued", ... }

curl https://api.fastgencloud.com/v1/jobs/<job id> \
  -H "Authorization: Bearer $FASTGEN_API_KEY"

# → 200 { "status": "succeeded", "output": { "images": [ { "url": "https://…", "width": 1024, "height": 1024 } ] } }

Endpoints

Endpoint	Purpose
`POST /v1/images/generations`	Text to image (qwen-image, flux-schnell, sdxl-*)
`POST /v1/images/edits`	Instruction-based image editing (qwen-image-edit)
`POST /v1/videos/generations`	Image to video (wan-2.2-i2v), 5 or 8 seconds
`GET /v1/jobs · GET /v1/jobs/{id} · POST /v1/jobs/{id}/cancel`	List, poll and cancel jobs
`GET /v1/models · GET /v1/loras`	Catalog with capabilities, price preview and license
`GET /v1/account · GET /v1/usage`	Balance, limits and usage aggregates

Billing

The wallet is prepaid. Each job is quoted from the public price list and debited when accepted; failed, canceled and blocked jobs are refunded automatically. GET /v1/account returns your balance and limits, and usage.charged_micros on every job shows what it cost (1 USD = 1,000,000 micros).

Idempotency and rate limits

Send an Idempotency-Key header on POSTs to safely retry: the same key + body replays the original job; a different body returns 409. Requests are rate limited per key (default 60 requests / minute) and per account by in-flight jobs (default 5). See Errors and limits.

Content policy

FastGen Cloud generates safe-for-work content only. Prompts, input images, and every generated output are screened automatically; requests for sexual or adult content, content depicting minors, non-consensual likenesses of real people, or graphic violence are rejected with a content_blocked error and refunded. Repeated violations pause the account. Read the content policy and the Acceptable Use Policy.

Need help?

Email support@fastgencloud.com with the request id or job id.