Docs / Get started

Quickstart

Early-access preview. Keys are issued to approved customers. Request access

The Gateway speaks the OpenAI, Anthropic and Gemini formats for text and images, and one task API for every video model. Make your first video in three calls.

Base URLhttps://api.5w1hstudios.com/v1
China regionhttps://api.5w1h.studio/v1

Authentication

Send your key as a Bearer token in the Authorization header. Never put a key in client-side code.

POST

/videos

Creates a render task and holds the estimated cost. The task settles on the seconds actually rendered.


      
FieldTypeDescription
modelstringAny video model ID, e.g. quasar-1, seedance-2.0, kling-3.0
promptstringShot description
referencesarrayImages, video or audio by URL or asset ID, with a role (first_frame, character, style)
durationintegerSeconds; the allowed range depends on the model
resolution, ratiostring480p, 720p, 1080p · 16:9, 9:16, 1:1
webhook_urlstringOptional callback when the task finishes
GET

/videos/{id}

Status moves through queued, running, succeeded, failed or cancelled.

POST

/videos/estimate

Same body as create. Returns the cost before you spend anything.

Errors and limits

402 insufficient balance · 422 invalid parameters · 429 rate limited · 451 blocked by content policy. Concurrency depends on your plan.