Why it fits
One pipeline for visual output
Image and video generation share the same authentication, billing, and routing.
Image generation
Generate images with FLUX.1 Schnell via /v1/images/generations, priced per image.
Video generation
Create short videos with Wan2.1 — submit an async job and poll for the result, billed per generation.
OpenAI-compatible images API
Use the standard images endpoint with the client you already have.
Pay per output
Per-image and per-generation pricing — no idle GPU costs to carry.
Fast iteration
Prototype quickly with low-latency image generation.
Multi-region
Requests route to a healthy region automatically.
Quickstart
Images now, video as a job
Images return synchronously; video runs as a background job you poll for.
# image generation (synchronous)
image = client.images.generate(
model="flux.1-schnell",
prompt="a neon city skyline at dusk",
)
# video generation (asynchronous job)
POST /v1/video/generations
{ "model": "wan21-t2v-1-3b", "prompt": "a calm ocean at sunrise" }
# -> poll GET /v1/video/jobs/{id} until "succeeded"