Video generation

modelrush/wan3-spicy, modelrush/wan3-pro-spicy, modelrush/wan3-prime-spicy, and modelrush/wan3-prime-pro-spicy use one asynchronous endpoint with three modes:

Wan 3 accepts prompts up to 20,000 characters, 2–30 seconds or -1 for smart duration, adaptive or fixed aspect ratios, native audio, and prompt expansion. Standard and Prime Spicy support 480P, 720P, and 1080P; Pro and Prime Pro Spicy support 1080P, 2K, and 4K. The Prime tiers trade a higher per-second rate for faster turnaround.

bash
curl https://api.modelrush.ai/v1/videos/generations \
  -H "Authorization: Bearer $MODELRUSH_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"modelrush/wan3-spicy","mode":"text-to-video","prompt":"A lunar fox tracing a request across glowing regions","duration":5,"resolution":"1080P","ratio":"16:9","audio":true}'

For image-to-video, set mode to image-to-video and add first_frame plus an optional last_frame. For reference-to-video, set mode to reference-to-video and send up to 10 reference_images, 5 reference_videos, and 5 reference_audios. The API returns 202 with a generation ID and queued status.

Register a public HTTPS endpoint with POST /webhooks/endpoints. ModelRush sends signed prediction.succeeded or prediction.failed events as soon as the asynchronous task completes. Verify the signature and deduplicate by event ID. See webhooks.

Polling remains the recovery path when webhook delivery is delayed:

bash
curl https://api.modelrush.ai/v1/videos/generations/GENERATION_ID \
  -H "Authorization: Bearer $MODELRUSH_API_KEY"

Use bounded backoff until the video endpoint returns completed or failed; read video_url on success. The unified Prediction endpoint uses succeeded and outputs. See asynchronous jobs.

Open a model page for its request parameters and current prices. The four Wan 3 landing pages include a developer API section below the Playground. Read GET /v1/models for current schemas and key-specific access; GET /api/model-pricing exposes current customer prices.

Video polling via GET /v1/videos/generations/:id ends with completed or failed and returns video_url on success. The unified GET /v1/predictions/:id instead uses succeeded and outputs. Follow the contract of the poll_url you use. Wan 3 reference-video time plus generated time cannot exceed 30 seconds. Only Prime and Prime Pro currently accept prompt_extend; check the per-model schema. LoRA supports three optional weight arrays, 480P/720P and 5/8 seconds. Wan Animate and FlashVSR use the video generation endpoint with source media.