Model API overview

Model IDs are not interchangeable across endpoint families. Choose the input/output contract first, then use GET /models to inspect the current callable catalog. Provider release research stays in the Admin candidate queue and is not returned as a customer-callable model.

Use the model catalog for model-level inputs and outputs, pricing for commercial terms, and GET /regions for the current execution surface.

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.

MuleRouter image calls can return HTTP 202 with id and poll_url. Poll that URL with the same API key; GET /v1/predictions/:id completes with status succeeded and outputs. Z-Image Pro Spicy accepts width and height from 256 to 2560 (default 1024), n = 1 and prompt_extend = false by default. Z-Image Spicy also produces one image per request. Do not copy another model's size or output-count limits.

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.