Documentation overview

ModelRush exposes an OpenAI-compatible base URL at https://api.modelrush.ai/v1. Start with an API key, inspect the live model catalog, then send a request. Every authenticated generation is associated with a request record for debugging and billing.

Live means the endpoint is available now. Beta means the contract can still change. Planned pages describe direction without implying availability.

Keep keys server-side, set a request timeout, retry only transient failures with bounded exponential backoff, retain request IDs, and verify current pricing and region availability before launch.

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.