POST /images/generations

Generate images using the selected model’s output limits. The base URL is https://api.modelrush.ai/v1.

model, prompt. Check GET /models → operations.input_schema for each model's fields and limits. Z-Image models use width/height and n=1; Z-Image Pro also accepts prompt_extend. Other models may use size, quality, output_format, watermark or thinking_mode. Send Authorization: Bearer $MODELRUSH_API_KEY for authenticated routes and Content-Type: application/json for JSON bodies.

Async models: HTTP 202 with id, poll_url; poll GET /predictions/:id until succeeded or failed and read outputs. Synchronous models: id, generation_request_id, model, modelrush_region, data. Preserve returned request or generation identifiers. Generated outputs and their Provider file references are removed from the ModelRush database 24 hours after request completion; download anything you need to keep.

Invalid inputs return a 4xx response with a structured error. A 403 with adult_attestation_required, portrait_rights_attestation_required, or person_rights_confirmation_required must be resolved by the account user and must never be retried automatically. Retry 429 according to Retry-After; retry 5xx failures only with a bounded backoff policy.

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 returns public prices without authentication; with a valid Bearer API key, it returns the prices applicable to that account.

ModelRush 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.