Starts a generation process and charges team credits. V1 types: image-generation, video-generation, image-upscale, video-upscale. The model must match the type (see GET /models). Always send an Idempotency-Key: retries with the same key and body return the original process instead of double-charging; the same key with a different body returns idempotency_conflict. input is validated per process type AND against the model's published capabilities (aspectRatios, resolutions, videoLengths from GET /models) — unsupported values are rejected with invalid_request, never silently coerced. Internal fields (batchId, filteringId, agent context) are ignored. metadata (flat string/number/boolean/null values, max 16 keys) is echoed back on reads. Optional webhookUrl receives a one-shot completion/failure notification.