{"model":{"id":"vision-next","name":"Vision Next","description":"Next-generation vision model. Supports both auto-captioning and visual Q&A via task_type.","tasks":["caption","vqa"],"credits_per_call":2,"input_fields":{"image_url":"string (required)","task_type":"\"caption\" | \"query\" (optional — defaults to \"caption\" with no prompt, \"query\" when prompt is provided)","prompt":"string (required when task_type is \"query\")"},"output_fields":{"result.text":"string"},"api_gross_margin_percent":20,"schema_url":"/api/v1/vision?model_id=vision-next","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","$id":"https://www.artemotion.ai/api/v1/vision?model_id=vision-next","title":"Vision Next request","type":"object","properties":{"model_id":{"type":"string","const":"vision-next"},"webhook_url":{"type":"string","format":"uri","maxLength":2048},"webhook_secret":{"type":"string","maxLength":512},"image_url":{"type":"string","format":"uri"},"task_type":{"type":"string","enum":["caption","query"]},"prompt":{"type":"string"},"question":{"type":"string"}},"required":["model_id","image_url"],"additionalProperties":false}},"version":"1","rate_limit":"20 req/min"}