# Gemini Omni Flash API on Wizzx - Model ID: `gemini-omni-flash` (Google Gemini Omni Flash) - Submit: `POST https://api.wizzx.ai/api/v1/task/submit/gemini-omni-flash` - Status: `GET https://api.wizzx.ai/api/v1/task/{task_id}` - Idempotency: optional `Idempotency-Key: ` header on submit - Auth: header `Authorization: Bearer $WIZZX_API_KEY` (server-side only) - Price: from $0.481/request, billed in credits; failed tasks are refunded - Page: https://wizzx.ai/model/gemini-omni-flash - JSON Schema: https://wizzx.ai/api/models/gemini-omni-flash/schema - API reference: https://docs.wizzx.ai/api-reference/endpoint/submit-gemini-omni-flash ## Flow 1. POST the JSON body to the submit URL. The response contains `data.task_id`. 2. Poll `GET /api/v1/task/{task_id}` until `data.status` is `SUCCEEDED`, then read the output URLs from `data.result_urls`. 3. Stop on `FAILED` or `REVIEW_REQUIRED`. Do not resubmit automatically. ## Parameters | Field | Type | Required | Default | Allowed | Description | |---|---|---|---|---|---| | `prompt` | string | yes | | | Describe the scene, subject, action, camera, and sound you want. | | `type` | string | no | text-to-video | text-to-video · image-to-video · reference-to-video | | | `image_urls` | url[] ≤ 3 | no | | | Image to video: exactly 1 image (first frame). Reference to video: 1 or 3 images. Reference images are not charged. | | `resolution` | string | no | 720p | 720p · 1080p · 4k | Resolution and duration select a fixed per-video price. | | `duration` | integer | no | 6 | 4 · 6 · 8 · 10 | Choose 4, 6, 8, or 10 seconds. | | `aspect_ratio` | string | no | 16:9 | 16:9 · 9:16 | | ## Example body ```json { "type": "text-to-video", "resolution": "720p", "duration": 6, "aspect_ratio": "16:9", "prompt": "A slow aerial push-in over a coastal cliff road at golden hour, cinematic motion" } ```