Gemini Omni Flash

Parameters below were verified against the live model directory on November 5, 2026. Check the model directory for current schema, availability, and prices.

Overview

Gemini Omni Flash Text-to-Video is a text-to-video model developed by Google DeepMind. Unveiled at Google I/O on May 19, 2026, it entered public preview on June 30, 2026, and officially opened its API in August 2026. As the first model in the Gemini Omni series, it combines Gemini’s reasoning capabilities with Veo video generation and image generation technologies, supporting direct generation of high-quality 24 FPS dynamic videos with audio from text prompts. Gemini Omni Flash is the first model in Google DeepMind’s Gemini Omni series, positioned as a unified multimodal generation model capable of “any input → any output.” Built on a Transformer-based architecture with native multimodal support for text, image, audio, and video inputs, it eliminates the need for cascading multiple independent models.

The full model guide, live parameter schema, and playground for every model ID are available in the HiPix model directory.

Model IDs

Model ID	Mode	Notes
`atlas/gemini-omni-flash/image-to-video`	Image-to-Video
`atlas/gemini-omni-flash/text-to-video`	Text-to-Video

Parameters

Requests are submitted to POST /v1/videos (video) or POST /v1/images/generations / POST /v1/images/edits (image). Fields marked metadata.* travel inside the metadata object.

`atlas/gemini-omni-flash/image-to-video`

API field	Type	Required	Values / limit
`prompt`	string	Yes	—
`metadata.image`	array	Yes	up to 1; ≤10 MB each; images
`metadata.resolution`	enum	Yes	`720p`; default `720p`
`metadata.ratio`	enum	Yes	`9:16`, `16:9`; default `9:16`
`seconds`	number	Yes	4–10 (integer); default 5

`atlas/gemini-omni-flash/text-to-video`

API field	Type	Required	Values / limit
`prompt`	string	Yes	—
`metadata.resolution`	enum	Yes	`720p`; default `720p`
`metadata.ratio`	enum	Yes	`9:16`, `16:9`; default `9:16`
`seconds`	number	Yes	4–10 (integer); default 5

Example

A minimal request for atlas/gemini-omni-flash/text-to-video:

curl -X POST https://api.apimart.cc/v1/videos \
  -H "Authorization: Bearer $HIPIX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "atlas/gemini-omni-flash/text-to-video", "prompt": "A kitten running through a sunlit garden", "seconds": 5, "metadata": {"resolution": "720p", "ratio": "9:16"}}'

Poll the task with GET /v1/videos/{task_id} until status is completed or failed.

Limits, availability, and pricing

Submit only the input types listed for the exact model ID; unsupported inputs are rejected or removed on HiPix.
See Submit a Video Task or the model directory for the full request contract, and Pricing & Billing for how charges are settled.
Prices and availability are shown per model ID in the model directory.