Gemini Omni Flash Extend
Gemini Omni Flash Extend adds 3 to 10 seconds after an existing clip. The model reads the last 10 seconds of the source, so the motion, the camera and the sound continue across the join. The result is the source followed by the new footage, in one clip.
video · model gemini-omni-flash-extend · catalog model-catalog@2026-10-06.v5 · pricing customer-pricing@2026-11-05.v15.Endpoint
POST https://api.roasos.com/v1/video/gemini-omni-flash-extendSend your API key as a bearer token. The key needs the scope api:write. Every paid request also needs an Idempotency-Key header.
The envelope fields quote_only, quote_id, webhook_url and wait_timeout_seconds behave the same on each model endpoint. Refer to Jobs and Quotes and credits.
Good at
Grow a take past its first render without a visible cut: a talking head that keeps speaking, a camera move that keeps going, a product reveal after a UGC clip. Send video_url (1 to 60 seconds, up to 100 MiB, MP4) and prompt. duration_seconds sets the new footage (3 to 10). The source sets the framing, so there is no aspect ratio. Sound is always generated. You cannot send an audio file. The source does not have to be a Gemini clip.
Pricing
The unit is one clip. Pricing key: gemini-omni-flash-extend.
| Request | Credits |
|---|---|
3s_720p | 3 |
7s_720p | 7 |
10s_720p | 10 |
The credits come from the roasOS pricing table. No other field changes the price. To get the exact price of your request, send it with quote_only: true first.
Modes
edit
Provider endpoints: google/gemini-omni-flash/v1.2/extend.
Request fields
| Field | Type | Required | Default | Rule |
|---|---|---|---|---|
duration_seconds | integer enum | no | 8 | 3, 4, 5, 6, 7, 8, 9, 10 |
prompt | string | yes | — | ≥ 1 character; ≤ 10,000 characters |
quote_id | string | no | — | UUID |
quote_only | boolean | no | false | — |
resolution | enum | no | 720p | 360p, 720p, 1080p, 4k |
video_url | string | yes | — | https URL; ≤ 4,096 characters |
wait_timeout_seconds | integer | no | 0 | 0–60 |
webhook_url | string | no | — | https URL; ≤ 4,096 characters |
The schema is strict. A field that is not in this table gets 400 unsupported_option. The field names are the roasOS role names. One role has one name in every family.
Media
This endpoint accepts these media roles:
video_url— the source video
Every other role is refused: avatar_id, elements, product_id, product_images, references, reference_images, image_url, end_image_url, scene_id, scene_image, video_urls, audio_urls, audio_url, voice_id. A refused role gets 400 unsupported_option.
https://cdn.roasos.com that your workspace owns. Any other URL gets 400 reference_media_not_workspace_owned. Refer to Reference media and uploads to learn how to put a file there.Prompt
Limit 10,000 characters.
- Describe what happens next, not the source. The model reads the source.
- Keep one action and one camera move, and say where the move ends.
- To continue speech, quote the next line with the speaker and the delivery.
Not exposed
These catalog entries describe omitted inputs, pinned values and source constraints. They do not imply that the provider accepts every listed field.
aspect_ratio— not accepted by this public endpoint.generate_audio— not accepted by this public endpoint.audio— pinned tono audio input exists on the provider; sound is always generated.
Result
The result kind is video. Always present: url.
{
"data": {
"id": "gen_…",
"kind": "video",
"model": "gemini-omni-flash-extend",
"status": "completed",
"result": {
"url": "https://cdn.roasos.com/workspaces/ws_01/result"
}
}
}The files are immutable objects on https://cdn.roasos.com. A result URL is a valid media input for your next request.
Example
The three steps are always the same: quote, run, poll.
# 1. Quote. Nothing is spent.
curl -X POST https://api.roasos.com/v1/video/gemini-omni-flash-extend \
-H "Authorization: Bearer roasos_sk_live_..." \
-H "Idempotency-Key: 0f1c9e2a-gemini-omni-flash-extend-0001" \
-H "Content-Type: application/json" \
-d '{"quote_only":true,"prompt":"A woman holds the bottle at eye level in a bright kitchen, morning light, static camera.","video_url":"https://cdn.roasos.com/workspaces/ws_01/uploads/video_url.mp4"}'
# 200 { "data": { "kind": "quote", "quote_id": "q_7Hk...", "credits": 3, "expires_at": "...",
# "confirmation": { "model": "gemini-omni-flash-extend", "example": "3s_720p" } } }
# 2. Run. Same body, same Idempotency-Key, quote_id in place of quote_only.
curl -X POST https://api.roasos.com/v1/video/gemini-omni-flash-extend \
-H "Authorization: Bearer roasos_sk_live_..." \
-H "Idempotency-Key: 0f1c9e2a-gemini-omni-flash-extend-0001" \
-H "Content-Type: application/json" \
-d '{"quote_id":"q_7Hk...","prompt":"A woman holds the bottle at eye level in a bright kitchen, morning light, static camera.","video_url":"https://cdn.roasos.com/workspaces/ws_01/uploads/video_url.mp4"}'
# 201 { "data": { "id": "gen_...", "status": "queued", "credits_reserved": 3 } }
# 3. Poll, then read the result.
curl https://api.roasos.com/v1/jobs/gen_.../status -H "Authorization: Bearer roasos_sk_live_..."
curl https://api.roasos.com/v1/jobs/gen_.../result -H "Authorization: Bearer roasos_sk_live_..."The deprecated path
POST /v1/generations still reaches this model for one minor version. It is deprecated. This is how it maps:
POST /v1/video/gemini-omni-flash-extend with video_url, prompt, duration_seconds (3-10, default 8) and resolution (360p|720p|1080p|4k, default 720p). The agent extendVideo tool uses this lane for Gemini clips.
See also
llms.txtfor this model — the same facts as one plain-text file for an agent.GET https://api.roasos.com/v1/catalog/gemini-omni-flash-extend— the machine-readable form: enums, defaults, limits and prices. Refer to the API reference.- Jobs — how to poll a job and read its result.
- Provider endpoints:
google/gemini-omni-flash/v1.2/extend.
Gemini Omni Flash
Gemini Omni Flash 1.2 makes video with synchronized audio at 360p to 4K, 3 to 15 seconds long, from text, a first frame (with an optional last frame), or a reference set: up to ten images bound with `<IMAGE_REF_n>` tags plus up to three clips of at most 15 seconds bound with `<VIDEO_REF_n>` tags. It is best at coherent physics, on-screen text and literal camera direction.
MiniMax H3 Max
MiniMax H3 Max makes video with sound from text, from one first frame, or from reference media. It renders at 480p, 768p or 1080p, in any whole length from 5 to 15 seconds. It follows the prompt closely and it is one of the most affordable premium lanes.