Video models
Gemini Omni 1.1 Flash
Google's newest multimodal video model — text, images, video and audio all in context, with a native 360p draft tier at half price and 4K delivery from the same request.
| modelId | gemini-omni-1-1-flash, gemini-omni-1-1-flash-edit |
| Modality | video |
| Pricing | See this model on the Pricing page for the current per-call price (with your markup). |
Operations
| Operation | modelId | Endpoint | Required input |
|---|---|---|---|
| Generate | gemini-omni-1-1-flash | POST /api/v1/generate | prompt |
| Video Edit | gemini-omni-1-1-flash-edit | POST /api/v1/generate | prompt, reference_video_urls |
| Poll task | — | GET /api/v1/task/{id}?model=gemini-omni-1-1-flash | — |
Generate — gemini-omni-1-1-flash
| Field | Type | Required | Values / example |
|---|---|---|---|
| prompt | string | Yes | What to generate. Use @Image1, @Image2 … to point at a specific reference image. (example: A paper boat drifts down a rainy street gutter, cinematic close-up, shallow depth of field) |
| reference_image_urls | string[] | No | Up to 7 references the video should follow. Cannot be combined with start/end frames. (image URL) |
| start_image_url | string | No | First frame of the clip. Cannot be combined with reference images. (image URL) |
| end_image_url | string | No | Last frame. Requires a start frame — the clip animates from the first to the last. (image URL) |
| voice | string | No | Google Flow voice preset for the spoken audio. Requires at least one reference image. (options: | achernar | achird | algenib | algieba | alnilam | aoede | autonoe | callirrhoe | charon | despina | enceladus | erinome | fenrir | gacrux | iapetus | kore | laomedeia | leda | orus | puck | pulcherrima | rasalgethi | sadachbia | sadaltager | schedar | sulafat | umbriel | vindemiatrix | zephyr | zubenelgenubi) (default: ) |
| duration | string | No | Clip length in seconds. Longer clips cost more. (options: 4 | 6 | 8 | 10) (default: 4) |
| aspect_ratio | string | No | Output orientation. (options: 16:9 | 9:16) (default: 16:9) |
| resolution | string | No | Options: 360p | 720p | 1080p | 4k (default: 720p) |
| seed | number | No | Reuse a seed to repeat a result closely. |
| allow_audio_filtered | boolean | No | When on, the video is delivered without audio instead of failing if the audio track is filtered. (true/false) (default: false) |
| nsfw_check | boolean | No | Check uploaded media for NSFW content. (true/false) (default: true) |
bash
curl -X POST https://you.bot/api/v1/generate \
-H "Authorization: Bearer $YOUBOT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"modelId":"gemini-omni-1-1-flash","input":{"prompt":"A paper boat drifts down a rainy street gutter, cinematic close-up, shallow depth of field","reference_image_urls":["https://you.bot/examples/grok-imagine-text-to-image.jpg"],"start_image_url":"https://you.bot/examples/grok-imagine-text-to-image.jpg","end_image_url":"https://you.bot/examples/grok-imagine-text-to-image.jpg","voice":"","duration":"4","aspect_ratio":"16:9","resolution":"720p","seed":1,"allow_audio_filtered":false,"nsfw_check":true}}'Video Edit — gemini-omni-1-1-flash-edit
| Field | Type | Required | Values / example |
|---|---|---|---|
| prompt | string | Yes | What to change. Use @Video1 for the source clip and @Image1, @Image2 … for reference images. (example: Make @Video1 look like it was filmed underwater) |
| reference_video_urls | string[] | Yes | The clip to edit. Exactly one video, up to 30 seconds. The edited result is about 10 seconds long — use the frame range below to choose which part of a longer clip to edit. (image URL) |
| reference_image_urls | string[] | No | Extra images the edit should follow. They count toward the 7-reference total with the source video. (image URL) |
| resolution | string | No | Options: 360p | 720p | 1080p | 4k (default: 720p) |
| start_frame | number | No | First source frame index included in the edit. Leave empty to start at the beginning. |
| end_frame | number | No | Last source frame index included in the edit. Leave empty to run to the end. |
| seed | number | No | Reuse a seed to repeat a result closely. |
| allow_audio_filtered | boolean | No | When on, the video is delivered without audio instead of failing if the audio track is filtered. (true/false) (default: false) |
| nsfw_check | boolean | No | Check uploaded media for NSFW content. (true/false) (default: true) |
bash
curl -X POST https://you.bot/api/v1/generate \
-H "Authorization: Bearer $YOUBOT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"modelId":"gemini-omni-1-1-flash-edit","input":{"prompt":"Make @Video1 look like it was filmed underwater","reference_video_urls":["https://you.bot/examples/gemini-omni.mp4"],"reference_image_urls":["https://you.bot/examples/grok-imagine-text-to-image.jpg"],"resolution":"720p","start_frame":1,"end_frame":1,"seed":1,"allow_audio_filtered":false,"nsfw_check":true}}'