> ## Documentation Index > Fetch the complete documentation index at: https://docs.apimart.ai/llms.txt > Use this file to discover all available pages before exploring further. # gemini-omni-1.2-flash-ext Video Generation > - gemini-omni-1.2-flash-ext unified video generation model - Supports Text-to-Video, first-frame Image-to-Video, first-and-last-frame video, multi-image reference, and video editing and extension - Supports 360p/720p/1080p/4k resolution and 3–15 second duration, billed per second - Asynchronous task API. Submit a task first, then query the result by task ID ```bash cURL theme={null} curl --request POST \ --url https://api.apimart.ai/v1/videos/generations \ --header 'Authorization: Bearer ' \ --header 'Content-Type: application/json' \ --data '{ "model": "gemini-omni-1.2-flash-ext", "prompt": "Aerial shot over a misty mountain lake at sunrise.", "duration": 10, "resolution": "1080p", "aspect_ratio": "9:16" }' ``` ```python Python theme={null} import requests url = "https://api.apimart.ai/v1/videos/generations" payload = { "model": "gemini-omni-1.2-flash-ext", "prompt": "Aerial shot over a misty mountain lake at sunrise.", "duration": 10, "resolution": "1080p", "aspect_ratio": "9:16" } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript JavaScript theme={null} const url = "https://api.apimart.ai/v1/videos/generations"; const payload = { model: "gemini-omni-1.2-flash-ext", prompt: "Aerial shot over a misty mountain lake at sunrise.", duration: 10, resolution: "1080p", aspect_ratio: "9:16" }; const headers = { "Authorization": "Bearer ", "Content-Type": "application/json" }; fetch(url, { method: "POST", headers: headers, body: JSON.stringify(payload) }) .then(response => response.json()) .then(data => console.log(data)) .catch(error => console.error("Error:", error)); ``` ```go Go theme={null} package main import ( "bytes" "encoding/json" "fmt" "io/ioutil" "net/http" ) func main() { url := "https://api.apimart.ai/v1/videos/generations" payload := map[string]interface{}{ "model": "gemini-omni-1.2-flash-ext", "prompt": "Aerial shot over a misty mountain lake at sunrise.", "duration": 10, "resolution": "1080p", "aspect_ratio": "9:16", } jsonData, _ := json.Marshal(payload) req, _ := http.NewRequest("POST", url, bytes.NewBuffer(jsonData)) req.Header.Set("Authorization", "Bearer ") req.Header.Set("Content-Type", "application/json") client := &http.Client{} resp, err := client.Do(req) if err != nil { panic(err) } defer resp.Body.Close() body, _ := ioutil.ReadAll(resp.Body) fmt.Println(string(body)) } ``` ```json 200 theme={null} { "code": 200, "data": [ { "status": "submitted", "task_id": "task_01KS1H7ZYSJWH1N779S2FSHTKA" } ] } ``` ```json 400 theme={null} { "error": { "code": 400, "message": "Invalid request parameters", "type": "invalid_request_error" } } ``` ```json 401 theme={null} { "error": { "code": 401, "message": "Authentication failed. Please check your API key", "type": "authentication_error" } } ``` ```json 402 theme={null} { "error": { "code": 402, "message": "Insufficient account balance. Please recharge and try again", "type": "payment_required" } } ``` ```json 429 theme={null} { "error": { "code": 429, "message": "Too many requests. Please try again later", "type": "rate_limit_error" } } ``` ## Authentication **Authorization** `string` *required* All requests require Bearer Token authentication. Get an API key: Visit the [API Key management page](https://apimart.ai/keys) to get your API key. Add the following header when making requests: ``` Authorization: Bearer YOUR_API_KEY ``` ## Request Parameters **model** `string` *required* Video generation model name. Fixed as `gemini-omni-1.2-flash-ext`. **prompt** `string` *required* Video description or editing instruction. It cannot be empty after leading and trailing whitespace is trimmed. For Text-to-Video, describe the scene, characters, actions, camera, and sound; with images or videos, describe the motion, style, or changes you want. Example: `"Aerial shot over a misty mountain lake at sunrise."` > [!WARNING] > > `prompt` is required in every mode, including first frame, multi-image reference, editing, and extension. A 400 error is returned if it is missing. **duration** `integer` (default: 10) Video duration in seconds. Must be an integer. * Text-to-Video / first frame / multi-image reference: output duration, `3`–`15` * First and last frames: output duration, `3`–`10` * Extension (`extend`): duration of the **newly added segment**, `3`–`10` * Editing (`edit`): must not be passed; the output duration follows the source video The alias `seconds` is also accepted. If both are passed, they must be equal. > [!WARNING] > > Passing `duration` in editing mode returns a `video edit does not accept duration` error. **resolution** `string` (default: 720p) Video resolution, case-insensitive. It determines the per-second price. Allowed values: * `360p` * `720p` * `1080p` * `4k` (`2160p` is also accepted) > [!WARNING] > > Any other resolution returns a 400 error. **aspect\_ratio** `string` (default: 16:9) Only `16:9` (landscape, default) and `9:16` (portrait) are supported; other values return a 400 error. **omni\_reference\_task\_type** `string` Task type, specifying how the input material is used. Allowed values: * `edit` - Edit a video. Use with `video_urls` or `extend_from_task_id` * `extend` - Extend a video by appending new content at the end. Use with `video_urls` or `extend_from_task_id` * `reference` - Multi-image reference. Use with `image_urls` * `text_to_video` / `image_to_video` / `reference_to_video` - Text-to-Video / first frame / reference images * `auto` - Detected from the input; treated as `edit` when a video is provided Optional when no video is provided; the mode is detected from the input. > [!WARNING] > > When `video_urls` or `extend_from_task_id` is passed, a task type is required (`omni_reference_task_type`, or the compatible field `generation_type`); omitting it returns a 400 error. Passing `edit` or `extend` explicitly is recommended; `auto` is treated as `edit`. **generation\_type** `string` Compatible field, equivalent to `omni_reference_task_type`. Allowed values: `frame` (same as `image_to_video`), `reference`, `edit`, `extend`. > [!WARNING] > > `generation_type` and `omni_reference_task_type` cannot be passed together. **image\_urls** `array\` Reference image array for multi-image reference (characters, products, styles, etc.). Supports 1–10 images. Only publicly accessible HTTP/HTTPS image URLs are supported. Upload local images first to get a public URL, then pass that URL; Base64 Data URLs are currently not supported and return a 400 error. When only 1 image is passed, how it is used depends on the task type: * `omni_reference_task_type` omitted: used as a reference image * `omni_reference_task_type` is `auto` or `image_to_video`: used as the first frame For first-frame generation, use `first_frame_image` directly instead of relying on the number of images. > [!WARNING] > > `image_urls` cannot be passed together with `first_frame_image` or `last_frame_image`, and images in `image_urls` are never treated as the first frame; images cannot be passed when editing or extending either. **first\_frame\_image** `string` First-frame image. The first frame of the generated video is this image. Only publicly accessible HTTP/HTTPS image URLs are supported; Base64 Data URLs are not supported. Passing it together with `last_frame_image` generates a first-and-last-frame video. **last\_frame\_image** `string` Last-frame image for first-and-last-frame generation; the video transitions from the first frame to this image. Only publicly accessible HTTP/HTTPS image URLs are supported; Base64 Data URLs are not supported. In first-and-last-frame mode: * `duration` supports `3`–`10`; 10 seconds if omitted * `system_prompt` and `negative_prompt` cannot be passed > [!WARNING] > > `last_frame_image` must be passed together with `first_frame_image`; passing only the last frame returns a `last_frame_image requires first_frame_image` error. It cannot be passed together with `image_urls`. **image\_with\_roles** `array\` Image array with roles, an equivalent way to write `first_frame_image` / `last_frame_image` / `image_urls`. **Array item** **url** `string` *required* Publicly accessible HTTP/HTTPS image URL. Base64 Data URLs are not supported. **role** `string` `first_frame` is the first frame and `last_frame` is the last frame (1 image each); any other value or an empty role is treated as a reference image. **video\_urls** `array\` Array of videos to edit or extend. Only 1 video is supported. You can also use the single-value field `video_url` instead; pass only one of them. Only publicly accessible HTTP/HTTPS video URLs are supported. Format: MP4 / MOV / WebM, up to 15 seconds and 64 MB. > [!WARNING] > > When passing `video_urls`, a task type is required. `omni_reference_task_type` set to `edit` or `extend` is recommended (`auto` is treated as `edit`); omitting it returns a 400 error. Passing 2 or more videos returns a 400 error. **extend\_from\_task\_id** `string` A task ID on this platform (`task_01…`). Continue editing or extending one of your previously completed `gemini-omni-1.2-flash-ext` tasks without re-uploading the video. Requirements: * The task belongs to the current account * The task model is `gemini-omni-1.2-flash-ext` * The task status is `completed` * The channel that generated the original task is still available; otherwise 503 `source_channel_unavailable` is returned * The original output is no longer than 15 seconds (applies to both editing and extension); in editing mode, its duration must also be detectable If the channel is unavailable or the original output's duration cannot be detected, download the original output and upload it with `video_urls` instead. If the original output is longer than 15 seconds, trim it to 15 seconds or less before uploading. > [!WARNING] > > `extend_from_task_id` cannot be passed together with `video_urls`, and a task type is required. `omni_reference_task_type` set to `edit` or `extend` is recommended (`auto` is treated as `edit`). **negative\_prompt** `string` Content you do not want to appear in the video. Example: `"people, cars, color"` > [!WARNING] > > `negative_prompt` cannot be passed in first-and-last-frame mode. **system\_prompt** `string` System instruction, such as fixing the visual style or forbidding on-screen text. Must be a string. Example: `"Render as a black-and-white silent film."` > [!WARNING] > > `system_prompt` cannot be passed in first-and-last-frame mode. ## Response **code** `integer` Response status code. Successful requests return `200`. **data** `array` Returned task array. **Array item** **status** `string` Initial task status. It is `submitted` after successful submission. **task\_id** `string` Unique task ID for querying task status and result. ## Query Task Result Video generation is asynchronous. After submission, a `task_id` is returned. Use the [Get Task Status](https://docs.apimart.ai/en/api-reference/tasks/status.md) API to query generation progress and results. ```bash cURL theme={null} curl --request GET \ --url https://api.apimart.ai/v1/tasks/task_01KS1H7ZYSJWH1N779S2FSHTKA \ --header 'Authorization: Bearer ' ``` Poll every 5-10 seconds and set the client timeout to at least 10 minutes. Reference generation times (including queueing): about 46 seconds for a 15-second 360p video, about 99 seconds for 15-second 1080p, and about 4-5 minutes for 15-second 4k. Progress may stay at 10% for a long time until the task completes. ### Successful Result Example ```json theme={null} { "code": 200, "data": { "id": "task_01KS1H7ZYSJWH1N779S2FSHTKA", "status": "completed", "progress": 100, "actual_time": 99, "cost": 0.695, "result": { "videos": [ { "url": ["https://cdn.example.com/videos/abc.mp4"] } ] } } } ``` The video URL is `data.result.videos[0].url[0]`. `data.actual_time` is the task processing time in seconds, not the video length. The output is MP4 (H.264, 24fps) with an AAC audio track and an invisible SynthID watermark; 4k outputs occasionally have no audio track. ### Failed Result Example ```json theme={null} { "code": 200, "data": { "id": "task_01KS1H7ZYSJWH1N779S2FSHTKA", "status": "failed", "progress": 100, "cost": 0, "error": { "code": "task_failed", "message": "content_rejected", "type": "task_failed" } } } ``` Failed tasks are fully refunded. ## Billing Billed per second: cost = per-second price of the selected resolution × billed seconds. All modes are billed at the requested resolution tier. See the [pricing page](https://apimart.ai/pricing) for actual prices. | Mode | Billed seconds | | - | - | | Text-to-Video / first frame / multi-image reference | `duration`; 10 seconds if omitted | | First and last frames | `duration` (up to 10 seconds); 10 seconds if omitted | | Editing | Source video duration (0.15 seconds of container tolerance is subtracted, then rounded up, minimum 1 second; e.g. 8.019 seconds bills as 8 seconds, 8.3 seconds as 9 seconds) | | Extension | Added seconds `duration`; 10 seconds if omitted. The original video is not billed | ## Use Cases ### Scenario 1: Text-to-Video ```json theme={null} { "model": "gemini-omni-1.2-flash-ext", "prompt": "Aerial shot over a misty mountain lake at sunrise.", "duration": 15, "resolution": "1080p", "aspect_ratio": "9:16" } ``` ### Scenario 2: First-Frame Video ```json theme={null} { "model": "gemini-omni-1.2-flash-ext", "prompt": "The camera slowly pushes in.", "duration": 6, "aspect_ratio": "9:16", "first_frame_image": "https://example.com/start.jpg" } ``` ### Scenario 3: First-and-Last-Frame Video ```json theme={null} { "model": "gemini-omni-1.2-flash-ext", "prompt": "The flower bud slowly opens into full bloom.", "duration": 8, "aspect_ratio": "16:9", "first_frame_image": "https://example.com/bud.jpg", "last_frame_image": "https://example.com/bloom.jpg" } ``` In first-and-last-frame mode, `duration` supports 3–10 seconds (10 seconds if omitted), and `system_prompt` / `negative_prompt` cannot be passed. ### Scenario 4: Multi-Image Reference ```json theme={null} { "model": "gemini-omni-1.2-flash-ext", "prompt": "The cat bats at the ball of yarn.", "duration": 8, "image_urls": [ "https://example.com/cat.png", "https://example.com/yarn.png" ] } ``` ### Scenario 5: Video Editing ```json theme={null} { "model": "gemini-omni-1.2-flash-ext", "prompt": "Make the violin invisible. Keep everything else the same.", "video_urls": ["https://example.com/clip.mp4"], "omni_reference_task_type": "edit" } ``` Do not pass `duration` when editing; the output duration follows the source video. ### Scenario 6: Video Extension ```json theme={null} { "model": "gemini-omni-1.2-flash-ext", "prompt": "Continue the scene: the dancer bows.", "video_urls": ["https://example.com/clip.mp4"], "omni_reference_task_type": "extend", "duration": 4 } ``` ### Scenario 7: Extend an Existing Task ```json theme={null} { "model": "gemini-omni-1.2-flash-ext", "prompt": "Extend this video: the camera pans across the mountains.", "extend_from_task_id": "task_01KS1H7ZYSJWH1N779S2FSHTKA", "omni_reference_task_type": "extend", "duration": 6 } ``` ### Scenario 8: System Prompt and Negative Prompt ```json theme={null} { "model": "gemini-omni-1.2-flash-ext", "prompt": "A busy city street at noon.", "system_prompt": "Render as a black-and-white silent film.", "negative_prompt": "people, cars, color", "duration": 6 } ``` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.