Video

Gemini Omni 1.2 Flash API

Gemini Omni 1.2 Flash API (gemini-omni-1.2-flash) is Google's multimodal video model for text-to-video, image-to-video, first/last-frame interpolation, video editing and extension. Set duration from 3 to 15 seconds, get audio in every clip, and pay per second by resolution on APIMart. The Ext channel gemini-omni-1.2-flash-ext covers the same core modes, including first and last frames, with a fixed price per second.

3–15s with audioEdit & extend video360p to 4K

Get API Key API Docs

Service Highlights

Official Discounts
Pay-as-you-go
Fast & Low Latency

Input

Model

Prompt

Aspect Ratio

Resolution

Duration

10s

Task

First / last frame

First Frame

Last Frame

Reference Image

Source video

Continue from task ID (optional)

Output

Video link valid for 72 hours

Gemini Omni 1.2 Flash API Pricing

Transparent pricing with no hidden fees. Pay only for what you use.

Variant	Tier	GoldCurrent price	Platinum	Diamond	Official	Your savings
`gemini-omni-1.2-flash`	360P	0.2Credits(~$0.02)/sec	0.19Credits(~$0.019)/sec	0.18Credits(~$0.018)/sec	0.25Credits(~$0.025)/sec	20%
	720P	0.6Credits(~$0.06)/sec	0.57Credits(~$0.057)/sec	0.54Credits(~$0.054)/sec	0.75Credits(~$0.075)/sec	20%
	1080P	0.904Credits(~$0.0904)/sec	0.8588Credits(~$0.0859)/sec	0.8136Credits(~$0.0814)/sec	1.13Credits(~$0.113)/sec	20%
	4K	1.808Credits(~$0.1808)/sec	1.7176Credits(~$0.1718)/sec	1.6272Credits(~$0.1627)/sec	2.26Credits(~$0.226)/sec	20%
`gemini-omni-1.2-flash-ext`	360P	0.16Credits(~$0.016)/sec	0.152Credits(~$0.0152)/sec	0.144Credits(~$0.0144)/sec	0.2Credits(~$0.02)/sec	20%
	720P	0.24Credits(~$0.024)/sec	0.228Credits(~$0.0228)/sec	0.216Credits(~$0.0216)/sec	0.3Credits(~$0.03)/sec	20%
	1080P	0.24Credits(~$0.024)/sec	0.228Credits(~$0.0228)/sec	0.216Credits(~$0.0216)/sec	0.3Credits(~$0.03)/sec	20%
	4K	0.56Credits(~$0.056)/sec	0.532Credits(~$0.0532)/sec	0.504Credits(~$0.0504)/sec	0.7Credits(~$0.07)/sec	20%

* Actual costs are subject to final output.

gemini-omni-1.2-flash

Pricing Details

Transparent pricing with no hidden fees. Pay only for what you use.

Token Pricing

Per 1M tokens

Rate	GoldCurrent price	Platinum	Diamond
Input	12~$1.2	11.4~$1.14	10.8~$1.08
Output	96~$9.6	91.2~$9.12	86.4~$8.64

Generate and Edit Videos with the Gemini Omni 1.2 Flash API

Send a prompt, images, first and last frames, or one source video to a single model ID. Gemini Omni 1.2 Flash returns 24 fps clips with dialogue, music or sound effects, from 360p up to upscaled 4K, and you choose the length with the duration parameter. The Ext channel (gemini-omni-1.2-flash-ext) accepts the same inputs, including first and last frames, and bills each second at a fixed rate.

Get API key

Key Features of the Gemini Omni 1.2 Flash API

One endpoint covers generation, references, editing and extension.

Text to Video up to 15 Seconds with Gemini Omni 1.2 Flash

Set duration to any whole number from 3 to 15 seconds; it defaults to 10. Unlike Gemini Omni 1.1 Flash, the requested length is applied to the output.

Image to Video and First/Last Frames in the Gemini-Omni-1.2-Flash Model

Pass first_frame_image to start from your image, or add last_frame_image to transition between two frames in up to 10 seconds. Both images should match aspect_ratio. gemini-omni-1.2-flash-ext also accepts both frames for 3–10 seconds, without negative_prompt or system_prompt.

Multi-Subject References with gemini-omni-1-2-flash

Send image_urls so several subjects interact in one scene. Up to 10 images including frames; for characters, use at most 2 characters with up to 3 images each. On gemini-omni-1.2-flash-ext, send up to 10 reference images without a first frame.

Video Editing and Extension via the Gemini Omni 1.2 Flash API

Edit one clip of up to 15 seconds through video_urls, or reuse your own task with extend_from_task_id. Set omni_reference_task_type to extend to add up to 10 more seconds. On gemini-omni-1.2-flash-ext, always set omni_reference_task_type to edit or extend when you send a video.

Native Audio in Every Gemini Omni 1.2 Clip

Each output includes generated sound. Describe dialogue, music or sound effects in the prompt; audio input is not supported.

360p to 4K in 16:9 or 9:16 with gemini-omni-1.2-flash

Choose 360p, 720p, 1080p or 4k; 1080p and 4k are upscaled. Output is 24 fps in 16:9 landscape or 9:16 portrait, and resolution sets the price tier.

Google Gemini Omni 1.2 Flash Pricing: Pay per Second

APIMart bills each second of output at the rate for your resolution; the live price table on this page shows current rates. Google lists output video at $12 per 1M tokens, about 31% below Gemini Omni 1.1 Flash, and failed tasks are not charged. The official model settles by token usage, while gemini-omni-1.2-flash-ext charges a fixed price per second: per-second rate × billed seconds.

One Async Endpoint for Gemini Omni Flash 1.2

Submit to POST /v1/videos/generations with model gemini-omni-1.2-flash, then poll GET /v1/tasks/{task_id}. A completed task returns the video URL and the final cost, and parameter errors fail at once without charge. The Ext channel uses the same endpoints with model gemini-omni-1.2-flash-ext.

What You Can Build with the Gemini Omni 1.2 Flash API

Match each workflow to the input it needs.

Product Videos from Reference Images

Combine product and scene images in image_urls, then describe the camera move and lighting for a reveal or close-up up to 15 seconds long.

Vertical Clips for Social Feeds

Set aspect_ratio to 9:16 for portrait videos with built-in audio, and use 360p or 720p drafts before rendering a final version in 1080p or 4k.

Storyboard Transitions

Turn two storyboard frames into a smooth shot: send first_frame_image and last_frame_image with a short motion prompt and a duration of up to 10 seconds. Works on gemini-omni-1.2-flash and gemini-omni-1.2-flash-ext; on Ext, leave out negative_prompt and system_prompt.

Character Scenes with Consistent Subjects

Provide up to 3 reference images for each of up to 2 characters, and describe how they act and interact in the prompt.

Post-Production Edits

Change an object, style or lighting in an existing clip. Keep the instruction short and add "Keep everything else the same" to protect the rest of the shot.

Scene Continuation

Continue one of your own generations with extend_from_task_id and omni_reference_task_type set to extend. The new segment is added at the end and billed only for the added seconds.

How to Get a Gemini Omni 1.2 Flash API Key and Start Building

Create a key, test a request in the playground, then integrate the asynchronous API.

Create a Gemini Omni 1.2 Flash API Key

→

Configure a gemini-omni-1.2-flash Request

Choose the prompt, duration, resolution, aspect ratio and any frames, images or source video, then check the estimated price on RUN.

→

Integrate the Gemini Omni 1.2 Flash API

Submit to POST /v1/videos/generations, then poll GET /v1/tasks/{task_id} every 5–10 seconds until the task is completed or failed.

Get API key

Gemini Omni 1.2 Flash API Examples: Text to Video and First/Last Frames

Submit an asynchronous video task, then query the task ID until the video is ready.

1
Authenticate Your Requests
Save your APIMart API key in the APIMART_API_KEY environment variable and send it as Authorization: Bearer <key> with every request.
2
Submit a gemini-omni-1.2-flash Task
POST model, prompt and the parameters you need to /v1/videos/generations and read data[0].task_id from the response. The example.com URLs are placeholders; replace them with your own public HTTP(S) URLs.
3
Retrieve the Video Result
Poll GET /v1/tasks/{task_id} until status is completed, then read data.result.videos[0].url[0] and the final charge in cost. If status is failed, check error.message. APIMart keeps results for 72 hours, so download the videos you want to keep.
See the APIMart API documentation for authentication and task status details.

POST /v1/videos/generations

curl -X POST https://api.apimart.ai/v1/videos/generations \
  -H "Authorization: Bearer $APIMART_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-omni-1.2-flash",
    "prompt": "Aerial shot over a misty mountain lake at sunrise, birds flying, slow forward camera move, soft wind and distant birdsong.",
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "duration": 15
  }'

import os
import time
import requests

API_BASE = "https://api.apimart.ai"
headers = {"Authorization": f"Bearer {os.environ['APIMART_API_KEY']}"}

# 1. Submit the generation task
payload = {
  "model": "gemini-omni-1.2-flash",
  "prompt": "Aerial shot over a misty mountain lake at sunrise, birds flying, slow forward camera move, soft wind and distant birdsong.",
  "aspect_ratio": "16:9",
  "resolution": "720p",
  "duration": 15
}
resp = requests.post(f"{API_BASE}/v1/videos/generations", headers=headers, json=payload, timeout=60)
resp.raise_for_status()
task_id = resp.json()["data"][0]["task_id"]

# 2. Poll the task until it finishes
for _ in range(200):
    task_resp = requests.get(f"{API_BASE}/v1/tasks/{task_id}", headers=headers, timeout=30)
    task_resp.raise_for_status()
    task = task_resp.json()["data"]
    if task["status"] == "completed":
        print(task["result"]["videos"][0]["url"][0])
        break
    if task["status"] == "failed":
        raise RuntimeError(task.get("error", {}).get("message", "generation failed"))
    time.sleep(10)
else:
    raise TimeoutError(f"task {task_id} did not finish in time; continue GET polling with this task ID")

curl -X POST https://api.apimart.ai/v1/videos/generations \
  -H "Authorization: Bearer $APIMART_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-omni-1.2-flash",
    "prompt": "Smooth transition from the first frame to the last frame, the camera slowly pushes in, keep the subject and lighting consistent.",
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "duration": 8,
    "first_frame_image": "https://example.com/first-frame.jpg",
    "last_frame_image": "https://example.com/last-frame.jpg"
  }'

TASK_ID="task_xxx"  # replace with the task_id returned by the POST request
curl "https://api.apimart.ai/v1/tasks/$TASK_ID" \
  -H "Authorization: Bearer $APIMART_API_KEY"

Gemini Omni 1.2 Flash API Parameters

Parameter	Type	Required	Default	Description
`model`	string	Required	Default: gemini-omni-1.2-flash	Fixed to gemini-omni-1.2-flash. For the Ext channel use gemini-omni-1.2-flash-ext: prompt is required, video inputs need edit or extend, and negative_prompt and system_prompt are available except with first and last frames.
`prompt`	string	Required	Default: —	Scene description for text to video, or the motion, style or edit instruction for image and video inputs. Required in every mode, including image, frame, video and extend_from_task_id requests; omitting it returns HTTP 400.
`duration`	integer	Optional	Default: 10	Output length in whole seconds, 3–15. First/last-frame interpolation allows up to 10. When extending, it sets the length of the added part (up to 10); when editing, it is ignored and the output follows the source video.
`resolution`	string	Optional	Default: 720p	360p, 720p, 1080p or 4k, case-insensitive; 2160p is treated as 4k. 1080p and 4k are upscaled. Sets the price tier.
`aspect_ratio`	string	Optional	Default: 16:9	16:9 landscape or 9:16 portrait. Any other value is treated as 16:9.
`image_urls`	array	Optional	Default: —	Reference images as publicly accessible HTTP(S) URLs. Up to 10 images including first and last frames; one image is used as the opening shot, several act as subject references.
`first_frame_image`	string	Optional	Default: —	First frame. Alone, the video starts from it; with last_frame_image, the model interpolates between the two.
`last_frame_image`	string	Optional	Default: —	Last frame. Must be sent together with first_frame_image.
`image_with_roles`	array	Optional	Default: —	Equivalent object form: [{"url": "...", "role": "first_frame"}, {"url": "...", "role": "last_frame"}]. Other roles are treated as reference images.
`video_urls`	array	Optional	Default: —	One video to edit or extend, up to 15 seconds, as a publicly accessible direct HTTP(S) link.
`omni_reference_task_type`	string	Optional	Default: auto	Task type: auto (default, detected from the inputs), edit, extend or reference (multi-image reference). Video inputs default to edit, so send extend to continue a video. text_to_video, image_to_video and reference_to_video are also accepted.
`extend_from_task_id`	string	Optional	Default: —	ID of one of your earlier generation tasks to continue without uploading the video again. Edits by default; combine with omni_reference_task_type set to extend to continue it.

Gemini Omni API Model Family

Compare Gemini Omni video models on APIMart. One API key calls every version; see each model page for live pricing.

Model	Best for	Resolution	Duration
Gemini Omni 1.2 Flash APIThis page	Latest version: clips up to 15 seconds with audio, references, video editing and extension	360p / 720p / 1080p / 4K	3–15s
Gemini Omni 1.1 Flash API	Up to 10 images, first and last frames, video editing and extension	360p / 720p / 1080p / 4K	3–10s
Gemini Omni 1.1 Flash Ext API	Duration set in the request, priced by resolution and duration (reference video billed per second); text, one image, reference video or three-image fusion	360p / 720p / 1080p / 4K	4 / 6 / 8 / 10s
Gemini Omni Flash Preview API	720p clips from text, up to 16 reference images or one video	720p	3–10s

Gemini Omni 1.2 Flash API FAQ

Duration, inputs, editing, pricing and integration.

What is the Gemini Omni 1.2 Flash API?

It is API access to Google's Gemini Omni 1.2 Flash video model, model ID gemini-omni-1.2-flash. One endpoint handles text to video, image to video, multi-subject references, first/last-frame interpolation, video editing and extension, and every clip includes audio. On APIMart you call it with your APIMart API key and pay per second of output. APIMart also offers gemini-omni-1.2-flash-ext, an Ext channel with a fixed price per second; switch to it above the playground.

What is the Gemini Omni API?

On APIMart, the Gemini Omni API means Google's Gemini Omni video models, called through POST /v1/videos/generations with one API key. Gemini Omni 1.2 Flash (gemini-omni-1.2-flash) is the latest version and creates 3–15 second clips from text, images, first and last frames, or an existing video. The model family table on this page compares the other versions.

Is the Omni Flash API the same as Gemini Omni 1.2 Flash?

Omni Flash is the short name for Google's Gemini Omni Flash line. This page covers Gemini Omni 1.2 Flash; set gemini-omni-1.2-flash in the model field to call this version.

What is the difference between gemini-omni-1.2-flash and gemini-omni-1.2-flash-ext?

They are two model IDs on this page. gemini-omni-1.2-flash is the official channel, billed by token usage, with first and last frames, multi-subject references, editing and extension. gemini-omni-1.2-flash-ext is a separate channel with a fixed price per second for each resolution; it supports text to video, a first frame, first and last frames (3–10 seconds), up to 10 reference images, editing and extension, and adds negative_prompt and system_prompt, which cannot be used with first and last frames. Their pricing fields and parameter rules are not interchangeable.

What changed in Gemini Omni 1.2 Flash compared with 1.1?

The duration parameter now works: outputs run 3–15 seconds instead of roughly 10 seconds every time with 1.1. Google's list price for output video drops from $17.50 to $12 per 1M tokens, about 31% lower. Inputs, resolutions and endpoints are otherwise the same. Gemini Omni 1.1 Flash remains available on its own page.

Gemini Omni 1.2 Flash vs Veo 3.1: what is the difference?

Both are Google video models. Gemini Omni 1.2 Flash creates 3–15 second clips and can edit or extend an existing video through the same endpoint. Google lists gemini-omni-1.2-flash as the replacement for its Veo 3.1 preview models in the Gemini API. If you already use Veo 3.1, compare both on your own prompts before switching.

Which parameters does the Gemini Omni 1.2 Flash API support?

model, prompt, duration, resolution, aspect_ratio, image_urls, first_frame_image, last_frame_image, image_with_roles, video_urls, omni_reference_task_type and extend_from_task_id. prompt is required in every mode, even when you send images, frames or video. System prompts, temperature and a negative-prompt field are not supported; put exclusions in the prompt. These rules apply to gemini-omni-1.2-flash. gemini-omni-1.2-flash-ext always requires a prompt, accepts last_frame_image only with first_frame_image, and supports negative_prompt and system_prompt except in first/last-frame requests.

Which requests does gemini-omni-1.2-flash-ext reject?

Requests are rejected at submission, without creating a task or charging, if they include audio input, seed, GIF output, n other than 1, watermark, width or height, or any other undocumented field, or if they send a last frame without a first frame, or negative_prompt or system_prompt with first and last frames. A prompt is always required, and a source video must be a public MP4, MOV or WebM up to 15 seconds and 64 MB.

How long can Gemini Omni 1.2 Flash videos be?

Set duration to a whole number from 3 to 15 seconds; it defaults to 10. First/last-frame interpolation is limited to 10 seconds. When extending, duration is the length of the added part, up to 10 seconds: a 5-second clip with duration 4 becomes about 9 seconds. When editing, duration is ignored and the output keeps the source length. Output is 24 fps, and a duration outside these limits fails the task with invalid_duration, without charge. On gemini-omni-1.2-flash-ext, sending duration with an edit returns an error, so leave it out.

Can Gemini Omni 1.2 Flash turn images into video?

Yes. A single image in image_urls or first_frame_image becomes the opening shot. Add last_frame_image to interpolate between two frames; sending only the last frame returns invalid_frame_images. Several images in image_urls act as subject references, and you describe how they interact in the prompt. On gemini-omni-1.2-flash-ext, use first_frame_image for the opening shot and add last_frame_image to move between two frames in 3–10 seconds; a last frame cannot be combined with image_urls.

How many reference images can I use?

Up to 10 images in total, counting first and last frames; more returns unsupported_image_count. For character references, use no more than 6 images: up to 2 characters with at most 3 images each. Images must be publicly accessible HTTP(S) URLs; Base64 and data URLs are not supported. On gemini-omni-1.2-flash-ext, up to 10 reference images are allowed and they cannot be combined with first or last frames.

How do video editing and extension work?

Send one clip of up to 15 seconds in video_urls, or reference one of your own tasks with extend_from_task_id. Without omni_reference_task_type, both inputs are edited in place; set omni_reference_task_type to extend to continue from the last frame. Extension adds up to 10 seconds and is billed only for the new seconds. Short instructions ending with "Keep everything else the same" work best. On gemini-omni-1.2-flash-ext, omni_reference_task_type is required whenever you send a video or task ID, and editing is billed for the length of the source video.

Does Gemini Omni 1.2 Flash generate audio?

Yes. Every output includes generated audio, such as dialogue, music or sound effects, which you can describe in the prompt. Audio files cannot be used as input.

Which resolutions and aspect ratios are available?

Resolution can be 360p, 720p (default), 1080p or 4k; 1080p and 4k are upscaled, and 2160p is accepted as 4k. Aspect ratio is 16:9 (default) or 9:16, and other values are treated as 16:9. Frames and reference images should match the chosen ratio. On gemini-omni-1.2-flash-ext, only 16:9 and 9:16 are accepted; if you omit the ratio with images or a video, the output follows your material.

How much does the Gemini Omni 1.2 Flash API cost?

It is billed per second of output, and resolution sets the rate; see the live pricing table on this page for APIMart prices. Google's reference rate is about $0.070 per second at 720p, so a 15-second 720p clip is about $1.04. On APIMart, Gold members pay $0.06 per second at 720p, so the same clip costs about $0.90 (November 8, 2026). A deposit is reserved at submission and settled against actual usage after completion. gemini-omni-1.2-flash-ext uses a fixed price per second instead of token-based settlement: the cost is the per-second price of the resolution × billed seconds (the duration, the source length when editing, or only the added seconds when extending), and failed tasks are fully refunded.

What does Gemini Omni API pricing depend on?

On APIMart, Gemini Omni 1.2 Flash is billed per second of output, and the rate depends on resolution. Gold members pay about $0.02 at 360p, $0.06 at 720p, $0.09 at 1080p and $0.18 at 4K per second (November 8, 2026). Check the pricing table on this page for current rates.

Is the Gemini Omni 1.2 Flash API free?

No. APIMart is pay-as-you-go with no subscription, and the RUN button shows the estimated price before you submit. Failed tasks, including parameter errors, are not charged. If your balance cannot cover the deposit for the selected tier, the request returns HTTP 402.

How do I get a Gemini Omni 1.2 Flash API key?

Sign up for APIMart, open API Keys in the dashboard and create a key, or use Get API key on this page. Send it as Authorization: Bearer <key>. The same key works for Gemini Omni 1.2 Flash and other models on APIMart.

How do I call the API and retrieve the video?

POST your request to /v1/videos/generations and save data[0].task_id. Poll GET /v1/tasks/{task_id} every 5–10 seconds until status is completed, then read data.result.videos[0].url[0]. Higher resolutions and longer clips take longer, so allow a client timeout of about 10 minutes. Results are kept for 72 hours.

Are there regional limits or watermarks?

In the EEA, Switzerland and the UK, editing or extending uploaded videos and editing images that contain minors are not supported. All outputs carry Google's invisible SynthID watermark.

Related Models

Explore more models in the same category.

View All Models →

Gemini Omni 1.2 Flash API FAQ

Duration, inputs, editing, pricing and integration.

What is the Gemini Omni 1.2 Flash API?

What is the Gemini Omni API?

Is the Omni Flash API the same as Gemini Omni 1.2 Flash?

Omni Flash is the short name for Google's Gemini Omni Flash line. This page covers Gemini Omni 1.2 Flash; set gemini-omni-1.2-flash in the model field to call this version.

What is the difference between gemini-omni-1.2-flash and gemini-omni-1.2-flash-ext?

What changed in Gemini Omni 1.2 Flash compared with 1.1?

Gemini Omni 1.2 Flash vs Veo 3.1: what is the difference?

Which parameters does the Gemini Omni 1.2 Flash API support?

Which requests does gemini-omni-1.2-flash-ext reject?

How long can Gemini Omni 1.2 Flash videos be?

Can Gemini Omni 1.2 Flash turn images into video?

How many reference images can I use?

How do video editing and extension work?

Does Gemini Omni 1.2 Flash generate audio?

Yes. Every output includes generated audio, such as dialogue, music or sound effects, which you can describe in the prompt. Audio files cannot be used as input.

Which resolutions and aspect ratios are available?

How much does the Gemini Omni 1.2 Flash API cost?

What does Gemini Omni API pricing depend on?

Is the Gemini Omni 1.2 Flash API free?

How do I get a Gemini Omni 1.2 Flash API key?

How do I call the API and retrieve the video?

Are there regional limits or watermarks?

In the EEA, Switzerland and the UK, editing or extending uploaded videos and editing images that contain minors are not supported. All outputs carry Google's invisible SynthID watermark.

Gemini Omni 1.2 Flash API

Gemini Omni 1.2 Flash API Pricing

Token Pricing

Generate and Edit Videos with the Gemini Omni 1.2 Flash API

Key Features of the Gemini Omni 1.2 Flash API

What You Can Build with the Gemini Omni 1.2 Flash API

How to Get a Gemini Omni 1.2 Flash API Key and Start Building

Create a Gemini Omni 1.2 Flash API Key

Configure a gemini-omni-1.2-flash Request

Integrate the Gemini Omni 1.2 Flash API

Gemini Omni 1.2 Flash API Examples: Text to Video and First/Last Frames

Authenticate Your Requests

Submit a gemini-omni-1.2-flash Task

Retrieve the Video Result

Gemini Omni 1.2 Flash API Parameters

Gemini Omni API Model Family

Gemini Omni 1.2 Flash API FAQ

What is the Gemini Omni 1.2 Flash API?

What is the Gemini Omni API?

Is the Omni Flash API the same as Gemini Omni 1.2 Flash?

What is the difference between gemini-omni-1.2-flash and gemini-omni-1.2-flash-ext?

What changed in Gemini Omni 1.2 Flash compared with 1.1?

Gemini Omni 1.2 Flash vs Veo 3.1: what is the difference?

Which parameters does the Gemini Omni 1.2 Flash API support?

Which requests does gemini-omni-1.2-flash-ext reject?

How long can Gemini Omni 1.2 Flash videos be?

Can Gemini Omni 1.2 Flash turn images into video?

How many reference images can I use?

How do video editing and extension work?

Does Gemini Omni 1.2 Flash generate audio?

Which resolutions and aspect ratios are available?

How much does the Gemini Omni 1.2 Flash API cost?

What does Gemini Omni API pricing depend on?

Is the Gemini Omni 1.2 Flash API free?

How do I get a Gemini Omni 1.2 Flash API key?

How do I call the API and retrieve the video?

Are there regional limits or watermarks?

Related Models

Latest Gemini Omni 1.2 Flash articles

Key Features of the Gemini Omni 1.2 Flash API

What You Can Build with the Gemini Omni 1.2 Flash API

How to Get a Gemini Omni 1.2 Flash API Key and Start Building

Create a Gemini Omni 1.2 Flash API Key

Configure a gemini-omni-1.2-flash Request

Integrate the Gemini Omni 1.2 Flash API

Gemini Omni 1.2 Flash API FAQ

What is the Gemini Omni 1.2 Flash API?

What is the Gemini Omni API?

Is the Omni Flash API the same as Gemini Omni 1.2 Flash?

What is the difference between gemini-omni-1.2-flash and gemini-omni-1.2-flash-ext?

What changed in Gemini Omni 1.2 Flash compared with 1.1?

Gemini Omni 1.2 Flash vs Veo 3.1: what is the difference?

Which parameters does the Gemini Omni 1.2 Flash API support?

Which requests does gemini-omni-1.2-flash-ext reject?

How long can Gemini Omni 1.2 Flash videos be?

Can Gemini Omni 1.2 Flash turn images into video?

How many reference images can I use?

How do video editing and extension work?

Does Gemini Omni 1.2 Flash generate audio?

Which resolutions and aspect ratios are available?

How much does the Gemini Omni 1.2 Flash API cost?

What does Gemini Omni API pricing depend on?

Is the Gemini Omni 1.2 Flash API free?

How do I get a Gemini Omni 1.2 Flash API key?

How do I call the API and retrieve the video?

Are there regional limits or watermarks?

Related Models