Gemini Omni Flash Video API

Gemini Omni Flash is a high-performance multimodal model for fast video generation, editing, and cinematic control. It can use text, images, audio, and video together, supports conversational editing through the Interactions API, and can apply Gemini world knowledge to physical scenes and storytelling.

Calling Method

Endpoint and Authentication

Use the Gemini-compatible Interactions endpoint:

POST https://api.exchangetoken.ai/v1beta/interactions

Use your Exchange Token API key in either of the following authentication headers:

x-goog-api-key: YOUR_API_KEY

Authorization: Bearer YOUR_API_KEY

Content-Type Header:

Content-Type: application/json

Request Body

The request body follows the Interactions create schema. The examples below use these common fields:

Field	Type	Required	Description
model	string	Yes	Model name. Use gemini-omni-flash-preview.
input	string, content object, or content array	Yes	Main interaction input. Use a string for text-to-video, or an array for multimodal image/video editing input.
input[].type	string	Conditional	Content item type, such as text, image, video, or user_input.
input[].text	string	Conditional	Text prompt when type is text.
input[].data	string	Conditional	Base64-encoded media bytes for image or video inputs.
input[].mime_type	string	Conditional	MIME type for media inputs, such as image/jpeg, image/png, or video/mp4.
input[].content	array	Conditional	Nested content array when using a user_input wrapper.
response_format	object	No	Output format options. Use {"type":"video"} for video output.
response_format.type	string	No	Output type. For this model, use video.
response_format.aspect_ratio	string	No	Video aspect ratio. Supported values used in examples: 16:9 and 9:16.
generation_config	object	No	Generation options.
generation_config.video_config.task	string	No	Optional video task hint. Supported values: text_to_video, image_to_video, reference_to_video, edit.

Response Body

Common fields:

Field	Type	Description
id	string	Unique identifier of the interaction
object	string	Resource type identifier, typically interaction
status	string	Current interaction status, such as in_progress, completed, or failed
role	string	Role associated with the response payload, typically model
created	string	Interaction creation time in ISO 8601 format
updated	string	Last interaction update time in ISO 8601 format
model	string	Name of the model used for the interaction
steps	array	Ordered step objects returned by the interaction
usage	object	Token usage summary for the interaction when provided by upstream

Common steps fields:

Field	Type	Description
type	string	Step type, for example model_output
content	array	Content items carried by the step

Example:

{
  "id": "v1_...",
  "status": "completed",
  "role": "model",
  "created": "2026-05-27T06:15:03Z",
  "updated": "2026-05-27T06:15:03Z",
  "steps": [
    {
      "content": [
        {
          "text": "",
          "type": "text"
        }
      ],
      "type": "model_output"
    },
    {
      "content": [
        {
          "mime_type": "video/mp4",
          "data": "AAAAIGZ0eXBpc29t...",
          "type": "video"
        }
      ],
      "type": "model_output"
    }
  ],
  "object": "interaction",
  "model": "gemini-omni-flash-preview"
}

Text to Video

Generate a video with audio from a text prompt. For best results, describe the scene, camera movement, lighting, mood, and key actions.

curl -X POST "https://api.exchangetoken.ai/v1beta/interactions" \
  -H "x-goog-api-key: $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-omni-flash-preview",
    "input": "A marble rolling fast on a chain reaction style track, continuous smooth shot."
  }'

Control Aspect Ratio

Set response_format.aspect_ratio to 9:16 for portrait video. The default is landscape 16:9.

curl -X POST "https://api.exchangetoken.ai/v1beta/interactions" \
  -H "x-goog-api-key: $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-omni-flash-preview",
    "input": "A futuristic city with neon lights and flying cars, cyberpunk style",
    "response_format": {
      "type": "video",
      "aspect_ratio": "9:16"
    }
  }'

Image to Video

Provide one or more reference images with your text prompt. The model decides how to use the images based on the prompt. This is useful for bringing product shots, illustrations, or photographs to life.

curl -X POST "https://api.exchangetoken.ai/v1beta/interactions" \
  -H "x-goog-api-key: $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-omni-flash-preview",
    "input": [
      { "type": "image", "data": "'"$BASE64_IMAGE"'", "mime_type": "image/jpeg" },
      { "type": "text", "text": "turn this into realistic footage, using the drawing only as a guide for movement, do not show the drawing in the final video" }
    ]
  }'

TIP

For image-to-video, use high-resolution images and provide specific motion descriptions. Vague prompts such as "make it move" are usually less effective than detailed camera, subject, and environment instructions.

Subject Reference

You can provide multiple images as subject references. For example, pass a cat image and a yarn image to generate a video of the cat playing with the yarn.

curl -X POST "https://api.exchangetoken.ai/v1beta/interactions" \
  -H "x-goog-api-key: $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-omni-flash-preview",
    "input": [
      { "type": "image", "data": "'"$CAT_B64"'", "mime_type": "image/png" },
      { "type": "image", "data": "'"$YARN_B64"'", "mime_type": "image/png" },
      { "type": "text", "text": "A cat playfully batting at a ball of yarn." }
    ]
  }'

Task Parameter

Use generation_config.video_config.task to clarify the intended behavior. If it is omitted, the model infers the task from the prompt.

Allowed values:

• text_to_video
• image_to_video
• reference_to_video
• edit

curl -X POST "https://api.exchangetoken.ai/v1beta/interactions" \
  -H "x-goog-api-key: $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-omni-flash-preview",
    "input": [
      { "type": "image", "data": "'"$BASE64_IMAGE"'", "mime_type": "image/jpeg" },
      { "type": "text", "text": "turn this into realistic footage, using the drawing only as a guide for movement, do not show the drawing in the final video" }
    ],
    "generation_config": {
      "video_config": {
        "task": "image_to_video"
      }
    }
  }'

Edit Your Own Videos

Upload or provide a video, then ask Gemini Omni Flash to edit it.

VIDEO_B64=$(base64 -w 0 "$VIDEO_FILE")

curl -sS -w "\n[HTTP %{http_code}]\n" "https://api.exchangetoken.ai/v1beta/interactions" \
  -H "x-goog-api-key: $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-omni-flash-preview",
    "input": [
      {
        "type": "user_input",
        "content": [
          {
            "type": "video",
            "mime_type": "video/mp4",
            "data": "'"$VIDEO_B64"'"
          },
          {
            "type": "text",
            "text": "When the person touches the mirror, make the mirror ripple beautifully like liquid, and the person arm turns into reflective mirror material"
          }
        ]
      }
    ],
    "response_format": { "type": "video" }
  }'