Loading model…正在加载模型详情…
Loading model…正在加载模型详情…
Create video from a scene description or images with Google’s Gemini Omni 1.1 Flash, with optional first and last frames for directing a shot.
A dog enters the scene and she pets it
A violinist is playing this violin
Musicians are playing in a concert as part of an orchestra. Every 1s cut to a close up of a different instrument. A consistent song plays throughout.
Gemini Omni 1.1 Flash is Google’s multimodal video creation model. Google describes it as offering greater creative control through scene context, reference inputs and first and last frame control.
On UniRoute, the callable video variant accepts a text prompt with optional reference images or first and last frames. Choose a resolution and duration option; aspect ratio and seed are also available under More options.
Gemini Omni 1.1 Flash follows Gemini Omni. On UniRoute, it adds reference image and first and last frame inputs alongside the text prompt and output options available on the earlier Gemini Omni page.
What you can do with Gemini Omni 1.1 Flash through UniRoute today.
Describe a subject, action, setting and camera movement, then choose an output option and review the quote before submitting.
Add reference images and describe how the scene should move. Use reference images separately from first and last frame inputs.
Provide a first frame to guide the start of a shot, with an optional last frame for its ending. Add the first frame before the last frame and describe the motion between them.
Other Gemini Omni modes (video references and scene extension, audio and character tools) aren’t available on UniRoute yet.
The variants you can call, with their options and prices.
| Variant | Model ID | Modes | Inputs | Output | Price |
|---|---|---|---|---|---|
| Gemini Omni 1.1 Flash | google/gemini-omni-flash-1-1 | Text to video | Text prompt and a size option | Resolution: 720p, 1080p; Duration: 4s, 8s | $0.28 to $0.47 per request |
Priced per request. The option you choose sets the price.
| Gemini Omni 1.1 Flash | |
|---|---|
| 720p · 4s | $0.28 |
| 720p · 8s | $0.47 |
| 1080p · 4s | $0.28 |
| 1080p · 8s | $0.47 |
Rounded to the cent; the live quote in the workspace shows the exact amount. Prices updated 2026-11-08.
Pay as you go from a single USD wallet balance. You see the quote before each request.
Call Gemini Omni 1.1 Flash from your own code with the media API.
# Requires bash, curl and jq. Set API_KEY to your own unified UniRoute Key.set -euo pipefail: "${API_KEY:?Set API_KEY first}"BASE='https://api.uniroute.app/v1/media'MODEL='google/gemini-omni-flash-1-1'OPTION='720p:4'PROMPT='A calm sunrise over a mountain lake'curl -fsS --max-time 60 "$BASE/catalog" -H "Authorization: Bearer $API_KEY" | jq -e '.data.models'BODY=$(jq -n --arg model "$MODEL" --arg option "$OPTION" --arg prompt "$PROMPT" '{model:$model,option:$option,prompt:$prompt}')QUOTE_BODY=$(printf '%s' "$BODY" | jq '{model,option}')QUOTE=$(curl -fsS --max-time 60 "$BASE/quote" -H "Authorization: Bearer $API_KEY" -H 'Content-Type: application/json' -d "$QUOTE_BODY")CAP=$(printf '%s' "$QUOTE" | jq -er '.data.quoted_usd')BODY=$(printf '%s' "$BODY" | jq --arg cap "$CAP" '. + {max_cost_usd:$cap}')IDEMPOTENCY="example-$(date +%s)-$$"create() { curl -fsS --max-time 60 "$BASE/tasks" -H "Authorization: Bearer $API_KEY" -H "Idempotency-Key: $IDEMPOTENCY" -H 'Content-Type: application/json' -d "$BODY"; }TASK_ID=$(create | jq -er '.data.task_id')# The same request and idempotency key must return the original task without charging again.REPLAY_ID=$(create | jq -er '.data.task_id')[ "$TASK_ID" = "$REPLAY_ID" ]for attempt in $(seq 1 120); do TASK=$(curl -fsS --max-time 60 "$BASE/tasks/$TASK_ID" -H "Authorization: Bearer $API_KEY") printf '%s' "$TASK" | jq -e '.data | {task_id,status,billing}' if printf '%s' "$TASK" | jq -e '.data.status == "success" and .data.billing.state == "charged"' >/dev/null; then index=0 while IFS= read -r url; do index=$((index+1)) curl -fL --max-time 120 "$url" -o "$TASK_ID-$index.bin" done < <(printf '%s' "$TASK" | jq -er '.data.urls[].url') break fi if printf '%s' "$TASK" | jq -e '.data.status == "failed" and .data.billing.state == "released"' >/dev/null; then exit 1; fi if [ "$attempt" = 120 ]; then echo "Polling limit reached. Keep task ID $TASK_ID and query it later; do not create a new task." >&2 exit 1 fi sleep 5donecurl -fsS --max-time 60 "$BASE/tasks?limit=20" -H "Authorization: Bearer $API_KEY" | jq -e '.data'# Check this task and the caller Key in Console usage; billing.charged_usd is the actual USD charge.| Name | In | Description |
|---|---|---|
model | Body | Model ID to run. |
option | Body | One of the options offered for the model: 720p:4, 720p:8, 1080p:4, 1080p:8. |
prompt | Body | Text prompt describing what to generate. |
max_cost_usd | Body | Maximum cost in USD for this task, taken from the quote. |
Idempotency-Key | Header | A unique key per task, so a repeated request returns the original task instead of charging again. |
Typical ways to put Gemini Omni 1.1 Flash to work.
Use a product image as a reference and describe the scene and movement to explore a video concept before planning a shoot.
Supply a first and last frame to communicate the intended start and ending of a shot, then describe the action connecting them.
Turn a written shot description into a moving preview for discussing framing, camera movement and the order of a scene.
Common questions about Gemini Omni 1.1 Flash.
Gemini Omni 1.1 Flash is Google’s multimodal video creation model. On UniRoute, its video variant supports text prompts with optional reference images or first and last frames, in the workspace and through the media API.
Use reference images or first and last frames in a request, rather than combining both. A last frame requires a first frame. Open More options to add these inputs, an aspect ratio or a seed.
Not currently. This UniRoute page exposes the video generation variant with the inputs shown in the workspace and API section. Video reference and extension inputs, audio and character tools are not callable here.
Choose a resolution and duration combination from the workspace. The specs and pricing tables show every currently available option; the optional aspect ratio and seed controls are under More options.
From $0.28 / clip. Each request is quoted for the whole clip at the selected option. See the Pricing section for every rate (prices updated 2026-11-08).
Use the media API to quote the selected model and option, create a task with an Idempotency-Key and a maximum cost, then poll its status until the video is ready. Include supported image or frame inputs when needed; the API section shows the field names.
No. Generation is paid from your wallet balance. You can open the workspace and review the price without paying, create an account to see a live quote for your exact settings, and you are charged only for requests that are accepted.