Pick a route, write a prompt, and see the estimated cost before you spend anything.
Create a video
Every route runs on the same async video endpoint.Results are kept for 24 hours — download anything you want to keep.
Gemini Omni 1.1 Flash is billed by tokens, not by the second. The final charge always uses the tokens the model actually returned.
First Test Cost
Text-to-Video · 5s · 360pOne 5s 360p sample
About 66 tests with $10 in credits.
Iterate prompts at 360p, confirm quality at 720p, and reserve 4K for final delivery — 4K costs 3x what 720p does for the same duration.
Testing Budget Guide
Pick an amount based on how many tests you expect.Good for a first validation.
Good for prompt iteration.
Good before production integration.
Estimates for a text-to-video request, including the reserve for thinking tokens. Input images and input video are billed separately at the input rate.
Every request settles per token across three SKUs — video output, input and thinking — against the token counts the upstream actually returns.
| Token type | What it covers | Price | Billing |
|---|---|---|---|
| Video outputPer 1K tokens | The generated video with its synchronized audio. 720p produces 5,792 tokens per second. | $0.015 / 1K tokens-15% 1.0115 cr / 1K tokens$0.018 official | Output tokens |
| InputPer 1K tokens | Your prompt text, input images and input video, combined. | $0.0013 / 1K tokens-15% 0.0867 cr / 1K tokens$0.0015 official | Input tokens |
| Thinking tokensPer 1K tokens | The model's internal reasoning. Typically a few hundred tokens per request. | $0.0077 / 1K tokens-15% 0.5202 cr / 1K tokens$0.0090 official | Output tokens |
Charges are settled per token against the tokens the upstream actually returned, so the final amount can differ slightly from the estimate. Logged-in users see the rates for their own pricing group.
gemini-omni-1.1-flash-text-to-videoNative audio included. 360p and 1080p and 4K scale the output tokens by 1/3, 1.5 and 3 against 720p; final charges use actual token usage.
Gemini Omni 1.1 Flash is Google’s GA multimodal video generation model. The stable Gemini API model ID is gemini-omni-1.1-flash; EvoLink exposes five task-specific routes on one endpoint: text-to-video, image-to-video, reference-to-video, video edit, and video extend. Generation and extension add 3–10 seconds per request, with native synchronized speech, music, and sound effects. The available output tiers are 360p, 720p, and upscaled 1080p or 4K.
Picking the right route matters more than sending more references. The same field can mean different things across routes — image order carries meaning in image-to-video and none in reference-to-video.
gemini-omni-1.1-flash-text-to-videoGenerate a 3–10 second clip from a prompt alone, with native synchronized audio, at 360p through 4K.
gemini-omni-1.1-flash-image-to-videoOne image animates it as the first frame. Two images are read in order as the first and last frame, and the model interpolates between them.
gemini-omni-1.1-flash-reference-to-videoGuide identity, style, or composition with up to 10 reference images plus up to 3 optional reference videos. Order carries no meaning here.
gemini-omni-1.1-flash-video-editRewrite objects, style, or lighting in one input video. Length and aspect ratio follow the input; quality: auto preserves its resolution, or you can select an output tier.
gemini-omni-1.1-flash-video-extendAppend 3–10 seconds that continue the motion and camera language. duration is the number of seconds added, not the total length.
Iterate at 360p, confirm at 720p, deliver at 4K. Output tokens scale 1/3, 1x, 1.5x, and 3x against 720p.
Speech, music, and sound effects are generated with the video at no extra cost. There is no toggle and no audio input.
Two ordered images define the start and end of the shot — verified with a PSNR check against the returned frames.
Manage long-running jobs with a task ID, polling, and HTTPS callbacks. Result links stay valid for 24 hours.
Use the EvoLink API for product integration and batch jobs, or call it from Codex, Claude, or Gemini for fast creative and development workflows. Both paths share the same EvoLink API key, balance, model routes, and task history.
Best for: product backends, batch jobs, automated workflows
Call EvoLink’s unified video API from your server and control the model ID, parameters, task queue, callbacks, and result storage.
Best for: creative and development tasks in Codex, Claude, and Gemini
Give the Agent your output goal, assets, and acceptance criteria. It can choose the route, assemble the request, track the task, and return the result without requiring you to hand-code every step.
This example shows the shortest runnable flow: create a task, save the returned task ID, then poll or wait for an HTTPS callback. Open the API tab for the complete parameter and response reference.
curl -X POST https://api.evolink.ai/v1/videos/generations \
-H "Authorization: Bearer $EVOLINK_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-omni-1.1-flash-text-to-video",
"prompt": "A premium product film with controlled camera motion",
"duration": 8,
"quality": "720p",
"aspect_ratio": "16:9",
"callback_url": "https://your-domain.com/webhooks/video"
}'
# Save the returned task ID, then query:
curl https://api.evolink.ai/v1/tasks/{task_id} \
-H "Authorization: Bearer $EVOLINK_API_KEY"Generation and Video Extend require an integer duration from 3 to 10; Video Edit requires duration: auto. Video Edit and Video Extend accept quality: auto or 360p / 720p / 1080p / 4k, require aspect_ratio: auto, and accept up to 10 optional reference images.
Seed, fps, negative prompt, output count, audio input, generate_audio, person generation, prompt enhancement, and output format are accepted but ignored. Write negative instructions into the prompt instead.
Check the Authorization bearer token and confirm the available balance and task billing in the console.
Keep the task ID, inspect the final state and billing record, and identify whether the cause is validation, review, or execution before retrying. Do not infer the billing outcome from the submission response.
callback_url must be a public HTTPS URL, not localhost or a private network address. Always keep the task ID as a polling fallback.
Use the same brief, the same input assets, and the same acceptance criteria to compare usable-shot rate, reruns, and total project cost. The right answer depends on shot length and how much resolution you actually need.
| Decision factor | Gemini Omni 1.1 Flash | Gemini Omni Flash | Seedance 2.5 |
|---|---|---|---|
| Best suited to | Short shots that need an upscaled 4K delivery, first-and-last-frame control, or extending an existing clip | Existing Gemini Omni workflows already tuned at 720p | Long shots, many references, and audio-driven pacing |
| Duration | 3–10 seconds; Video Extend appends 3–10 more | 3–10 seconds | 4–30 seconds |
| Resolution | 360p / 720p / upscaled 1080p / upscaled 4K | 720p only | 480p / 720p / 1080p |
| Inputs | Text, first and last frame, up to 10 reference images plus up to 3 reference videos | Text, one image, up to 6 reference images | Text, images, video and audio references, up to 50 assets |
| Audio | Native, always on, no audio input accepted | Native, always on | Native, toggleable, accepts audio references |
| Cost decision | Cheapest per second at 360p; 4K costs 3x 720p, so decide the delivery resolution before you budget | Single 720p rate — simplest to forecast | Per-second pricing; compare cost per usable shot on longer clips |
The hard part of a production video API integration is not one request. It is managing model choice, cost, references, asynchronous jobs, callbacks, failures, and fallback routes after launch. EvoLink brings these into one video API and console so teams can test first, integrate second, and route by usable-shot rate and total project cost.
All five Gemini Omni 1.1 Flash routes share EvoLink authentication, balance, and task infrastructure. Your server stores one EVOLINK_API_KEY and selects the model ID that matches each input.
When you also need Seedance, MiniMax H3, Veo, or another video model, you do not have to maintain separate provider accounts, keys, balances, and authentication code. Keep the same task and billing framework and change routes by duration, resolution, and use case.
The upstream silently clamps out-of-range durations — asking for 11 seconds returns 10, asking for 2 returns 3, with no error either way. EvoLink rejects those values instead, so you never pay for a length you did not ask for.
Video Extend is the sharper edge: its duration means "seconds appended", and omitting it makes the upstream append 10 seconds by default — 3.3x the cost of a 3-second extension. EvoLink always sends an explicit duration.
Output tokens scale linearly with resolution, so a 10-second clip is roughly 57,920 video tokens at 720p and 173,760 at 4K. That is a 3x difference on the largest line of the bill.
The pricing section shows both the raw token rates and the per-second equivalent for each resolution, and the Playground estimate updates as you change the resolution — so the decision happens before the spend, not after.
Save the task ID and verify the final status, failure reason, and billing record in the console instead of treating “request created” as “video generated.” Use the final billing record as the source of truth for the charge outcome.
Video generation is asynchronous. Production systems should use polling or a public HTTPS callback, handle missing or duplicate callbacks and timeouts, and retry only after identifying a validation, review, or execution failure.
Compare Google video routes under one EvoLink account and API key, then choose by shot duration, resolution, and cost.
This page. 3–10s shots at 360p to 4K, first-and-last-frame control, video edit and extend.
The previous Gemini Omni Flash generation: 720p only, four routes, no video extend. Still live for existing integrations.
View API
Google’s cinematic video model with native audio, for longer-form and higher-fidelity shots.
View APIWhen Gemini Omni 1.1 Flash is not the default, use the same brief to compare resolution, shot duration, audio, motion stability, and total project cost.
For 4–30 second shots with up to 50 multimodal references; compare usable-shot rate on longer clips.
View API
For detailed 2K clips of 4–15 seconds; compare its usable-shot rate with the same brief.
View API
For creative generation, action, and multi-shot video; a production fallback outside the Gemini family.
View API
When a shot already has usable motion and composition but looks soft, use Topaz for detail recovery and 1x, 2x, or 4x upscaling.
View APIHigh-intent questions about availability, model IDs, pricing, limits, model selection, and troubleshooting.
Yes. EvoLink exposes five Gemini Omni 1.1 Flash routes: text-to-video, image-to-video, reference-to-video, video edit, and video extend. Validate the output in Playground first, then integrate with the same EvoLink API key.
gemini-omni-1.1-flash-text-to-video, gemini-omni-1.1-flash-image-to-video, gemini-omni-1.1-flash-reference-to-video, gemini-omni-1.1-flash-video-edit, and gemini-omni-1.1-flash-video-extend. Pick the route that matches your input — text-to-video rejects media URLs, and edit and extend each require exactly one input video.
Per token, across three rates: video output, input (prompt text, images and input video combined), and thinking tokens. Output tokens scale with resolution and duration — 720p produces 5,792 tokens per second, 4K produces 17,376. The pricing section converts those into a per-second figure for each resolution.
No. A generation creates 3–10 seconds, and each extension appends 3–10 seconds. Google documents up to 10 seconds per multi-turn extension, with a cumulative ceiling of 40 seconds and the last up to 10 seconds used as context. EvoLink has verified one extension, not the complete repeated-extension path to 40 seconds.
A generation creates 3 to 10 seconds; an extension appends 3 to 10 seconds, at 24fps. 360p and 720p are direct outputs; 1080p and 4K are upscaled. Omitting the resolution gives 720p. Values outside 3–10 are silently clamped upstream, so EvoLink rejects them instead.
Order carries meaning: the first image is the first frame and the second is the last frame. Sending one image animates it as the first frame. A last frame cannot be sent alone — the upstream has no role marker for images, so position in the request is the only signal.
It is the number of seconds appended to your input video, not the total output length. A 3-second input with duration 3 returns roughly 6 seconds, and only the appended part is charged as output. EvoLink always sends an explicit duration, because omitting it makes the upstream append 10 seconds by default.
It generates speech, music, and sound effects with the video. Usage is settled with the returned video tokens; there is no separate audio toggle. It does not accept audio files as input.
Select endpoint
All APIs require Bearer Token authentication.
Authorization:
Bearer YOUR_API_KEY/v1/videos/generationsGenerate a 3-10 second video with natively synchronized audio from a text prompt, at 360p, 720p, 1080p, or 4K.
Processing is asynchronous. Use the returned task ID to query pending, processing, completed, or failed status. Result links stay valid for 24 hours.
modelstringRequiredDefault: gemini-omni-1.1-flash-text-to-videoFixed value: gemini-omni-1.1-flash-text-to-video
gemini-omni-1.1-flash-text-to-videopromptstringRequiredNon-empty text prompt. There is no separate negative-prompt parameter — write negative instructions directly into the prompt.
A cinematic product film with slow camera movementdurationintegerOptionalDefault: 5Output duration in seconds.
| Value | Description |
|---|---|
| 3-10 | Any integer from 3 through 10 |
5qualitystringOptionalDefault: 720pOutput resolution.
| Value | Description |
|---|---|
| 360p | 640×360 — 1/3 of the 720p output tokens |
| 720p | 1280×720 |
| 1080p | 1920×1080 — 1.5x the 720p output tokens |
| 4k | 3840×2160 — 3x the 720p output tokens |
720paspect_ratiostringOptionalDefault: autoOutput aspect ratio.
| Value | Description |
|---|---|
| auto | Select automatically |
| 16:9 | 16:9 |
| 9:16 | 9:16 |
16:9callback_urlstringOptionalOptional HTTPS callback URL for terminal task updates.
https://your-domain.com/webhooks/videoParameters that have no effect
n, fps, seed, negative_prompt, generate_audio, person_generation, enhance_prompt, output_format, content_filter, audio_urls and model_params are accepted but ignored, so one request body works across all five routes. Audio is generated natively and always included; the model does not accept audio files as input.
{
"model": "gemini-omni-1.1-flash-text-to-video",
"prompt": "A cinematic product film with slow camera movement",
"duration": 5,
"quality": "720p",
"aspect_ratio": "16:9"
}