Google High-fidelity video generation
Veo 3.1
Direct a cinematic shot with motion, sound and references in mind.
Veo 3.1 is a Google video route for high-fidelity generation. TokenHot lists text, image and video inputs, video output and a native-audio, camera-control and reference-input workflow in the catalog description. Use it for cinematic shorts, advertising storyboards and shots where physical motion and audio-visual timing deserve careful review.
- Text + image + video
- Video output
- Native-audio workflow
The route exposes 720p, 1080p and 4K pricing conditions. Duration, reference-media support, audio behavior and asynchronous job details must be verified in the endpoint response before promising a deliverable.
Try this model
Choose an aspect ratio, resolution, and duration to generate a video.
veo3.1Input
Generated result
Enter a prompt, choose your settings, and generate.
USD /call
Pricing
| Group | Tier | Price |
|---|---|---|
| default | 720p | $1.6544 |
| default | video | $1.6544 |
| default | 1080p | $1.704032 |
| default | 4k | $2.101088 |
Public list prices are shown in USD. Final charges may vary by account group and usage tier.
Overview
What is Veo 3.1?
A cinematic brief names the subject, environment, lens or camera move, action, sound and final frame. Keep the first test to one shot so defects in motion, continuity or audio have a clear cause.
Use reference inputs to guide a shot, then compare the output to the reference and the acceptance rubric. A high-fidelity label is not a substitute for reviewing faces, physics, text and sound.
Direct the camera
Separate subject action, camera movement, framing and final hold so the shot can be judged.
Write the sound cue
Specify dialogue, ambience or silence and inspect whether timing supports the visible action.
Anchor the look
State what an image or video reference should preserve and what the model may change.
From brief to deliverable
Put Veo 3.1 to work
Directors and creative teams
Develop a cinematic short
Use a focused shot brief and reference to test camera movement, physical motion and the final frame before building a sequence.
- Tools you need
- Video generation, player, storage and editorial review.
- Keep in mind
- A single shot cannot prove multi-shot continuity or final delivery readiness.
View a task brief
Use the supplied shot brief, reference media, aspect ratio, duration and review rubric. to plan develop a cinematic short. Return a selected video take with motion and sound notes., state the evidence limits and list the checks required before accepting the result. Do not claim an output or interaction was verified without direct evidence.
Advertising and brand teams
Create an advertising storyboard take
Prototype a product or brand beat with explicit copy-safe space, camera path and audio cue.
- Tools you need
- Reference upload, generation queue and a design review.
- Keep in mind
- Inspect product details, typography and rights separately from motion quality.
View a task brief
Use the supplied product reference, story beat, camera move, audio cue and target resolution. to plan create an advertising storyboard take. Return a reviewable ad take and storyboard annotation., state the evidence limits and list the checks required before accepting the result. Do not claim an output or interaction was verified without direct evidence.
Content and VFX teams
Transform a reference clip
Use a short reference video to guide motion while keeping the intended subject and physical constraint explicit.
- Tools you need
- Video upload, generation, frame review and an editor.
- Keep in mind
- Reference input does not guarantee exact timing, identity or geometry across every frame.
View a task brief
Use the supplied reference clip, transformation request, invariant list and output settings. to plan transform a reference clip. Return a motion variation with a comparison report., state the evidence limits and list the checks required before accepting the result. Do not claim an output or interaction was verified without direct evidence.
Capabilities in context
Key features
| Feature | What you get | Why it matters |
|---|---|---|
| Input modes | Text, image and video inputs are listed | Use a source manifest and verify duration, encoding and reference limits before submission. |
| Video output | The route produces video | Treat generation as an asynchronous job and retain model, parameters and output metadata. |
| Audio workflow | The catalog description highlights native audio | Review dialogue, ambience, timing and rights; audio finishing remains a separate step. |
| Resolution tiers | Pricing exposes 720p, 1080p and 4K labels | Keep resolution explicit and use the current dynamic table for estimates. |
| Reference control | Camera and reference workflows are emphasized | State what should remain stable, then compare the output frame by frame where needed. |
The page uses TokenHot catalog metadata and the existing Veo trial/API workflow. Verify resolution, duration, audio and reference parameters on the selected endpoint.
Audience & fit
Where Veo 3.1 fits
Directors and creative teams
Use Veo 3.1 to prototype cinematic shots and review motion, framing and sound before assembling a full sequence.
Advertising and brand teams
Provide a product reference and a precise beat, then keep copy, identity and rights checks explicit.
Video platform builders
Store job parameters, status, outputs and review notes so a selected take is reproducible.
Cost context
Plan the cost of a useful result
Price the resolution choice
720p, 1080p and 4K have different catalog conditions. Keep the chosen resolution and duration with the estimate.
Budget failed takes
High-fidelity work still needs retries. Include review, storage, transcoding and edit time in the project cost.
Separate final delivery
Audio mix, color, captions, rights and export validation remain outside the generation call.
Use the current pricing table for available rates and account groups. Model IDs and prices come from TokenHot’s catalog; provider pricing and subscriptions are separate.
API
Code examples
curl --location 'https://api.tokenhot.ai/v1/video/generations' \
--header 'Content-Type: application/json' \
--data '{
"model": "veo3.1",
"prompt": "a golden retriever running across a sunny beach, slow motion, cinematic",
"aspect_ratio": "16:9",
"resolution": "1080p"
}'FAQ
Frequently asked questions
What is Veo 3.1 best suited for?
Veo 3.1 is suited to the input, output, and capability types listed on this page. Test production workloads before choosing it for a critical system.
How is Veo 3.1 priced?
Pricing is shown in the pricing section above. Actual cost depends on usage volume, account group, and the request payload.
How can I call Veo 3.1?
Use the model ID shown above with one of the supported API protocols. Code examples are provided when usage data is available.
Does Veo 3.1 generate audio?
The catalog description highlights a native-audio workflow. Verify the returned job and endpoint configuration before promising synchronized sound.
Can it use reference video?
The catalog lists video input. Check the current endpoint for accepted encoding, duration and reference parameters.
How does video pricing vary?
The current expression exposes 720p, 1080p and 4K conditions. Use the dynamic pricing table for the exact request.
What should a Veo prompt specify?
Name the subject, action, camera move, framing, sound cue, duration and final frame. Keep the first test to one reviewable shot.
Get started
Build with Veo 3.1
API