The Veo 3.1 API produces our launch teasers from a single still — no storyboard, no manual keyframing. Replaces a half-day session for the editing team.
The Veo 3.1 API animates a still image with natural-language prompts (Google Veo 3.1 preview) — 4/6/8-second clips at 720p or 1080p, optional synchronized audio, up to 3 reference images, optional last_image keyframe — all through one REST endpoint, priced 5% below Google's Veo 3.1 API list.
Input
The text prompt sent to the model
Output
SampleRun the model to replace this previewVeo 3.1 API: Image to Video
Use the Veo 3.1 API to animate still images with natural-language prompts.
The Veo 3.1 API animates a still image with natural-language prompts (Google's preview tier). Renders 4/6/8-second clips at 720p or 1080p, with optional synchronized audio, 16:9 or 9:16 aspect ratios, and up to 3 reference images for identity continuity — all through one REST endpoint.
The Veo 3.1 API also accepts an optional last_image keyframe to lock the final frame, giving you motion-path control without manual tweening. Pricing is 5% below Google's published Veo 3.1 API rate — $0.190 per second video-only, $0.340 per second with synchronized audio. 720p and 1080p share the same per-second rate, so you get full HD without paying a resolution premium. One RouterBase key works alongside 200+ other models.
Six reasons teams ship on the Veo 3.1 API
From identity-locked references to per-second pricing — what the Veo 3.1 API gets right.
Natural-language motion
Describe the motion in plain English; the Veo 3.1 API animates your still image into a 4/6/8-second clip without timeline editing.
Reference images
Pass up to 3 reference images alongside the base; the Veo 3.1 API locks identity, brand assets, or scene continuity across the clip.
last_image keyframe
Specify the final frame and the Veo 3.1 API interpolates the motion path, giving you keyframe control without tweening tools.
Audio generation
Toggle generate_audio and the Veo 3.1 API produces synchronized audio in the same generation — no separate TTS or post-edit pass.
720p / 1080p, 4–8 sec
Switch resolution and duration per Veo 3.1 API call. 720p (default) is faster; 1080p is the higher-fidelity tier — same per-second rate.
5% off Google list
Pay 5% less than Google's published Veo 3.1 API rate. $0.190/s video, $0.340/s with audio — 720p and 1080p share the same rate.
Quickstart
Get started with the Veo 3.1 API in 3 steps
From sign-up to your first Veo 3.1 API clip in under 5 minutes.
Create a RouterBase API key
Sign up and generate sk-rb-… — one key works across 200+ models on RouterBase, including the Veo 3.1 API.
POST to the Veo 3.1 API
Send a base image plus prompt in JSON. The Veo 3.1 API endpoint is async — RouterBase polls upstream until the render completes (typically 1–3 minutes), then returns a signed URL.
Inspect the result
Each Veo 3.1 API response includes generation metadata for auditing and a render URL ready to embed in your product.
Pay only for what you use
RouterBase passes through partner-tier pricing. Compared against the model's official published API rate.
| Size | Video $0.190 / s | Video + Audio $0.340 / s |
|---|---|---|
| 4s | $0.760 | $1.520 |
| 6s | $1.140 | $2.280 |
| 8s | $1.520 | $3.040 |
Your request will cost $1.520 per run (8s / Video).With $1 you can run this model approximately 1 times.
Official price = Google's published Veo 3.1 API rate ($0.20/s video, $0.40/s with audio; same rate for 720p and 1080p). RouterBase pass-through saves 5% on every Veo 3.1 API generation.
What teams build with the Veo 3.1 API
Real production loads running on the Veo 3.1 API and the RouterBase model catalog.
We swapped three providers through RouterBase in one line of code when OpenAI had its outage. Our users never noticed.
Reference-image locking on the Veo 3.1 API keeps brand assets consistent across a 200-clip product catalog. We stopped manually QA-ing every render.
Synchronized audio inside one Veo 3.1 API generation removed an entire post-processing step from our pipeline.
Plugged the Veo 3.1 API into my existing OpenAI SDK with one base URL swap — less work than writing this testimonial.
RouterBase puts 200+ models behind one key. Our research team stopped asking for new provider accounts.
Veo 3.1 API last_image keyframes give us tight control over the final frame — the difference between a placeholder render and one we'd ship to customers.
We migrated 42 services to RouterBase over a weekend. The only PR comment we got was 'wait, that's all?'.
The Veo 3.1 API is 5% below Google's published rate at every duration / audio combo — at our scale that's six figures saved per quarter on video alone.
Frequently Asked Questions
Common questions about the Veo 3.1 API.
The Veo 3.1 API is RouterBase's pass-through to Google Veo 3.1. It animates a still image with natural-language prompts into a 4/6/8-second clip at 720p or 1080p, optionally with synchronized audio.