The Veo 3 API turns a one-line prompt into our launch teasers — fast iteration when we are A/B-testing creatives at scale.
The Veo 3 API generates videos from natural-language prompts (Google Veo 3) — 8-second clips at 720p or 1080p, optional synchronized audio, 16:9 or 9:16 aspect ratios — all through one REST endpoint, priced 5% below Google's Veo 3 API list.
Input
The text prompt sent to the model
Output
SampleRun the model to replace this previewVeo 3 API: Text to Video
Use the Veo 3 API to generate videos from natural-language prompts.
The Veo 3 API generates videos from natural-language prompts (Google's original Veo video model). Renders 8-second clips at 720p or 1080p, with optional synchronized audio, and 16:9 or 9:16 aspect ratios — all through one REST endpoint.
The Veo 3 API keeps the surface compact: prompt + audio toggle. Pricing is 5% below Google's published Veo 3 API rate — $1.520 per 8-second clip without audio, $3.040 with synchronized audio. 720p and 1080p share the same per-clip 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 API
From compact surface to per-clip pricing — what the Veo 3 API gets right.
Natural-language video
Describe the scene in plain English; the Veo 3 API renders an 8-second clip from the prompt — no storyboard, no timeline editing.
Audio generation
Toggle generate_audio and the Veo 3 API produces synchronized audio in the same generation — no separate TTS or post-edit pass.
720p / 1080p, 8-sec clips
The Veo 3 API renders 8-second clips at 720p (default) or 1080p — same per-clip rate. Switch resolution per call without recoding.
Aspect-ratio per call
16:9 (landscape) for hero banners or 9:16 (portrait) for vertical reel content. Set aspect per Veo 3 API call as a single string parameter.
Safety controls
person_generation toggles (allow_adult / dont_allow / allow_all) and negative_prompt support let the Veo 3 API enforce content guidelines per workspace.
5% off Google list
Pay 5% less than Google's published Veo 3 API rate. $1.520 per 8s clip ($3.040 with audio) — 720p and 1080p share the same rate.
Quickstart
Get started with the Veo 3 API in 3 steps
From sign-up to your first Veo 3 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 API.
POST to the Veo 3 API
Send a prompt in JSON. The Veo 3 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 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.
| Resolution | RouterBase | Official | Save |
|---|---|---|---|
| resolution=720p · sound=false | $1.520 | −5% | |
| resolution=720p · sound=true | $3.040 | −5% | |
| resolution=1080p · sound=false | $1.520 | −5% | |
| resolution=1080p · sound=true | $3.040 | −5% |
Your request will cost $1.520 per run (resolution=720p · sound=false).With $1 you can run this model approximately 1 times.
What teams build with the Veo 3 API
Real production loads running on the Veo 3 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.
For prompt-driven motion the simpler Veo 3 API surface (prompt + audio toggle) is exactly what we need — no extra knobs to misconfigure.
The Veo 3 API delivers synchronized audio inside one generation — removed an entire post-processing step from our pipeline.
Plugged the Veo 3 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.
720p and 1080p at the same per-clip rate on the Veo 3 API means we sample at low res and finalise at HD without budget surprises.
We migrated 42 services to RouterBase over a weekend. The only PR comment we got was 'wait, that's all?'.
The Veo 3 API is 5% below Google's published rate on every clip — at our scale that's six figures saved per quarter on video alone.
Frequently Asked Questions
Common questions about the Veo 3 API.
The Veo 3 API is RouterBase's pass-through to Google Veo 3 — the original Veo video model. The text-to-video variant generates an 8-second clip at 720p or 1080p from a natural-language prompt, optionally with synchronized audio.