Can Veo 3 generate videos from a text description?

Yes. Veo 3 lists text as an input and video as an output, so a text description is enough to start a generation.

Can Veo 3 turn a still image into a video?

Yes. Veo 3 accepts image input, so a still image can be used as the starting frame.

Can videos generated by Veo 3 include sound?

Yes. Veo 3 declares audio together with video in its output modalities, so generated clips can carry sound.

When was Veo 3 released as a video generation model?

Veo 3 was released on 2025-09-09.

Can Veo 3 create portrait-oriented videos?

Yes. Veo 3 lists portrait aspect ratios (9:16), so vertical video is supported.

Can Veo 3 generate background music for a video?

The output of Veo 3 includes an audio track alongside the video, so a generated clip can carry music or other audio.

Can Veo 3 generate speech for characters in a video?

Veo 3 returns audio together with the video; whether that audio is speech depends on the prompt and the provider’s implementation, so confirm dialogue support in the provider documentation.

Model detail

Veo 3

Provided by Google

Pay-as-you-go

Google's Veo 3 generates short video clips with native audio from text prompts or image inputs.

Model specs

Model ID: veo-3.0-generate-001

Context length: –
Max output: –
I/O modalities
Released: 2025-09

API endpoints

One MixRoute gateway, OpenAI-compatible

Gemini /v1beta/models/{model}:generateContent POST
OpenAI-compatible /v1/chat/completions POST

Pricing

Flat rate, unit: /1M Tokens

Input

$75.0000 /1M Tokens

Completion

$75.0000 /1M Tokens

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

Google's Veo 3 generates short video clips

Google's Veo 3 generates short video clips with native audio from text prompts or image inputs.

What should you check before using it?

Check duration, resolution, and aspect ratio limits

Model type: video. Verify supported features and quotas with the provider documentation. Released 2025-09-09.

Why use it through MixRoute?

Veo 3 takes text and images on one route

Text and image inputs share the same route and the same key. MixRoute serves Veo 3 on the OpenAI-compatible endpoint /v1/chat/completions; point your existing client at https://api.mixroute.ai/v1 with the model ID veo-3.0-generate-001 and re-run your integration tests.

Capabilities & compatibility

Unconfirmed capabilities stay "Unknown," no guesses

Vision input

Veo 3 can process image inputs alongside text.

EX Pass a base64-encoded image in a image_url content part alongside text messages.

Token cost estimator

Live estimate from this page's pricing, not an actual bill

Input tokens

Output tokens

Requests / month

Cache hit rate –

This model has no cache-read price; caching is not counted

FAQ

Veo 3 is a video generation model from Google. It accepts text, image and returns video, audio.

Get started

01

Create an API key

Generate a key in the Console; one key calls every model.
02

Set the base URL

Fully OpenAI SDK-compatible; just swap the URL to connect.

https://api.mixroute.ai/v1
03

Specify the model ID

In the request's model field, enter:

veo-3.0-generate-001

Create an API key

New users get $5 in free credits

Test this model and alternate routes with the same request format

Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.

Create an API key View integration docs