How do you start calling Veo 3.1?

Set the model parameter to “veo-3.1-generate-preview” and use your MixRoute API key.

Can Veo 3.1 generate videos from a text description?

Yes. Veo 3.1 lists text as an input and video as an output, so a text description is enough to start a generation.

Can Veo 3.1 turn a still image into a video?

Yes. Veo 3.1 accepts image input, so a still image can be used as the starting frame.

Can Veo 3.1 use an existing video as a reference?

Yes. Veo 3.1 accepts video input, so an existing clip can be supplied as a reference.

Can videos generated by Veo 3.1 include sound?

Yes. Veo 3.1 declares audio together with video in its output modalities, so generated clips can carry sound.

How is video generation with Veo 3.1 billed?

Video generation with Veo 3.1 is billed per second at 0.60 USD, in batch mode. Different resolutions or durations can land on different rates.

Can Veo 3.1 create portrait-oriented videos?

Yes. Veo 3.1 lists portrait aspect ratios (9:16), so vertical video is supported.

Model detail

Veo 3.1

Provided by Google

Pay-as-you-go

Google's state-of-the-art video generation model, built for maximum visual fidelity in final production cuts. Veo 3.1 generates high-quality 1080p video from text or image prompts with native synchronized audio — including dialogue, ambient effects, and background sound. Supports scene extension (up to 20 chained clips for 140+ second narratives), frames-to-video transitions between two images, vertical video for Shorts, and 4K upscaling.

Model specs

Model ID: veo-3.1-generate-preview

Context length: –
Max output: –
I/O modalities
Released: 2026-03

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?

Video generation for professional-grade 4K video generation

Veo 3.1 — Cinematic engine for high-end creative storytelling and experimental video production, 4K output with synchronized audio.

What should you check before using it?

4K cinematic output with synchronized audio

Video Generation. Released 2026-01.

Why use it through MixRoute?

Available through MixRoute's OpenAI-compatible endpoint

Use the Google Gen AI SDK or call through MixRoute. Set the model parameter to "veo-3.1-generate-preview".

Capabilities & compatibility

Unconfirmed capabilities stay "Unknown," no guesses

Vision input

Veo 3.1 can process image inputs alongside text.

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

OpenAI SDK

Call Veo 3.1 through MixRoute's OpenAI-compatible endpoint.

EX Change base_url to https://api.mixroute.ai/v1; everything else follows the OpenAI style.

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 3.1 is a state-of-the-art cinematic video generation engine for high-end creative storytelling and experimental video production. 4K output with synchronized 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-3.1-generate-preview

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