# Veo 3.1 fast

> Veo 3.1 fast is a proprietary video generation model from Google DeepMind, released on 15 Oct 2025. It accepts text, images and video and generates video, with a 480-token context window and up to 8K output tokens per response.

Source page: https://www.aimodel.directory/models/veo-3-1-fast-generate-preview
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Google DeepMind
- **Release date:** 15 Oct 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/veo-3.1-fast-generate-preview.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/veo-3.1-fast-generate-preview.toml)
- **Weights:** Proprietary (API only) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/veo-3.1-fast-generate-preview.toml)
- **Context window:** 480 (480 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/veo-3.1-fast-generate-preview.toml)
- **Max output:** 8K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/veo-3.1-fast-generate-preview.toml)
- **Input:** Text, images and video (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/veo-3.1-fast-generate-preview.toml)
- **Output:** Video (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/veo-3.1-fast-generate-preview.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/veo-3.1-fast-generate-preview.toml)
- **Tool calling:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/veo-3.1-fast-generate-preview.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Gemini API | – | – | – | 480 |

## FAQ

### What is the context window of Veo 3.1 fast?

Veo 3.1 fast has a context window of 480 tokens (480) and can generate up to 8,192 tokens in a single response, according to models.dev.

### Is Veo 3.1 fast open source?

No. Veo 3.1 fast is a proprietary model; Google DeepMind has not released its weights. It is available through APIs including Gemini API.

### When was Veo 3.1 fast released?

Google DeepMind released Veo 3.1 fast on 15 Oct 2025, according to models.dev.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Veo 3.1 fast", https://www.aimodel.directory/models/veo-3-1-fast-generate-preview