Veo 3.1 lite
by Google · family veo · listed Mar 2026V
Video model for prompt-guided generation, editing, and motion workflows
Current rates USD per 1M tokens
Input—
Output—
Cache read—
Cache write—
Against the market
On the record
- Model id
veo-3.1-lite-generate-preview- Context window
- 480 tokens
- Max output
- 8K tokens
- Input modalities
- text, image
- Output modalities
- video
- Reasoning
- no
- Tool calls
- no
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2026-03-31
- Last updated
- 2026-03-31
- Provider docs
- ai.google.dev/gemini-api/docs/models