Google DeepMind
Veo 3.1 Fast Preview
Image inputVideo inputVideo output
Video model for prompt-guided generation, editing, and motion workflows
- Released
- 1y ago
- Pricing
- Not published
Sources:models.dev
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
No benchmark results have been matched to this model yet.
Specifications
- Developer
- Google DeepMind
- Model family
- Veo
- Type
- Video generation
- Predecessor
- —
- Successor
- —
- Released
- October 15, 2025
- Model ID
google/veo-3.1-fast-generate-preview- Openness
- Closed
- License
- —
- Input modalities
- text, image, video
- Output modalities
- video
- Modality
- text+image+video->video
- Hugging Face
- —
- Source freshness
- Metadata synced Oct 8, 2026, 10:17 PM UTC
Additional source evidence
- Source model
- google/veo-3.1-fast-generate-preview
- Source family
- veo
- Last updated
- 2026-01-01
- Model context
- 1K
- Model output limit
- —
- Open weights
- No
- File attachments
- Yes
- Reasoning
- No
- Tool calling
- No
- Temperature control
- No
Complete source record (JSON)
{
"id": "google/veo-3.1-fast-generate-preview",
"name": "Veo 3.1 Fast Preview",
"description": "Video model for prompt-guided generation, editing, and motion workflows",
"family": "veo",
"last_updated": "2026-01-01",
"attachment": true,
"reasoning": false,
"tool_call": false,
"temperature": false,
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"video"
]
},
"limit": {
"context": 1024,
"output": 0
},
"release_date": "2025-10-15",
"open_weights": false
}Infrastructure
Provider availability
Provider-specific media pricing is not available in the imported source data yet.
Text provenance
Gemini app/webGoogle SynthID text watermarking
Google DeepMind says text generated in the Gemini app and web experience is watermarked with SynthID by adjusting token probabilities.
Official explanation