Google Veo release notes on a new model or snapshot
4 Google Veo entries on a new model or snapshot, 9 April 2025 to 31 March 2026, across Veo 2, Veo 3, Veo 3.1 and Veo 3.1 Lite. The latest: Veo 3.1 Lite preview is released as a lower-cost tier for high-volume use. From 1 source page, read 2026-09-25; no maker pays to be listed.
| Line | Entries |
|---|---|
| Adobe Firefly Video | 1 |
| Amazon Nova Reel | 2 |
| Gemini Omni | 4 |
| Google Veo | 4 |
| Grok Imagine | 3 |
| HappyHorse | 2 |
| Kling AI | 10 |
| LTX | 3 |
| Luma Ray | 3 |
| Midjourney video | 1 |
| MiniMax Hailuo | 5 |
| PixVerse | 5 |
| Runway | 9 |
| Seedance | 4 |
| Sora | 2 |
| Vidu | 2 |
| Wan | 10 |
Inclusion rule. Lines with at least one entry of this kind. Order. Alphabetical by line.
The register holds 4 Google Veo entries on a new model or snapshot; the first is dated 9 April 2025.
1The entries
9 April 2025, Veo 2
Released veo-2.0-generate-001 , a generally available (GA) text- and image-to-video model
Google, Gemini API changelog
- April 9Veo 2 becomes generally available in the Gemini API for text and image input2025
17 July 2025, Veo 3
Launched veo-3.0-generate-preview , the latest update to Veo introducing video with audio generation.
Google, Gemini API changelog
- July 17Veo 3 preview arrives in the Gemini API and generates sound with the picture2025
It came 99 days after the previous one.
15 October 2025, Veo 3.1
Released Veo 3.1 and 3.1 Fast models in public preview, with new features including: Extending Veo-created videos. Referencing up to three images to generate a video. Providing first and last frame images to generate videos from.
Google, Gemini API changelog
- October 15Veo 3.1 preview adds extension, up to three reference images and first-and-last-frame input2025
It came 90 days after the previous one.
31 March 2026, Veo 3.1 Lite
Launched Veo 3.1 Lite Preview, veo-3.1-lite-generate-preview , our most cost-efficient video generation model
Google, Gemini API changelog
- March 31Veo 3.1 Lite preview is released as a lower-cost tier for high-volume use2026
The gap from the previous entry: 167 days.
2The same kind of change in other lines
- Adobe Firefly Video: 1 entry, October 2024
- Amazon Nova Reel: 2 entries, December 2024 to April 2025
- Gemini Omni: 4 entries, June 2026 to August 2026
- Grok Imagine: 3 entries, January 2026 to August 2026
- HappyHorse: 2 entries, April 2026 to June 2026
- Kling AI: 10 entries, November 2024 to September 2026
- LTX: 3 entries, October 2025 to August 2026
- Luma Ray: 3 entries, September 2025 to June 2026
- Midjourney video: 1 entry, June 2025
- MiniMax Hailuo: 5 entries, February 2025 to August 2026
- PixVerse: 5 entries, August 2025 to April 2026
- Runway: 9 entries, July 2024 to August 2026
- Seedance: 4 entries, April 2026 to August 2026
- Sora: 2 entries, October 2025 to January 2026
- Vidu: 2 entries, September 2025 to September 2026
- Wan: 10 entries, January 2025 to August 2026
Google Veo, every entry · New models and snapshots, every line · Veo 3 · Veo 3.1
3Notes read
- Google, Gemini API changelog, read 2026-09-25
4A pipeline on current models
Release notes such as “Google Veo” matter once a pipeline runs the models; SceneMixer's guides describe how it does:
It is one of the 2K tiers, with SeedDream 5.0 Lite; the Qwen tiers render at lower pixel counts.
SceneMixer, SeedDream 5.0 Pro — “Is this the highest-resolution image tier?” (read 2026-10-13)
The default and Pro Qwen tiers follow the presets well; SeedDream Pro for 2K.
SceneMixer, Anime and stylised looks across the tiers — “Which image tier is best for anime sheets?” (read 2026-10-13)