Veo 3.1 API
Google's Veo 3.1 turns a prompt or a start frame into short clips with dialogue, ambience and effects in sync.
Prices are temporarily unavailable — refresh the page in a minute.
What Veo 3.1 is good for
Veo 3.1 is Google's video model with native audio, so speech, ambient sound, and effects arrive matched to the action. It adds control over how a clip opens and closes through start and end frames, and it can hold a character's look across shots using several reference images. It suits short ads, social posts, and story scenes where sound and continuity matter.
- Vertical 9:16 social ads with spoken lines and matching sound effects
- Clips that open on a specific frame, such as your product photo
- Quick concept tests in Fast mode before a final Quality render
- Product shots in 4K with accurate lighting and smooth camera moves
Veo 3.1 pricing
Same price for text to video, image to video and reference to video — unless the option says otherwise.
| Option | Price, USD | Video Blade tokens |
|---|---|---|
| Lite · 720p | tokens | |
| Lite · 1080p | tokens | |
| Fast · 720p | tokens | |
| Fast · 1080p | tokens | |
| Lite · 4K | tokens | |
| Fast · 4K | tokens | |
| Quality · 720ptext to video, image to video — same price | tokens | |
| Quality · 1080ptext to video, image to video — same price | tokens | |
| Image to video · Quality · 4K | tokens | |
| Text to video · Quality · 4K | tokens |
Prices are per clip (same price for 4–8 s) and live from our price list. Tokens are held when a run starts and settled to what was actually used; a failed run costs nothing.
Use Veo 3.1 from your AI agent
- Create an account on Video Blade and pick a plan — from .
- Copy the agent link from your dashboard into Claude Code, Codex or Cursor.
- Say the phrase below — the agent shows the price, runs Veo 3.1 and saves the result.
Make a 6-second 16:9 clip at 1080p with Veo 3.1 Quality: a chef tosses vegetables in a flaming wok, oil sizzling, busy kitchen chatter behind.
This request ≈ · Quality · 1080p
Veo 3.1 FAQ
How much does Veo 3.1 cost?
8-second clip from . Prices are live from our price list, and you see the exact price before anything runs.
What is the difference between Veo 3.1 Fast and Veo 3.1 Quality?
Fast is tuned for quick turnaround, so it fits social posts, ad variations, and trying out ideas. Quality aims for richer detail, smoother motion, and more accurate lighting, which makes it the better choice for finished, professional pieces.
What clip lengths, aspect ratios, and resolutions does Veo 3.1 support?
Each Veo 3.1 clip runs 4, 6, or 8 seconds. You can choose 16:9 for widescreen, 9:16 for vertical feeds, or Auto, and render at 720p, 1080p, or 4K depending on where the clip will be shown.
How do I use Veo 3.1 from my AI agent?
Create a Video Blade account, paste the agent link from your dashboard into Claude Code, Codex or Cursor, and ask: “Make a 6-second 16:9 clip at 1080p with Veo 3.1 Quality: a chef tosses vegetables in a flaming wok, oil sizzling, busy kitchen chatter behind.” The agent runs Veo 3.1 (model id veo3-generate-veo-3-video), shows the price before it starts and saves the result to your dashboard.
How is Veo 3.1 billed?
Per clip: every option (mode and resolution) has its own fixed price, whatever the clip length. Tokens are held when a run starts and settled to what was actually used; a failed run costs nothing. Current prices are shown on this page.
What settings does Veo 3.1 support?
Aspect ratio: 16:9, 9:16 or Auto. Resolution: 720p, 1080p or 4K. Length: 4 s, 6 s or 8 s.
Veo 3.1 in the Video Blade API
veo3-generate-veo-3-videoYour agent sends this model id with the order; the result lands in the project, and every request is in your generation log with its price.
Through Video Blade a clip is ordered from a prompt with an optional start frame (and an end frame where the model takes one), in the lengths and resolutions the model offers.
POST /api/v1/projects/{id}/video-sessions/{item_id}/generate
{"prompt": "…", "model": "veo3-generate-veo-3-video", "duration": …, "start_url": "https://…"}
Similar models
Seedance 2.5
Text to videoImage to video 8-second clip from · per second
Seedance 2.0
Text to videoImage to video 8-second clip from · per second
Wan 3.0 Video
Text to videoImage to video 8-second clip from · per second