Choose flagship
Use the top model when correctness, reasoning depth, and coding reliability matter more than cost.
Veo collection
Compare Veo 3.1 variants for fast, quality, 4K, reference-frame, and native-audio video generation workflows.
| Model | Best For | Input | Output | Context | Cached |
|---|---|---|---|---|---|
Lite | Lower-cost Veo 3.1 generation for quick video drafts. | Text / image | Video | Standard | Async |
Fast | Fast generation for short-form production and rapid iteration. | Text / 2 frames | Video | Standard | Native audio |
Fast 4K | Fast Veo generation with 4K output support where available. | Text / 2 frames | Video | 4K | Native audio |
Reference | Reference-guided generation with up to three reference images. | Text / 3 refs | Video | Reference | Native audio |
Use the top model when correctness, reasoning depth, and coding reliability matter more than cost.
Use value models for assistants, automation, support, and workflows that still need strong quality.
Use lightweight models for routing, classification, extraction, and high-volume background tasks.
Prototype and ship features on Video models without managing multiple provider SDKs.
Route across the family by changing the model id — pricing, channels, and fallbacks stay on the platform.
Evaluate versions side by side, then move traffic between models without rewriting integration code.
Unified access
Keep product code stable while changing models, providers, pricing, and channel routes from the platform.
curl https://apiany.ai/v1/videos/generations \
-H "Authorization: Bearer $APIANY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "veo3-1-fast",
"prompt": "A cinematic product reveal with soft studio lighting",
"duration": "5"
}'Send requests to one OpenAI-compatible APIAny endpoint with a single API key, and set the public model id in the request body — no provider-specific SDKs required.
Usage is paid from prepaid APIAny credits at the rates shown in the comparison table. Credits never expire and there is no subscription.
Yes. Change only the model id in your request — endpoint, auth, and response format stay the same across the family.
Use the comparison table and the How to choose guidance above: pick flagship for quality, balanced for everyday production, and budget for high-volume tasks.
| Veo 3.1 Quality Quality |
| Higher-quality Veo generation for polished creative output. |
| Text / 2 frames |
| Video |
| Standard |
| Native audio |
| Veo 3.1 Quality 4K Quality 4K | Premium Veo quality mode with 4K output support. | Text / 2 frames | Video | 4K | Native audio |