VACE is Pruna's video generation model that creates videos from text prompts and reference images, optimized for character-driven animation and creative transformations. Reference images keep a character's appearance consistent across a sequence, and the model generates videos up to 81 frames with adjustable quality and speed modes so developers can balance turnaround against output fidelity. It supports both landscape and portrait resolutions (1280x720 and 832x480, plus 720x1280 and 480x832), with configurable sampling solvers, guidance scale, sampling steps, and seed control for reproducible results. This lets teams move from rapid testing in faster modes to higher-quality final renders. VACE works well for character animation that needs stable visual continuity, scene editing, and creative video transformations that maintain subject coherence. It performs best with detailed text prompts and high-quality reference imagery, making it suited to studios and creators that prioritize character consistency in automated video production.
Usage-based pricing, billed per generation, not by token.
| Variant | Price |
|---|---|
| Standard | $0.10 / generation |
VACE runs on 1 route through the qynio gateway. Compare residency, zero retention, and training posture at a glance — full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Price |
|---|---|---|---|---|
| US | Not by default | No | $0.10 / generation |
Each route hosting VACE has its own privacy posture, residency, and no-KYC terms. Postures are maintained by qynio with a last-verification timestamp.
Zero data retention is not on by default — abuse monitoring. No training on customer data. US; wallets; deposit available.
Call VACE through the qynio gateway with one API key. Let your coding agent set it up, or call it directly — qynio is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up qynio for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.QYN_API_KEY,baseURL: "https://api.qyn.io/v3/compat",});const completion = await client.chat.completions.create({model: "pruna/vace",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, crypto rails, pricing, and benchmarks.
