Wan 2.6 Reference-to-Video takes a reference video of a subject and generates new footage in which that subject's appearance, voice, and manner carry over. Reference-driven generation was the headline addition of Alibaba's Wan 2.6 series in December 2025, pitched as letting anyone appear in generated video as themselves. A text prompt describes the new motion and setting while the reference clip supplies identity, and output runs 2 to 10 seconds at 720p or 1080p with synchronized audio. It suits presenter and spokesperson videos, consistent characters across a series, and personalized content built around a real subject.
Usage-based pricing, billed by the second and tiered by variant, not by token.
| Variant | Price |
|---|---|
| 1080p | $0.15 / sec |
| 720p | $0.10 / sec |
Wan 2.6 Reference-to-Video 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 |
|---|---|---|---|---|
| Multi | Not by default | No | from $0.10 / sec |
Wan 2.6 Reference-to-Video runs on a single route through the qynio gateway today, so its availability is that provider's availability.
Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. .
Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider qynio monitors.
Each route hosting Wan 2.6 Reference-to-Video 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. GLOBAL; wallets; deposit available.
Call Wan 2.6 Reference-to-Video 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: "alibaba:global/wan2.6-r2v",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, crypto rails, pricing, and benchmarks.
