wan2.7-r2v

by Qwen

Wanxiang 2.7 — reference-driven video generation: more stable references for characters, props, and scenes; supports up to five mixed image/video references; supports audio/timbre references; combined with foundational capability upgrades to deliver stronger performance.

API Pricing

Input

$2 / 1M tokens

Specifications

Modalities

text, video

Use wan2.7-r2v via the AIHubMix unified API — one interface for every major LLM.