Qwen: Wan v2.7 Reference-to-Video
Wan v2.7 Reference-to-Video is a video generation model from Qwen released on Apr 7, 2026. It reads text and writes video.
- Modalities
- In / out price
- n/a
- Context
- n/a
- Max output
- n/a
- Released
- Apr 7, 2026
- Knowledge cutoff
- n/a
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
Supported request parameters
What you can set when you call Wan v2.7 Reference-to-Video through an OpenAI compatible API.
- Temperature
temperature
More from Qwen
- 262K context
Reads text and images. Tool calling, reasoning.
by qwenOct 5, 2026$0.10/M input tokens$0.60/M output tokens
- 262K context
Reads text and images. Tool calling, reasoning.
by qwenOct 5, 2026$0.10/M input tokens$0.60/M output tokens
- 262K context
Reads text and images. Tool calling, reasoning.
by qwenOct 5, 2026$0.10/M input tokens$0.60/M output tokens
- 262K context
Reads text and images. Tool calling, reasoning.
by qwenOct 5, 2026$0.10/M input tokens$0.60/M output tokens
- 262K context
Reads text and images. Tool calling, reasoning.
by qwenOct 5, 2026$0.10/M input tokens$0.60/M output tokens
- 262K context
Reads text and images. Tool calling, reasoning.
by qwenOct 5, 2026$0.10/M input tokens$0.60/M output tokens
Wan v2.7 Reference-to-Video questions
Is Wan v2.7 Reference-to-Video open source?
No. Qwen serves it through an API only, so you cannot download the weights or host it yourself.
When was Wan v2.7 Reference-to-Video released?
Apr 7, 2026.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.
Building on Wan v2.7 Reference-to-Video?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting