Qwen2.5 VL

language modelAlibaba (Qwen)

Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images. License: apache-2.0.

Key facts

Made byAlibaba (Qwen)
Typelanguage model
ReleasedJanuary 26, 2025
Licenseapache-2.0
Reads at once128,000 tokens
Price (API, per million tokens)$0.8 in · $1 out
Input → outputtext, image → text
Sizes72B, 7B, 3B, 32B
Downloads (recent)5.4M
Likes on Hugging Face1.8K

Questions about Qwen2.5 VL

Who makes Qwen2.5 VL?

Qwen2.5 VL is made by Alibaba (Qwen).

When was Qwen2.5 VL released?

We first saw Qwen2.5 VL listed on January 26, 2025.

How much does Qwen2.5 VL cost?

Through OpenRouter it costs $0.8 per million input tokens and $1 per million output tokens. Prices change, so check the provider before you build on it.

How much text can Qwen2.5 VL read at once?

Up to 128,000 tokens, roughly 96K words.

More from Alibaba (Qwen)

Other language models

Modelcast collects this page automatically from public sources (OpenRouter, Hugging Face). Facts are copied from those sources, not written by the maker. Not affiliated with Alibaba (Qwen).