Qwen3 VL
language modelAlibaba (Qwen)
Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon... License: apache-2.0.
Key facts
| Made by | Alibaba (Qwen) |
|---|---|
| Type | language model |
| Released | September 23, 2025 |
| License | apache-2.0 |
| Reads at once | 262,144 tokens |
| Price (API, per million tokens) | $0.25 in · $0.75 out |
| Input → output | image, text → text |
| Sizes | 8B, 30B, 235B, 4B, 2B |
| Downloads (recent) | 6.1M |
| Likes on Hugging Face | 1.2K |
Questions about Qwen3 VL
Who makes Qwen3 VL?
Qwen3 VL is made by Alibaba (Qwen).
When was Qwen3 VL released?
We first saw Qwen3 VL listed on September 23, 2025.
How much does Qwen3 VL cost?
Through OpenRouter it costs $0.25 per million input tokens and $0.75 per million output tokens. Prices change, so check the provider before you build on it.
How much text can Qwen3 VL read at once?
Up to 262,144 tokens, roughly 196.6K 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).