Qwen: Qwen3 VL 8B Thinking
Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and...
Everything else
| Max output | 33K |
|---|---|
| Input / 1M | $0.18 |
| Output / 1M | $2.10 |
| Cache read / 1M | — |
| Cache write / 1M | — |
| 1M in + 1M out | $2.28 |
| Takes | image, text |
| Returns | text |
| Tools | yes |
| Reasoning | always on |
| Open weights | yes |
| Released | 2025-10-14 |
| Knowledge cutoff | — |
| Retires | — |
| Catalog id | qwen/qwen3-vl-8b-thinking |
Using it
In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.