Qwen3 VL 30B A3B Thinking
Open weightVisionToolsQwen · Released October 2025 · Knowledge cutoff March 2025
Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...
It is part of Alibaba's Qwen family, a broad catalog where Max leads on capability, Plus balances cost, and Flash and the open-weight sizes cover high-volume work.
Facts and pricing
- Provider
- Qwen
- Context window
- 131K tokens
- Input price
- 2.2 credits / 1M tokens ($0.20 raw)
- Output price
- 26.4 credits / 1M tokens ($2.40 raw)
- Vision (image input)
- Yes
- Tool calling
- Yes
- Extended reasoning
- No
Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.
Try Qwen3 VL 30B A3B Thinking now
What Qwen3 VL 30B A3B Thinking is best for
- Everyday chat and drafting on an open-weight model with transparent lineage
- Working with images: screenshots, charts, photos and scanned documents alongside text
- Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows
Example prompts
Prompts that suit a open weight model like Qwen3 VL 30B A3B Thinking:
- Draft a project update from these rough notes
- Explain how HTTPS works to a curious teenager
- Turn this list of features into a changelog entry
- Brainstorm objections to this proposal and how to answer them
Qwen family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| Qwen3.8 Flash | 1M | 1.7 | 5.2 | August 2026 |
| Qwen3.8 27B | 1M | 4.6 | 33.0 | August 2026 |
| Qwen3.8 2.4T A95B (batch) | 1.0M | 22.0 | 66.0 | August 2026 |
| Qwen3.8 2.4T A95B | 1M | 22.0 | 66.0 | August 2026 |
| Qwen3.7 Flash | 1M | 0.33 | 1.4 | July 2026 |
| Qwen3.7 Plus | 1M | 3.5 | 14.1 | June 2026 |
| Qwen3.7 Max | 1M | 16.2 | 48.7 | May 2026 |
| Qwen3.5 Plus 2026-04-20 | 1M | 3.3 | 19.8 | April 2026 |
| Qwen3.6 Flash | 1M | 2.1 | 12.4 | April 2026 |
| Qwen3.6 35B A3B | 262K | 1.1 | 9.9 | April 2026 |
Frequently asked questions
- What is Qwen3 VL 30B A3B Thinking?
- Qwen3 VL 30B A3B Thinking is an AI model by Qwen. Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...
- How much does Qwen3 VL 30B A3B Thinking cost on Zeplik?
- Input tokens cost 2.2 credits per million and output tokens 26.4 credits per million (1 credit = $0.10; the raw provider rates are $0.20 and $2.40 per million). New accounts start with free credits.
- How long can a conversation with Qwen3 VL 30B A3B Thinking be?
- Qwen3 VL 30B A3B Thinking has a 131K-token context window (131,072 tokens), which covers the conversation plus any documents you attach.
- Does Qwen3 VL 30B A3B Thinking support images and tools?
- Qwen3 VL 30B A3B Thinking accepts image input and supports tool calling.
Related models
Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.
Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...
Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...
Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...
Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...
Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...
More you can do with Qwen3 VL 30B A3B Thinking
- 465 AI skillsReady-to-run expert methods for writing, data, code and more, each running on Qwen3 VL 30B A3B Thinking or any model you pick.
- 997 integrationsConnect Gmail, Slack, GitHub, Notion and hundreds more so the assistant can work in your apps.
- Simple pricingPlus, Pro and Max plans with a monthly credit allowance that works across every model.