Qwen VL Max
qwen/qwen-vl-maxVision-language specialist strong on documents, charts and OCR-heavy enterprise inputs.
Model overview
Context window
128K
tokens
Input price
—
quoted on request
Output price
—
quoted on request
Weekly volume
—
tokens / week
Open weights
No
API only
Capabilities
3
of 11 tags
Description
Qwen VL Max is a vision model from Alibaba Qwen. Webparam does not stock this model yet and can source it on request — tell us what you need it for and we will come back with availability and a price. Alibaba Qwen’s stated focus is the broadest open model family in the world. The weights are not published, so it is API-only.
Capabilities
- Vision input
- Accepts images alongside text in the prompt.
- Tool calling
- Calls functions you define and returns their arguments as structured data, the basis of agents.
- Streaming
- Emits tokens as they are generated, so answers appear progressively rather than all at once.
Strengths & weaknesses
Strengths
- Excellent document and table understanding
- Strong CJK OCR
- Reasonable pricing for vision
Weaknesses
- Natural-scene reasoning trails document skill
- No JSON mode
Pricing
| Rate | Price | Unit |
|---|---|---|
| Input | — quoted on request | — |
| Output | — quoted on request | — |
This model is not provisioned yet; the rate is quoted on request.
Context window
128Ktokens
covers prompt and response together, so a long input leaves less room for the answer.
Supported features
| Feature | Support |
|---|---|
| Tool calling | Supported |
| JSON mode | Not supported |
| Streaming | Supported |
| Vision input | Supported |
| Audio input | Not supported |
| Long context | Not supported |
| Open weights | Not supported |
| Reasoning | Not supported |
| Fine-tunable | Not supported |
| Batch | Not supported |
| Caching | Not supported |
Example use cases
Invoice and form extraction
Chart reading
Screenshot QA
Comparison
Compare against anything →| Attribute | Qwen VL Max | Qwen3 Max | Kimi VL |
|---|---|---|---|
| Context window | 128K | 256K | 128K |
| Input price | R0.00 | R0.00 | R0.00 |
| Output price | — not charged | — not charged | — not charged |
| Tool calling | Supported | Supported | Not supported |
| JSON mode | Not supported | Supported | Not supported |
| Vision input | Supported | Supported | Supported |
| Open weights | Not supported | Not supported | Not supported |
| Prompt caching | Not supported | Supported | Not supported |
Best value in each row is highlighted. Blank cells are facts the supplier does not publish, not zeroes.
Provider information
View Alibaba Qwen →Alibaba Qwen · 通义千问 · Hangzhou, China · est. 2023 (Model lab; parent Alibaba founded 1999)
Alibaba's Qwen family spans every size class from edge models to frontier MoE systems, most released with open weights. Its breadth (chat, coding, vision, embeddings) and permissive licensing made it the default base model for much of the global open-source ecosystem.
Recent releases
Documentation
Frequently asked questions
Input is billed at R0.00 per 1M tokens, and there is no separate output charge. Every figure on this page is an illustrative placeholder.
No. Qwen VL Max is served through its provider's API only; the weights are not published, so self-hosting is not an option.
Prompt and response share one window: Qwen VL Max accepts up to 128K tokens in total, so a long input leaves less room for the answer. The median across vision models is 128K. Recall is strongest well inside the limit. Test at your real prompt depth before relying on the ceiling.
Qwen3 Max is the closest neighbour in the catalogue, with 256K of context at R0.00 per 1M tokens in. Put both in a comparison before wiring a fallback chain, so the trade-off is a decision rather than a default.