Qwen vision-language model for visual reasoning, documents, and agent tasks
Qwen/Qwen3-VL-30B-A3B-Thinking by alibaba is offered by 6 providers on this page. Public prices are shown for 5 of them. Its reference price is $0.20 per 1M input tokens and $2.40 per 1M output tokens. The lowest paid channel is NovitaAI at $0.20 / $1.00 per 1M, about 1.4× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
The context window is 131,072 tokens at the reference host, but hosts report different limits, from 128,000 to 262,144, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and Video. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-03-31.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| NovitaAI | Gateway | $0.20 | $1.00 | — | — | 131,072 | 32,768 | |
| SiliconFlow Qwen/Qwen3-VL-30B-A3B-Thinking | Cloud | $0.29 | $1.00 | — | — | 262,000 ⚠ | 262,000 | |
| SiliconFlow (China) Qwen/Qwen3-VL-30B-A3B-Thinking | Cloud | $0.29 | $1.00 | — | — | 262,000 ⚠ | 262,000 | |
| OpenRouter | Gateway | $0.20 | $2.40 | — | — | 262,144 ⚠ | 32,768 | |
| Kilo Gateway | Gateway | $0.20 | $2.40 | — | — | 131,072 | 32,768 | |
| Qiniu | Gateway | — | — | — | — | 128,000 ⚠ | 32,000 | hostTable.undisclosed |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
3 / 6 providers expose no reasoning control (reasoning_options: []).