Qwen instruction model for multilingual chat, reasoning, and tool use
Qwen Plus by alibaba is offered by 11 providers on this page. Its official list price is $0.40 per 1M input tokens and $1.20 per 1M output tokens. The lowest paid channel is Merge Gateway at $0.115 / $0.287 per 1M, about 3.5× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
The context window is 1,000,000 tokens at the reference host, but hosts report different limits, from 131,072 to 1,000,000, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-04.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Merge Gateway | Gateway | $0.12 | $0.29 | $0.023 | — | 1,000,000 | 250,000 | |
| Alibaba (China)Official | First-party | $0.12 | $0.29 | $0.012 | $0.14 | 1,000,000 | 32,768 | |
| Ofox | Gateway | $0.12 | $0.29 | $0.023 | — | 1,000,000 | 32,768 | |
| Ofox | Gateway | $0.12 | $0.29 | $0.023 | — | 1,000,000 | 32,000 | |
| Kilo Gateway | Gateway | $0.26 | $0.78 | $0.052 | $0.33 | 1,000,000 | 32,768 | |
| OpenRouter | Gateway | $0.26 tiered >256K: $0.78 | $0.78 | $0.052 | $0.33 | 1,000,000 | 32,768 | |
| NanoGPT | Gateway | $0.40 | $1.20 | $0.20 | — | 995,904 ⚠ | 32,768 | |
| LLMTR | Gateway | $0.40 | $1.20 | — | — | 1,000,000 | 32,768 | |
| AlibabaOfficial | First-party | $0.40 | $1.20 | — | — | 1,000,000 | 32,768 | |
| DevPass (LLM Gateway) | Gateway | $0.40 | $1.20 | $0.08 | $0.50 | 131,072 ⚠ | 32,768 | |
| LLM Gateway | Gateway | $0.40 | $1.20 | $0.08 | $0.50 | 131,072 ⚠ | 32,000 |
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.
2 / 11 providers expose no reasoning control (reasoning_options: []).