Qwen instruction model for multilingual chat, reasoning, and tool use
Qwen2.5 14B Instruct by alibaba is offered by 3 providers on this page. Public prices are shown for 2 of them. Its official list price is $0.35 per 1M input tokens and $1.40 per 1M output tokens. The lowest paid channel is Alibaba (China) at $0.144 / $0.431 per 1M, about 2.4× below the list price.
The context window is 131,072 tokens, with an output limit of 8,192 tokens. It supports tool use. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Its training knowledge cuts off at 2024-04.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Alibaba (China)Official | First-party | $0.14 | $0.43 | — | — | 131,072 | 8,192 | |
| AlibabaOfficial | First-party | $0.35 | $1.40 | — | — | 131,072 | 8,192 | |
| DigitalOcean qwen-2.5-14b-instruct | Cloud | — | — | — | — | 131,072 | 131,072 | 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.