Large open Qwen MoE for multilingual reasoning, coding, and tool useQwen3 235B-A22B by alibaba is offered by 8 providers on this page. Its official list price is $0.70 per 1M input tokens and $2.80 per 1M output tokens. The lowest paid channel is Jiekou.AI at $0.20 / $0.80 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 131,072 tokens at the reference host, but hosts report different limits, from 40,960 to 131,072, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-04.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Jiekou.AI qwen/qwen3-235b-a22b-fp8 | Gateway | $0.20 | $0.80 | — | — | 40,960 ⚠ | 20,000 | |
| Hugging Face Qwen/Qwen3-235B-A22B | Cloud | $0.20 | $0.80 | — | — | 40,960 ⚠ | 16,384 | |
| Alibaba (China)Official | First-party | $0.29 | $1.15 | — | — | 131,072 | 16,384 | deprecated |
| Merge Gateway | Gateway | $0.29 | $1.15 | $0.057 | — | 131,072 | 32,768 | |
| Qiniu | Gateway | $0.29 | $1.16 | — | — | 128,000 ⚠ | 32,000 | deprecated |
| 302.AI | Gateway | $0.29 | $2.86 | — | — | 128,000 ⚠ | 16,384 | |
| Moneo qwen3-235b:web | Gateway | $0.40 | $3.00 | — | — | 128,000 ⚠ | 16,384 | |
| AlibabaOfficial | First-party | $0.70 | $2.80 | — | — | 131,072 | 16,384 | deprecated |
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 / 8 providers expose no reasoning control (reasoning_options: []).
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Aider Polyglot | — | 59.6 | percent correct | Source ↗ |
| SWE-Bench Pro | dataset: public | 21.41 | resolve rate | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.