Qwen instruction model for multilingual chat, reasoning, and tool use
Qwen3 235B-A22B-2507 by alibaba is currently listed from a single provider. Its reference price is $0.072 per 1M input tokens and $0.464 per 1M output tokens.
Artificial Analysis rates it 12.7 on the Intelligence Index, with 22.1 for coding and 1.3 for agentic tasks. Against its lowest blended price of $0.17 per 1M, that is roughly 75 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 73 tokens per second, with 2.72s to the first token. Running one task of the Artificial Analysis suite costs about $0.0806, which reflects how many tokens its reasoning consumes rather than the unit price alone.
The context window is 131,000 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 2025-06-30.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| TensorX | Gateway | $0.072 | $0.46 | $0.018 | $0.09 | 131,000 | — |
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.
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.