Multimodal Qwen workhorse for long-context agents, visual inputs, and codingQwen3.7 Plus by alibaba is offered by 36 providers on this page. Public prices are shown for 32 of them. Its official list price is $0.40 per 1M input tokens and $1.60 per 1M output tokens. The lowest paid channel is 302.AI at $0.228 / $0.92 per 1M, about 1.7× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 4 covered by a paid subscription; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
Median output speed is 57 tokens per second, with 2.24s to the first token.
The context window is 1,000,000 tokens at the reference host, but hosts report different limits, from 983,616 to 1,064,000, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, Video, and PDF. 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.
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 |
|---|---|---|---|---|---|---|---|---|
| Alibaba Coding Plan | Gateway | Subscription | $0 | $0 | 1,000,000 | 64,000 | ||
| Alibaba Token Plan | Gateway | Subscription | $0 | $0 | 1,000,000 | 65,536 | ||
| Alibaba Token Plan (China) | Gateway | Subscription | $0 | $0 | 1,000,000 | 65,536 | ||
| Alibaba Coding Plan (China) | Gateway | Subscription | $0 | $0 | 1,000,000 | 64,000 | ||
| 302.AI | Gateway | $0.23 tiered >256K: $0.68 | $0.92 | $0.023 | $0.29 | 1,000,000 | 64,000 | |
| Zenifra | Gateway | $0.27 tiered >256K: $0.80 | $1.03 | $0.073 | — | 1,000,000 | 131,072 | |
| Alibaba (China)Official | First-party | $0.28 tiered >256K: $0.83 | $1.10 | $0.055 | $0.35 | 1,000,000 | 64,000 | |
| AIHubMix | Gateway | $0.28 tiered >256K: $0.85 | $1.13 | $0.056 | $0.35 | 991,000 ⚠ | 64,000 | |
| CrossModel | Gateway | $0.32 tiered >256K: $0.96 | $1.25 | $0.032 | $0.40 | 1,000,000 | 64,000 | |
| Requesty | Gateway | $0.32 | $1.28 | $0.032 | $0.40 | 1,048,576 ⚠ | 131,072 |
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.
Interleaved thinking (reasoning between tool calls) is declared by 7 of 36 providers.
5 / 36 providers expose no reasoning control (reasoning_options: []).
4 more channels offer $0 (Alibaba Coding Plan, Alibaba Token Plan, Alibaba Token Plan (China) etc.); free tiers usually have rate limits and no SLA, excluded from ranking.
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.