Qwen vision-language model for visual reasoning, documents, and agent tasks
Qwen3.5 35B-A3B by alibaba is offered by 23 providers on this page. Its official list price is $0.25 per 1M input tokens and $2.00 per 1M output tokens. The lowest paid channel is AIHubMix at $0.056 / $0.451 per 1M, about 5.5× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
Artificial Analysis rates it 19.3 on the Intelligence Index. Against its lowest blended price of $0.155 per 1M, that is roughly 124 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 145 tokens per second, with 2.18s to the first token.
The context window is 262,144 tokens at the reference host, but hosts report different limits, from 131,072 to 262,144, 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 Audio. 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 2025-01.
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 |
|---|---|---|---|---|---|---|---|---|
| AIHubMix | Gateway | $0.056 tiered >128K: $0.23 | $0.45 | — | — | 262,144 | 65,536 | |
| EmpirioLabs AI qwen3-5-35b-a3b | Gateway | $0.057 tiered >128K: $0.23 | $0.46 | $0.057 | — | 256,000 ⚠ | 64,000 | |
| OrcaRouter | Gateway | $0.057 | $0.46 | — | — | 262,144 | 65,536 | |
| Merge Gateway | Gateway | $0.057 | $0.46 | $0.02 | — | 131,072 ⚠ | 32,768 | |
| 302.AI | Gateway | $0.06 | $0.46 | — | — | 262,144 | 65,536 | |
| Deep Infra Qwen/Qwen3.5-35B-A3B | Cloud | $0.14 | $1.00 | $0.05 | — | 262,144 | 81,920 | |
| Requesty | Gateway | $0.14 | $1.00 | $0.05 | — | 262,144 | 262,144 | |
| OpenRouter | Gateway | $0.15 | $1.00 | $0.05 | — | 262,144 | 235,929 | |
| Kilo Gateway | Gateway | $0.16 | $1.30 | — | — | 262,144 | 235,929 | |
| CoreWeave Qwen/Qwen3.5-35B-A3B | Cloud | $0.25 | $1.25 | $0.25 | — | 262,144 | 262,144 | |
| AlibabaOfficial | First-party | $0.25 | $2.00 | — | — | 262,144 | 65,536 | |
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 2 of 23 providers.
2 / 23 providers expose no reasoning control (reasoning_options: []).
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.