Open multimodal Qwen MoE for local agents that need vision, audio, and codeQwen3.6 35B-A3B by alibaba is offered by 51 providers on this page. Public prices are shown for 44 of them. Its official list price is $0.375 per 1M input tokens and $2.25 per 1M output tokens. The lowest paid channel is engy at $0.045 / $0.30 per 1M, about 7.8× 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 5 free ($0) channels and 1 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 110 tokens per second, with 2.07s to the first token.
The context window is 262,144 tokens at the reference host, but hosts report different limits, from 16,384 to 1,048,576, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and Video. 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.
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 |
|---|---|---|---|---|---|---|---|---|
| Umans AI Coding Plan umans-qwen3.6-35b-a3b | Gateway | Subscription | $0 | $0 | 262,144 | 262,144 | deprecated | |
| QVAC | Gateway | Free | — | — | 262,144 | 65,536 | ||
| NaN qwen3.6 | Gateway | Free | — | — | 262,144 | 65,536 | ||
| InferX Qwen3.6-35B-A3B-FP8 | Gateway | Free | — | — | 262,000 ⚠ | 65,536 | ||
| InferX Qwen3.6-35B-A3B-fp8-no-thinking | Gateway | Free | — | — | 262,000 ⚠ | 65,536 | ||
| Hetzner Qwen/Qwen3.6-35B-A3B-FP8 | Cloud | Free | $0 | — | 262,144 | 262,144 | beta | |
| engy | Gateway | $0.045 | $0.30 | $0.015 | — | 208,192 ⚠ | 8,192 | |
| Boundless qwen3.6 | Gateway | $0.04 | $0.35 | $0.02 | — | 262,144 | 65,536 | |
| EmpirioLabs AI qwen3-6-35b-a3b | Gateway | $0.07 | $0.42 | $0.035 | — | 131,072 ⚠ | 16,384 | |
| SaladCloud AI Gateway | Gateway | $0.09 | $0.60 | — | — | 262,144 | 262,144 | |
| AlibabaOfficial | First-party | $0.38 | $2.25 | — | — | 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 9 of 51 providers.
9 / 51 providers expose no reasoning control (reasoning_options: []).
6 more channels offer $0 (Umans AI Coding Plan, QVAC, NaN etc.); free tiers usually have rate limits and no SLA, excluded from ranking.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Verified | — | 73.4 | resolved | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
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.