Open multimodal Qwen MoE for local agents that need vision, audio, and code
Qwen3.6 35B-A3B by alibaba is offered by 33 providers on this page. Public prices are shown for 30 of them. Its official list price is $0.248 per 1M input tokens and $1.49 per 1M output tokens. The lowest paid channel is engy at $0.045 / $0.30 per 1M, about 8.3× 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 2 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.
Artificial Analysis rates it 18.2 on the Intelligence Index, with 41.9 for coding and 13.1 for agentic tasks. Against its lowest blended price of $0.109 per 1M, that is roughly 167 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 132 tokens per second, with 2.11s to the first token. Running one task of the Artificial Analysis suite costs about $0.4751, which reflects how many tokens its reasoning consumes rather than the unit price alone.
The context window is 262,144 tokens at the reference host, but hosts report different limits, from 16,384 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 2025-04.
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 |
|---|---|---|---|---|---|---|---|---|
| NaN qwen3.6 | Gateway | Free | — | — | 262,144 | 65,536 | ||
| Umans AI Coding Plan umans-qwen3.6-35b-a3b | Gateway | Subscription | $0 | $0 | 262,144 | 262,144 | ||
| QVAC | Gateway | Free | — | — | 262,144 | 65,536 | ||
| engy | Gateway | $0.045 | $0.30 | $0.015 | — | 208,192 ⚠ | 8,192 | |
| 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 | |
| AKI.IO qwen3.6-35b | Gateway | $0.15 | $0.50 | — | — | 256,000 ⚠ | 32,768 | |
| Zenifra | Gateway | $0.19 | $0.48 | — | — | 262,144 | 65,536 | |
| Cortecs | Gateway | $0.17 | $0.56 | — | — | 262,000 ⚠ | 32,768 | |
| NanoGPT | Gateway | $0.11 | $0.80 | $0.056 | — | 262,144 | 16,384 | |
| AlibabaOfficial | First-party | $0.25 | $1.49 | — | — | 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 5 of 33 providers.
7 / 33 providers expose no reasoning control (reasoning_options: []).
3 more channels offer $0 (NaN, Umans AI Coding Plan, QVAC); 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 harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.