Qwen3.6 27B
qwen
Qwen vision-language model for visual reasoning, documents, and agent tasks
ReasoningTool CallingAttachmentsStructured OutputOpen Weights
Context Window
262K
Max Output
66K
Temperature
Yes
Open Weights
Yes
Knowledge Cutoff
N/A
Released
2026-04-22
Last Updated
2026-04-22
Modalities
Input:TextImageVideoAudio
→Output:Text
Benchmarks
| Benchmark | Score | Metric |
|---|---|---|
| SWE-Bench Verified | 77.2 | resolved |
Available Providers (2)
| Provider | Input /1M | Output /1M | Cache Read /1M | Cache Write /1M | Reasoning | Status |
|---|---|---|---|---|---|---|
 Vercel AI Gateway | Rp 10.821 | Rp 64.922 | — | — | toggle, budget_tokens | — |
 NanoGPT | Rp 3.661 | Rp 40.396 | — | — | — | — |