Your sovereign, private Qwen 3.6 27B
Qwen3.6-27B is the first open-weight variant of Qwen3.6: a 27B dense model with a vision encoder, 262K native context (extensible to ~1M) and strong agentic-coding gains, including frontend workflows, repository-level reasoning and thinking preservation across turns. A reasoning model in the small tier, served on ToothFairyAI's AU, EU and US endpoints — private by default, billed in US dollars per million tokens at the published rates below. No training on your data, no vendor lock-in.
How Qwen 3.6 27B compares
Independent intelligence index for Qwen 3.6 27B against every peer in the Small tier (and the tier above where needed) — same source, same tests.
Latency — end-to-end seconds for a 500-token answer
Capability indexes
Domain-weighted agentic performance for Qwen 3.6 27B.
Capability index vs small peers
The evaluations behind the index
Independent benchmark results for Qwen 3.6 27B — Elo scores as published; pass rates shown as percentages.
Per-evaluation economics
| Evaluation | Score | Time / task | Output tokens / task |
|---|---|---|---|
| AA-Briefcase | 811.50 | 9.7 min | 37422 |
| GDPval-AA | 973.34 | 6.6 min | 25780 |
| AutomationBench-AA | 11.0% | 8.0 min | 31038 |
| Terminal-Bench 4.0 | 0.0% | 30.2 min | 117047 |
| SciCode | 42.8% | 1.3 min | 5033 |
| Humanity's Last Exam | 23.1% | 7.7 min | 29975 |
| GDP.pdf | 11.0% | 2.7 min | 10318 |
| CritPt | 1.1% | 12.3 min | 47806 |
| AA-Omniscience | -2001.7% | 2.4 min | 9427 |
| AA-LCR (long context) | 77.3% | 0.6 min | 2242 |
Run Qwen 3.6 27B privately
One key, one endpoint, three jurisdictions.
- Size tierSmall
- Serving routeStandard
- Input rate$0.17/1M
- Output rate$0.51/1M
- Cached input rate—
- Context window131K tokens
- Max output16K tokens
- ReasoningYes — emits thinking traces
- Vision & video inputSupports image input
- Tool callingSupported
- Data residencyAU, EU and US endpoints — processing stays inside the region you call