Strands Decider 2B
Open-weights “decision model” from AWS Strands Labs. It picks among given options or rates on a scale with calibrated probabilities; it does not generate free text. Download from Hugging Face (Apache 2.0).
PriceFree
Checked1 October 2026
No published training cutoff
At least1,298events since its release on 1 October 2026
57 historic, 291 major. 49 days of news.
Amazon Web Services (Strands Labs) doesn’t publish a training cutoff, so we count from its release date. The real gap is larger.
How to call it
Where to use Strands Decider 2B.
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Hugging Face | huggingface.co |
Pricing
| Input | $0 per 1M tokens |
|---|---|
| Output | $0 per 1M tokens |
As published: “free open weights (self-hosted)”.
Source: huggingface.co, checked 1 October 2026.
Specs
- Input
- Text
- Output
- Text
- Context window
- Not published
- Max output
- Not published
- Open weights
- Yes
- Licence
- Apache-2.0
- Training cutoff
- Not published
- Released
- 1 October 2026
- Status
- Preview
- Type
- Language model
What stands out
What its maker marketed at launch, and what people found later, each with its source.
Decision model (option scoring)
Replaces the LM head of Qwen3.5-2B-Base with a readout/pointer head that scores the supplied options and returns calibrated confidences in one pass: JevBench public 0.723, ~106 ms median latency on an RTX 3090 (VentureBeat).
Notes
Experimental release from AWS Strands Labs (LoRA adapter on Qwen/Qwen3.5-2B-Base). Uses: routing, tool selection, guardrails, triage. Weaker on long multi-step documents (model card). Open-source alternative to TypeSafe’s hosted Jev.