Structured output

2 items

Architecture diagram of Strands Decider 2B: on the left, a decoder language model whose text-generating head is discarded; on the right, the same Qwen3.5-2B-Base torso with a LoRA adapter feeds a pointer head that turns the listed options into per-option probabilities.

Models

Amazon's Strands Labs releases Decider 2B, an open decision model that runs locally

Strands Labs, the experimental arm of the Strands Agents project, released Strands Decider 2B on October 1, 2026. The model does not write text: it picks one of the options you give it, answers yes or no, or scores on a scale, and it attaches a confidence value to each answer. The team reports a median of 115 ms per decision on Nvidia's RTX 3090. Code, weights, training data, and scripts are public under Apache-2.0. If you build agents, this gives you a cheap local step for routing, tool checks, and guardrails.

Strands AgentsOctober 1verified

Models

TypeSafe AI opened early access to Jev, a model that returns decisions instead of text

Jev does not write sentences. It reads unstructured input and returns a value whose shape you declared in advance, with a calibrated probability attached to every field. TypeSafe AI charges $0.042 per million input tokens, charges nothing for output, and reports end-to-end response times of 70 to 500 milliseconds. The speed and cost multiples on its home page come from evaluations the company built and ran itself.

TypeSafe AISeptember 19verified