# Strands Decider 26B-A4B

Decision models · checked 2026-10-25 · https://dbggr.dev/models/strands-decider-26b-a4b/

Open-source 26B MoE decision model on Gemma 4 for agent workflows; reads text only

Strands Decider 26B-A4B is an open-weight decision model from AWS Strands Labs (Apache 2.0, plus data and training code, 26B MoE (4B active), a LoRA adapter on Gemma 4 26B-A4B parameters): it answers typed questions, such as yes or no, pick one or pick several, with probabilities instead of writing text. There's no hosted version: you run it on your own hardware. It scores 66.7 (self-hosted; seconds are the board's estimate) on the independent JevBench Capability Score (board v1.7.46), where Jev, the reference, scores 77.1.

- Made by: AWS Strands Labs
- Weights: Open, Apache 2.0, plus data and training code
- Size: 26B MoE (4B active), a LoRA adapter on Gemma 4 26B-A4B
- Where: Self-host only
- Images: No, text only
- Fine-tuning: Full recipe published
- Docs: https://github.com/strands-labs/strands-decider

## Strands Decider 26B-A4B price

US dollars per million input tokens. Decision models don't write text, so none of the hosted ones charge for output.

| Where | Input | Output | Notes | Checked |
|---|---|---|---|---|
| Self-host only | Self-host | – | – | [2026-10-25](https://huggingface.co/StrandsAgents/strands-decider-26B-A4B-gemma4-v1-2610) |

## Strands Decider 26B-A4B benchmarks

| Benchmark | Result | What it measures | Reported by |
|---|---|---|---|
| JevBench v1.7.46 | 66.7 | Capability Score: accuracy and calibration on typed decisions, with Jev as the reference system | [Independent](https://benchmarkheaven.com/jev-models) |
| JevBench time | 0.37 s | Seconds per decision: measured end to end for hosted APIs, the board's estimate for self-hosted models | [Independent](https://benchmarkheaven.com/jev-models) |
| Reported speed | 245 ms median per JevBench question on one H100 | Latency on the maker's own hardware | AWS Strands Labs |

Makers' speeds are measured on their own hardware and aren't comparable with each other or with JevBench's timings.

## Decision models like Strands Decider 26B-A4B

| Model | Input / M | JevBench | Weights |
|---|---|---|---|
| Strands Decider 26B-A4B | Self-host | 66.7 | Open |
| [Mammoth-1](https://dbggr.dev/models/mammoth-1/) | Free | 85.2 | Open |
| [Perplexity Decider V1.2](https://dbggr.dev/models/pplx-decider-v1-2/) | $0.02 | 80.8 | Open |
| [d1-ultra](https://dbggr.dev/models/d1-ultra/) | $0.042 | 80.5 | Closed |
| [Clef](https://dbggr.dev/models/clef/) | $0.24 | 75.3 | Open |
| [Jev 1.14](https://dbggr.dev/models/jev/) | $0.042 | 75.0 | Closed |
| [d1](https://dbggr.dev/models/d1/) | $0.02 | 74.4 | Closed |
| [Mercury Decide](https://dbggr.dev/models/mercury-decide/) | $0.02 | 73.6 | Closed |
| [OpenAI Decisions (GPT-6 Luna)](https://dbggr.dev/models/openai-decisions/) | $0.10 | 73.5 | Closed |
| [Microsoft-Decision-1](https://dbggr.dev/models/microsoft-decision-1/) | $0.042 | 70.8 | Closed |
| [Elephant-1](https://dbggr.dev/models/elephant-1/) | Free | 70.2 | Open |
| [Clef-flash](https://dbggr.dev/models/clef-flash/) | $0.038 | 63.8 | Open |
| [Perplexity Decider Flash V1.2](https://dbggr.dev/models/pplx-decider-flash-v1-2/) | $0.01 | 61.7 | Open |
| [Clef-omni](https://dbggr.dev/models/clef-omni/) | $0.15 | 58.3 | Open |
| [d1-3B](https://dbggr.dev/models/d1-3b/) | Self-host | 49.5 | Open |
| [d1-omni-600M (experimental)](https://dbggr.dev/models/d1-omni-600m/) | Self-host | 32.8 | Open |
| [Laya](https://dbggr.dev/models/laya/) | Free | 32.5 | Open |
| [CLM-8B](https://dbggr.dev/models/clm-8b/) | Self-host | 20.1 | Open |
| [Clairic](https://dbggr.dev/models/clairic/) | $0.10 | – | Closed |
| [Strands Decider 2B](https://dbggr.dev/models/strands-decider-2b/) | Self-host | – | Open |

## FAQ

### How much does Strands Decider 26B-A4B cost?

Strands Decider 26B-A4B has no hosted, per-token price: you download it and run it yourself, so the cost is your own compute.

### Is Strands Decider 26B-A4B open weight?

Yes. AWS Strands Labs publishes the weights under Apache 2.0, plus data and training code, so you can run and fine-tune it yourself.

### How fast is Strands Decider 26B-A4B?

AWS Strands Labs reports 245 ms median per JevBench question on one H100, measured on its own hardware. JevBench gives 0.37 seconds per decision, its estimate for self-hosting.

### How does Strands Decider 26B-A4B compare with Jev?

On JevBench's Capability Score (board v1.7.46), Strands Decider 26B-A4B scores 66.7 against Jev's 77.1. Jev costs $0.042 per million input tokens; Strands Decider 26B-A4B is self-host only. JevBench is a one-person project that uses Jev as its reference, which favours cheap hosted models.