Model tracker / Decision models / AWS Strands Labs
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
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 |
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 |
| JevBench time | 0.37 s | Seconds per decision: measured end to end for hosted APIs, the board's estimate for self-hosted models | Independent |
| 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
Every other decision model we track, by independent JevBench score.
| Model | Input / M | JevBench | Weights |
|---|---|---|---|
| Strands Decider 26B-A4B | Self-host | 66.7 | Open |
| Mammoth-1 Baseten (Base Labs) | Free | 85.2 | Open |
| Perplexity Decider V1.2 Perplexity | $0.02 | 80.8 | Open |
| d1-ultra Liquid AI | $0.042 | 80.5 | Closed |
| Clef Cloudflare | $0.24 | 75.3 | Open |
| Jev 1.14 TypeSafe AI | $0.042 | 75.0 | Closed |
| d1 Liquid AI | $0.02 | 74.4 | Closed |
| Mercury Decide Inception | $0.02 | 73.6 | Closed |
| OpenAI Decisions (GPT-6 Luna) OpenAI | $0.10 | 73.5 | Closed |
| Microsoft-Decision-1 Microsoft | $0.042 | 70.8 | Closed |
| Elephant-1 Baseten (Base Labs) | Free | 70.2 | Open |
| Clef-flash Cloudflare | $0.038 | 63.8 | Open |
| Perplexity Decider Flash V1.2 Perplexity | $0.01 | 61.7 | Open |
| Clef-omni Cloudflare | $0.15 | 58.3 | Open |
| d1-3B Liquid AI | Self-host | 49.5 | Open |
| d1-omni-600M (experimental) Liquid AI | Self-host | 32.8 | Open |
| Laya Convai Innovations | Free | 32.5 | Open |
| CLM-8B Stanford and NVIDIA | Self-host | 20.1 | Open |
| Clairic Cloudflare | $0.10 | – | Closed |
| Strands Decider 2B AWS Strands Labs | Self-host | – | Open |
Compare them all in the decision models table →
Strands Decider 26B-A4B 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.