Model tracker / Decision models / Nace.AI
Drex Max v1.1
Closed multimodal decision model for computer-use agents: screenshots, images and text
Drex Max v1.1 is a closed decision model from Nace.AI: it answers typed questions, such as yes or no, pick one or pick several, with probabilities instead of writing text. It costs $0.03 per million input tokens (Nace Console API; OpenRouter (served by DeepInfra) lists the drex-max id without saying which version), and output is free. It scores 84.2 (the original Drex Max, measured on 21 October through Nace's API; JevBench says Nace has since updated the model behind the id) on the independent JevBench Capability Score (board v1.7.46), where Jev, the reference, scores 77.1.
- Made by
- Nace.AI
- Weights
- Closed
- Size
- Undisclosed
- Where
- Nace Console API; OpenRouter (served by DeepInfra) lists the drex-max id without saying which version
- Images
- Yes
- Context
- 262,144 for the whole request, images included (Nace's product page says 131,072 per question)
- Fine-tuning
- None documented for Drex Max; Nace offers tuning on your decisions on request
Drex Max v1.1 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 |
|---|---|---|---|---|
| Nace Console API; OpenRouter (served by DeepInfra) lists the drex-max id without saying which version | $0.03 | Free | Output is free. A launch price, 50% off a $0.06 list price, with no end date given; OpenRouter shows the same discount. Up to 8 images per request on Nace (PNG, JPEG or WebP), 4 on OpenRouter. Nace's pages disagree on whether drex-max now serves v1.1 or the original Drex Max (released 13 October); drex-max-v1.1 pins v1.1 (28 October). Drex Max Finance (drex-max-finance, 1 November) is a finance-tuned version at the same price. | 2026-11-07 |
Drex Max v1.1 benchmarks
| Benchmark | Result | What it measures | Reported by |
|---|---|---|---|
| JevBench v1.7.46 | 84.2 | Capability Score: accuracy and calibration on typed decisions, with Jev as the reference system | Independent |
| JevBench time | 0.25 s | Seconds per decision: measured end to end for hosted APIs, the board's estimate for self-hosted models | Independent |
| Reported speed | 172 ms median API time per decision, network included | Latency on the maker's own hardware | Nace.AI |
Makers' speeds are measured on their own hardware and aren't comparable with each other or with JevBench's timings.
Decision models like Drex Max v1.1
Every other decision model we track, by independent JevBench score.
| Model | Input / M | JevBench | Weights |
|---|---|---|---|
| Drex Max v1.1 | $0.03 | 84.2 | Closed |
| Mammoth-1 Baseten (Base Labs) | $0.10 | 85.2 | Open |
| Perplexity Decider V1.2 Perplexity | $0.02 | 80.8 | Open |
| d1-ultra Liquid AI | $0.042 | 80.5 | Closed |
| Kev-27B Jared Palmer | Self-host | 78.9 | Open |
| 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) | $0.035 | 70.2 | Open |
| Strands Decider 26B-A4B AWS Strands Labs | Self-host | 66.7 | Open |
| Clef-flash Cloudflare | $0.038 | 63.8 | Open |
| Perplexity Decider Flash V1.2 Perplexity | $0.01 | 61.7 | Open |
| Kev-9B Jared Palmer | Self-host | 61.5 | Open |
| Clef-omni Cloudflare | $0.15 | 58.3 | Open |
| Joey-1 Baseten (Base Labs) | $0.01 | 57.8 | Open |
| d1-3B Liquid AI | Self-host | 49.5 | Open |
| d1-omni-600M (experimental) Liquid AI | Self-host | 32.8 | Open |
| Laya Convai Innovations | $0.011 | 32.5 | Open |
| CLM-8B Stanford and NVIDIA | Self-host | 20.1 | Open |
| Clairic Cloudflare | $0.10 | – | Closed |
| d1-2B Liquid AI | Self-host | – | Open |
| d1-omni-2B Liquid AI | Self-host | – | Open |
| Drex 1.5 Nace.AI | $0.05 | – | Open |
| Drex 2.0 Nace.AI | $0.06 | – | Open |
| Kev-0.8B Jared Palmer | Self-host | – | Open |
| Kev-4B Jared Palmer | Self-host | – | Open |
| Koa Decisions Salesforce | Self-host | – | Closed |
| Strands Decider 12B AWS Strands Labs | Self-host | – | Open |
| Strands Decider 2B AWS Strands Labs | Self-host | – | Open |
| Strands Decider E2B AWS Strands Labs | Self-host | – | Open |
| Strands Decider E4B AWS Strands Labs | Self-host | – | Open |
Compare them all in the decision models table →
Drex Max v1.1 on dbggr
- Stop asking your LLM multiple-choice questions: a guide to decision models Article, 2026-10-02
Drex Max v1.1 FAQ
How much does Drex Max v1.1 cost?
Drex Max v1.1 costs $0.03 per million input tokens at Nace Console API; OpenRouter (served by DeepInfra) lists the drex-max id without saying which version. Output is free. A launch price, 50% off a $0.06 list price, with no end date given; OpenRouter shows the same discount. Up to 8 images per request on Nace (PNG, JPEG or WebP), 4 on OpenRouter. Nace's pages disagree on whether drex-max now serves v1.1 or the original Drex Max (released 13 October); drex-max-v1.1 pins v1.1 (28 October). Drex Max Finance (drex-max-finance, 1 November) is a finance-tuned version at the same price. Checked 7 November 2026.
Is Drex Max v1.1 open weight?
No. Drex Max v1.1 is only available through Nace Console API; OpenRouter (served by DeepInfra) lists the drex-max id without saying which version.
How fast is Drex Max v1.1?
Nace.AI reports 172 ms median API time per decision, network included, measured on its own hardware. JevBench gives 0.25 seconds per decision, measured end to end.
How does Drex Max v1.1 compare with Jev?
On JevBench's Capability Score (board v1.7.46), Drex Max v1.1 scores 84.2 against Jev's 77.1. Jev costs $0.042 per million input tokens; Drex Max v1.1 costs $0.03. JevBench is a one-person project that uses Jev as its reference, which favours cheap hosted models.