Plexe
Models for the messy data
behind real industries.
Specialist models that turn inconsistent supplier data into decisions you can build on. Each one is trained against a written definition and measured on data it has never seen. We are starting with travel.
The only model that's frontier-accurate in under a second.
200 hotels none of the models had seen, one written definition of a room. GPT-5.5 and GPT-6.1 match mlr-1's F1 at 17+ seconds a hotel.
| Model | F1 | Purity | Completeness | Seconds per hotel |
|---|---|---|---|---|
| GPT-5.5 | 94.1 | 92.1 | 96.2 | 44.0 |
| GPT-6.1 | 93.6 | 91.3 | 96.0 | 17.3 |
| mlr-1 | 93.0 | 94.2 | 91.9 | 0.26 |
| gpt-oss-120b open | 89.0 | 96.6 | 82.4 | 25.8 |
| JEV (Typesafe) | 86.2 | 92.1 | 80.9 | 0.38 |
| DeepSeek V3.2 open | 68.2 | 58.7 | 81.5 | 4.7 |
| Qwen3 32B open | 59.3 | 51.4 | 70.1 | 3.1 |
| Llama 3.3 70B open | 52.1 | 39.0 | 78.5 | 1.6 |
Hotels drawn at random from our 1,000-hotel blind benchmark. Costs are list token prices; ours is our usage price. JEV was asked one name at a time. 10 Nov 2026.
Same rates. Fewer cards.
American Inn by OYO Colorado City I-20, Colorado City, from the benchmark, resolved in 203 ms. Hover a room to see its names.
- Queen Bed Non-Smoking
- 2 Double Beds Smoking
- Queen Bed Smoking
- 2 Double Beds Non-Smoking
- Queen Bed Accessible
- ROOM, QUEEN BED
- ROOM, QUEEN BED, SMOKING
- ROOM, 2 DOUBLE BEDS, SMOKING
- ROOM, 2 DOUBLE BEDS
- DOUBLE TWO DOUBLE BEDS
- DOUBLE QUEEN BED NON SMOKING
- DOUBLE QUEEN BED SMOKING
- DOUBLE TWO DOUBLE BEDS NON SMOKING
- DOUBLE Accessible-Queen Size Bed
- Run of House
- Standard room
- Standard Quadruple room
- Standard Double room
- Standard Sextuple room
- Queen Room6 names
- Room, 2 Double Beds6 names
- Queen Room, Accessible2 names
- Run of House1 name
- Standard Room1 name
- Standard Quadruple Room1 name
- Standard Double Room1 name
- Standard Sextuple Room1 name
Room names are language, not data.
- Signature Suite, Bathtub
- Signature Suite, Sea View
- Signature Suite Taj Club, Lounge Access
1 in 5
| Rule engines | Decision model | |
|---|---|---|
| Built | Per supplier, by hand | Once, for every supplier |
| Taught by | Patterns and code tables | A written definition of a room |
| New wording | Breaks | Reads it |
| New customer | Rebuilds the work | Clean rooms from the first call |
Pay for what you resolve.
Priced per hotel resolved, not per room, supplier or call. Every supplier included.
Usage
$0.20 per 1,000 hotels
- No monthly fee or minimum
- $0.15 per 1,000 above 10 million hotels a month
- Live and batch API, room hierarchy, support
Enterprise
Custom
- Volume pricing above 20 million hotels a month
- Dedicated GPU and an availability target
- A shared support channel
A hotel is one hotel's rooms from all its suppliers, resolved once. Prices exclude taxes.
Starting with travel
Travel inventory reaches you from dozens of suppliers, each describing the same hotel, room and photo in its own way. Our first models resolve that, behind one API.
Room resolution
Groups every supplier's offers for a hotel by room, and those rooms into room types. Reads names as suppliers write them, with any beds, views and features they send.
Try it on a real hotel →Image search
An image search model for travel content. Details on release.
Hotel resolver
Resolves each supplier's hotel record to one property, from its name, address and location.