Models
THE NEWEST MODELS, TESTED BEFORE THEY REACH YOUR CHAT
Every reply your visitors get comes from a named model. This page reads from the same catalogue the product uses, so what you see here is what runs.
WHAT EACH PLAN RUNS ON TODAY
Routing and intent calls on every plan use GPT-6 Luna, a small, fast model, so your visitors' replies get the big one.
EVERY MODEL ON OFFER
Cheapest first. A model appears here only after a test reply has worked from our own servers.
| Model | Maker | Per million tokens, in / out | Runs |
|---|---|---|---|
| GPT-6 Luna | OpenAI | $0.10 / $0.50 | Starter, Business, Pro |
| Claude Haiku 5.5 | Anthropic | $0.10 / $0.50 | |
| GPT-4o Mini | OpenAI | $0.15 / $0.60 | |
| GPT-4.1 Mini | OpenAI | $0.40 / $1.60 | |
| GPT-5.4 Mini* | OpenAI | $0.75 / $4.50 | |
| GPT-6 Sol | OpenAI | $2.00 / $10.00 | Extreme |
| GPT-4.1* | OpenAI | $2.00 / $8.00 | |
| Claude Sonnet 5* | Anthropic | $2.00 / $10.00 | |
| Claude Sonnet 5.5 | Anthropic | $2.00 / $10.00 | |
| GPT-4o | OpenAI | $2.50 / $10.00 |
* Available as an add-on pack on any paid plan: GPT-4.1, Claude Sonnet 5, GPT-5.4 Mini.
HOW A MODEL GETS HERE
The honest version.
- 01
Found
Our catalogue asks OpenAI and Anthropic what models exist, on a schedule and on demand. A new one is listed within a day of release.
- 02
Priced
A price is entered from the maker's own page, never guessed. An unpriced model is never used, because a wrong cost would hide inside every margin.
- 03
Tested
A real reply is requested from our own servers. If it fails, as some do on launch day, the model stays off until it passes.
- 04
Offered
Only then can a plan run on it. The pricing page reads the plan's model live, so what it says is what you get.
GPT and OpenAI are trademarks of OpenAI. Claude and Anthropic are trademarks of Anthropic, PBC. BotMatrix Labs is an independent product and is not endorsed by either.
TRY THE CURRENT MODEL ON YOUR CONTENT
Start free, add your content, and see what it answers. No card, no call.
Create your chatbot