Decision Models (decision-flash, decision-pro)
Telnyx's hosted decision models, in beta on Telnyx Inference. One request carries shared state and up to 64 typed questions (choice, yes/no noul, ordered score) and returns a probability per option, with no generated text, on a TypeSafe-compatible /v1/systemone route.
Two Telnyx-managed aliases: decision-flash, the default (lowest cost and latency, 32k tokens for state plus the longest question), and decision-pro for longer context ($0.20 per million input tokens). Telnyx does not name the model behind either alias and says both may change during the beta. The TypeSafe Python SDK works with Telnyx's base URL for the supported request subset, but Telnyx says that does not mean identical predictions, calibration or pricing. Choice and score take 2 to 64 options. Telnyx states its scores describe relative preference, not calibrated correctness. No weights and no accuracy numbers are published.
What it decides
- choice — picks one option from a set
- score — places the input on an ordered scale
- noul — answers a yes/no question with one probability
- classify — assigns a category from a fixed taxonomy
- route — sends the input to one of several destinations
At a glance
| Maker | Telnyx |
| Released | 2026-09-22 |
| License | proprietary |
Hosted API
Served by Telnyx — $0.035/MTok input, $0/MTok output. Get access · API docs.
Read more
This page was opened by System One for Telnyx, who can claim the organisation and take it over at any time.