HEAD TO HEAD
Telnyx: decision-flash and DecisionTune: decisiontune, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | telnyx/decision-flash | decision-tune/decisiontune |
|---|---|---|
| Summary | 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. | DecisionTune's 395M decision model: ModernBERT-large fine-tuned with a 4 KB scoring head that scores a marker per option, answering a choice or yes/no question in one encoder pass with a probability for every option. Runs locally on CPU or GPU via PyTorch, MLX or ONNX. |
| Decides | choice, score, noul, classify, route | choice, noul, route, classify |
| Architecture | telnyx-decision | decisiontune |
| Fine-tuned from | — | answerdotai/modernbert-large |
| License | proprietary | apache-2.0 |
| Availability | Hosted API | Open weights |
| Hosted by | Telnyx | — |
| Input price | $0.035/MTok | — |
| Decision accuracy | — | — |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | — | — |
| p95 latency | — | — |
| Evaluation suite | — | — |
| Latest version | 2026.09 | 1.0.0 |
| Variants | — | onnx |
| Size of latest version | — | 2.9 GB |
| Files | 0 | 8 |
| Downloads | 0 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, hosted, typesafe-compatible, voice-agents | system-one, encoder, modernbert, mlx, onnx, mcp, 395m |
| Updated | Oct 7, 2026 | Oct 7, 2026 |
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
decision-flash is from Telnyx and decisiontune from DecisionTune. decision-flash is only available as a hosted API; decisiontune has open weights you can download and run. Both answer choice, noul, classify and route questions. Only decision-flash answers score. decision-flash is licensed proprietary; decisiontune, apache-2.0.
Neither publishes an accuracy figure. Test both on your own labelled examples.
decision-flash: $0.035 / $0 per 1M. decisiontune: Free (open weights). Open weights cost nothing per call beyond your own hardware.
decisiontune yes — systemone pull decision-tune/decisiontune downloads its weights. The other is only served as a hosted API.