Decision models
Models that serve the Decisions API. They return typed answers (a probability, one option from a list, or a level on a rubric) instead of text, for agent steps such as tool routing, approval gates and grounding checks. Available via POST /decisions.
Recommended
-
d3 Preview
d3-preview - Hosting
- T-Cloud Germany (EU)
-
DiffusionGemma 26B A4B Preview
diffusiongemma-26B- A4B- it- Preview - Context
- 256K
- Hosting
- T-Cloud Germany (EU)
Both are preview models on T-Cloud. DiffusionGemma accepts text and image and has a 256K context window.
Showing 2 of 2 models
| Output types | Token-by-token output via Server-Sent Events. Suitable for low-latency, real-time UI. | Function / tool calling (OpenAI-compatible). The model can return structured tool invocations. | Price per million prompt tokens served from the prefix cache: 15% of the normal input price. T-Cloud-hosted language models only. | Details | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| | Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany, within the EU. | Text, Image | Text | ✓ | ✓ | 256K | €0.00 | €0.00 | €0.00 | Free on any active plan | ||
| ||||||||||||
| | Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany, within the EU. | Text, Image | Text | ✗ | ✗ | — | €0.00 | €0.00 | €0.00 | Free on any active plan | ||
| ||||||||||||
| No models match the current filters. | ||||||||||||