Embedding Models
This content is for v1.1.0. Switch to the latest version for up-to-date documentation.
Convert text to dense vectors for semantic search, clustering, and retrieval-augmented generation. Available via the POST /embeddings endpoint.
Showing 3 of 3 models
| 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. | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| BGE-M3 | | Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany. | Text | Vector | ✗ | ✗ | 8K | €0.05 | €0.05 | EssentialProfessionalAgentic | |
| Jina Embeddings v2 Base DE | | Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany. | Text | Vector | ✗ | ✗ | 8K | €0.05 | €0.05 | EssentialProfessionalAgentic | |
| Ada Text Embedding | | Hosted on Microsoft Azure (EU regions). | Text | Vector | ✗ | ✗ | 8K | €0.11 | €0.11 | EssentialProfessionalAgentic | |
| No models match the current filters. | |||||||||||