Audio (Speech-to-Text)
Whisper-family models for transcription and translation. Available via the POST /audio/transcriptions and POST /audio/translations endpoints.
Showing 5 of 5 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. | Price per million prompt tokens served from the prefix cache: 15% of the normal input price. T-Cloud-hosted models only — cached pricing for external providers will be added later. | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Whisper Large v3 |  OpenAI | Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany. | Audio | Text | ✗ | ✗ | 448 | €14.61 | €14.61 | €2.1915 | EssentialProfessionalAgentic | |
| Whisper Large v3 Turbo | OpenAI | Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany. | Audio | Text | ✗ | ✗ | 448 | €9.21 | €9.21 | €1.3815 | EssentialProfessionalAgentic | |
| Gemini 3 Flash | '/%3e%3cdefs%3e%3cradialGradient%20id='prefix__paint0_radial_980_20147'%20cx='0'%20cy='0'%20r='1'%20gradientUnits='userSpaceOnUse'%20gradientTransform='matrix(16.1326%205.4553%20-43.70045%20129.2322%201.588%206.503)'%3e%3cstop%20offset='.067'%20stop-color='%239168C0'/%3e%3cstop%20offset='.343'%20stop-color='%235684D1'/%3e%3cstop%20offset='.672'%20stop-color='%231BA1E3'/%3e%3c/radialGradient%3e%3c/defs%3e%3c/svg%3e){kind=small} Google | Hosted on Google Cloud Platform (EU regions). | Text, Image, Audio | Text | ✓ | ✓ | 1M | €0.45 | €2.70 | n/a | EssentialProfessionalAgentic | |
| Gemini 3 Pro (>200k) | Google | Hosted on Google Cloud Platform (EU regions). | Text, Image, Audio | Text | ✓ | ✓ | 1M | €3.60 | €16.20 | n/a | EssentialProfessionalAgentic | |
| Gemini 3 Pro (≤200k) | Google | Hosted on Google Cloud Platform (EU regions). | Text, Image, Audio | Text | ✓ | ✓ | 200K | €1.80 | €10.80 | n/a | EssentialProfessionalAgentic | |
| No models match the current filters. | ||||||||||||