de.NBI Cloud Berlin
LLM API Gateway
Acknowledgement
This service is provided by the de.NBI Cloud Berlin node. If you use this service in your research, please acknowledge the de.NBI Cloud in your publications.
Citation
"This work was supported by the de.NBI Cloud within the German Network for Bioinformatics Infrastructure (de.NBI) and ELIXIR-DE (Forschungszentrum Jülich and W-de.NBI-001, W-de.NBI-004, W-de.NBI-008, W-de.NBI-010, W-de.NBI-013, W-de.NBI-014, W-de.NBI-016, W-de.NBI-022)."
"This work was supported by the de.NBI Cloud within the German Network for Bioinformatics Infrastructure (de.NBI) and ELIXIR-DE (Forschungszentrum Jülich and W-de.NBI-001, W-de.NBI-004, W-de.NBI-008, W-de.NBI-010, W-de.NBI-013, W-de.NBI-014, W-de.NBI-016, W-de.NBI-022)."
API Key & Support
Contact denbi-cloud@bih-charite.de for your API key and technical support.
Sensitive / Clinical Data
If you are working with sensitive or clinical data, we recommend using our Clinical Cloud for enhanced security and compliance.
Please contact us at cci-support@charite.de.
Available Models
Endpoints
| Protocol | Endpoint | Notes |
|---|---|---|
| OpenAI Chat | https://denbi-llm-api.bihealth.org/v1 |
External |
| OpenAI Chat | https://denbi-llm-api-internal.bihealth.org/v1 |
Internal (VMs) |
Recommendations
- Set a reasonable
max_tokens=2048(~1500 words) appropriate for your tasks to save compute. - Use exponential backoff for retries to handle rate limits gracefully.
- Please use the service fairly and avoid spamming endpoints.
Policy
- We have a zero-retention policy: none of your input or output content is stored.
- Your data is never used for fine-tuning, training, or model optimization.
- We only collect minimal operational telemetry (e.g., model version, token count, request timings, etc) for operational purposes.