Dedicated Inference
Deploy open-source and custom AI models on isolated, managed infrastructure in European data centers. Managed endpoints with an OpenAI-compatible API.
Updated
Dedicated Inference gives you a fully managed inference endpoint on infrastructure reserved exclusively for your workload. You get an OpenAI-compatible API URL — LLMBase handles the deployment, model loading, runtime, and hardware. There is no SSH access, no container configuration, and no infrastructure to manage.
On request. Dedicated endpoints are set up by our team, not self-service. Request one through the enterprise form.
What you get
Once your dedicated endpoint is set up you receive a unique base URL:
https://<endpoint-id>-inference.llmbase.cloud
This endpoint exposes the standard OpenAI-compatible chat completions interface:
POST https://<endpoint-id>-inference.llmbase.cloud/v1/chat/completions
Use it with the OpenAI SDK, any OpenAI-compatible client, or plain HTTP — the same way you would use https://api.llmbase.ai/v1.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://<endpoint-id>-inference.llmbase.cloud/v1",
apiKey: process.env.LLMBASE_API_KEY,
});
const response = await client.chat.completions.create({
model: "<model-id-from-/v1/models>",
messages: [{ role: "user", content: "Hello!" }],
});
Supported models
Dedicated endpoints support:
- Open-source foundation models — any model available in the LLMBase model catalog
- Your own fine-tuned models — bring weights you have fine-tuned on your own data
- Custom models — deploy a private model not in the public catalog
For custom and fine-tuned models, you provide the model weights (GGUF, safetensors, or vLLM-compatible format) during endpoint setup. LLMBase loads and serves them on your reserved infrastructure — you do not configure vLLM, Triton, or any inference runtime yourself.
How it differs from Serverless Inference
| Dedicated Inference | Serverless Inference | |
|---|---|---|
| Infrastructure | Reserved exclusively for you | Shared across users |
| Pricing | On request, see the dedicated endpoints page | Per input/output token |
| Rate limits | Sized to your reserved capacity | Shared pool limits apply |
| Latency | Consistent, no cold starts | May vary under load |
| Custom models | Yes — bring your own weights | No |
| Setup | Requested via the enterprise form, set up by LLMBase | API key only |
| Best for | Steady high-throughput workloads | Spiky or experimental traffic |
Choose dedicated inference when you run continuous high-throughput workloads, need predictable latency, or want to deploy a custom or fine-tuned model. Choose Serverless Inference when you need to start quickly, have unpredictable traffic, or want pay-per-token billing.
Isolation and compliance
Each dedicated endpoint runs on infrastructure that is not shared with any other customer during its lifetime. Compute and networking resources are fully isolated. All endpoints are hosted in EU data centers; personal data is processed under the GDPR, and a DPA is available.
Pricing
Prices on request; see the dedicated endpoints page. Dedicated endpoints are hosted in Germany.
Separately, the Inference API is available as API with location Germany. That option keeps per-token billing at the normal price plus a 20% surcharge on all token prices.
Request an offer through the enterprise form.
Requesting an endpoint
- Describe your workload, model and location needs in the enterprise form
- We send you an offer
- After you accept, we set up the endpoint and send you its URL
The endpoint URL follows the pattern https://<endpoint-id>-inference.llmbase.cloud/v1.
Authentication
Use your LLMBase API key in the Authorization header, the same as the Serverless Inference API:
Authorization: Bearer <LLMBASE_API_KEY>
See Authentication for how to create and manage API keys.