LLMBase Inference API
OpenAI-compatible inference API for EU-hosted open models. Switch by changing the base URL, use your OpenAI SDK, and pay per use.
base URL
https://api.llmbase.aiLLMBase exposes an OpenAI-compatible REST API. Switch from OpenAI by changing one line: the baseURL. Authentication, request format and response shape stay the same.
Docs
Quickstart
Make your first LLMBase API call in under two minutes.Authentication
How to authenticate requests to the LLMBase API using Bearer tokens.OpenAI compatibility
Migrate OpenAI-compatible chat clients to LLMBase and understand the supported compatibility surface.Chat connectors
Connect accounts and compatible remote MCP servers to LLMBase Chat, then choose where they are available.Gmail connector
Use Gmail from LLMBase Chat to search, read, send, archive, and trash email with OAuth consent.Google Calendar connector
Use Google Calendar from LLMBase Chat to list, search, create, update, and delete events.Dedicated Inference
Deploy open-source and custom AI models on isolated GPUs in European data centers. Managed endpoints with an OpenAI-compatible API.OCR (Optical Character Recognition)
Extract text from images and PDFs by sending image content to a vision-capable model through the LLMBase Inference API.Buying inference credits as a business
Set business details, a VAT ID, and a separate billing email when purchasing LLMBase credits.Agents
Agent integrations
Use an LLMBase Pro or Business chat subscription from OpenAI-compatible agents such as OpenClaw and Hermes.Agent Skills and WebMCP
Machine-readable LLMBase skills, read-only WebMCP tools, and content negotiation support.Models for agents
Understand which LLMBase models are available to OpenAI-compatible agents and which models to start with.Agent usage and rate limits
Understand the included Chat/Agent budget, approximate request coverage, and request limits for chat-agent access.Agent setup examples
Create a chat agent key and configure OpenAI-compatible agents, Hermes, the OpenAI SDK, or cURL.Agent discovery metadata
Machine-readable LLMBase discovery endpoints for agents and compatible clients.Inference API
Models
Browse the current LLMBase Inference API model catalog.Model discovery
List models, inspect metadata, and filter the LLMBase Inference API catalog programmatically.Rate limits
Direct Inference API request rate, balance, spend-cap, concurrency, and availability limits.How billing works
Why the Inference API reserves credit before a request, how the reservation is sized, why a 402 can happen with credit left, and how to avoid it.Chat completions
Request and response reference for POST /v1/chat/completions.Streaming
Stream chat completion tokens with Server-Sent Events.Tools
Use OpenAI-compatible function tools with chat completions.Structured outputs
Request JSON output with json_object or JSON Schema response formats.Prompt caching
Use prompt_cache_key and cache-read pricing for repeated long prompts.Model availability
Handle temporary model availability errors from the Inference API.Reasoning
Use reasoning_effort and read reasoning traces when models support them.