> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.privategpt.dev/providers/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.privategpt.dev/_mcp/server.

# Inference Providers

## Docs

- [Overview](https://docs.privategpt.dev/providers/overview.md): PrivateGPT works with any OpenAI-compatible server. This page covers common local setups.
- [Ollama](https://docs.privategpt.dev/providers/ollama.md): Run local LLMs with Ollama — the easiest way to get started with PrivateGPT.
- [LM Studio](https://docs.privategpt.dev/providers/lmstudio.md): Run local models with LM Studio's built-in server — GUI-driven, full tokenizer support.
- [LlamaCPP Server](https://docs.privategpt.dev/providers/llamacpp.md): Run GGUF models locally with llama-server — full tokenizer support, CPU and GPU.
- [vLLM](https://docs.privategpt.dev/providers/vllm.md): High-throughput inference with vLLM — full capability support including structured output.
- [DaoXE](https://docs.privategpt.dev/providers/daoxe.md): Use DaoXE as an OpenAI-compatible cloud gateway — access GPT, Claude, Grok, GLM and more model families through a single endpoint.
- [OrcaRouter](https://docs.privategpt.dev/providers/orcarouter.md): Use OrcaRouter as an OpenAI-compatible cloud gateway — access 150+ models from OpenAI, Anthropic, Google, DeepSeek, Qwen and more through a single endpoint.
- [Cheaper Inference](https://docs.privategpt.dev/providers/cheaperinference.md): Use Cheaper Inference as an OpenAI-compatible cloud gateway for models from OpenAI, Anthropic, Google, DeepSeek, Z.ai and other labs.
- [Opper](https://docs.privategpt.dev/providers/opper.md): Use Opper as an OpenAI-compatible cloud gateway for 700+ models from 50+ providers, with chat and embeddings behind one key.
- [API Route](https://docs.privategpt.dev/providers/api-route.md): Configure PrivateGPT with API Route for OpenAI-compatible chat models and a separate local embeddings server.