> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tokios.com/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Tokios exposes private local models through https://api.tokios.com using an outbound-only connector tunnel.
> Use 'connector' for the local tokios-connector process.
> Use 'deployment' for the public model name in the API model field.
> Use 'upstream model id' for the model served by Ollama, llama.cpp, vLLM, LM Studio, or another local backend.
> API keys use the prefix sk-tok-. Connector tokens use the prefix ct-tok-.

# One endpoint for all your local models

> Point any agent or app at your local models — from anywhere.

I want to…

Connect a local runtimeExpose what you already run — without opening a port.

Ollama
LM Studio
llama.cpp
vLLM

→

[Open](https://docs.tokios.com/setup/connector-install.md)

Use Tokios with an agent or appPoint a coding agent or chat app at your local model.

Claude Code
Codex
Cursor

→

[Open](https://docs.tokios.com/guides/compatible-clients.md)

Choose a modelFind what fits your hardware, and which family fits your task.

Fit finder
By task

→

[Open](https://docs.tokios.com/guides/model-fit.md)

## Get started in 3 steps

[01Run a modelAny backend that speaks Chat Completions, on your own hardware.](https://docs.tokios.com/setup/supported-backends.md)

[02Connect TokiosInstall the connector and register your model in under 5 minutes.](https://docs.tokios.com/quickstart.md)

[03Use your endpointPoint any OpenAI- or Anthropic-compatible client at your endpoint.](https://docs.tokios.com/guides/compatible-clients.md)

## Verified compatibility

Check what works out of the box — [View the complete matrix →](https://docs.tokios.com/guides/compatible-clients.md)

ClientOllamavLLMLM Studio

Claude CodeVerifiedVerifiedVerified

OpenAI CodexVerifiedVerifiedVerified

OpenAI SDKVerifiedVerifiedVerified

Anthropic SDKVerifiedVerifiedVerified

Popular runtimes
[Ollama remote access](https://docs.tokios.com/guides/ollama-remote-access.md)
[LM Studio remote access](https://docs.tokios.com/guides/lm-studio-remote-access.md)
[vLLM remote access](https://docs.tokios.com/guides/vllm-remote-access.md)
[All runtimes →](https://docs.tokios.com/setup/supported-backends.md)

Popular clients
[Claude Code](https://docs.tokios.com/guides/claude-code.md)
[OpenAI Codex](https://docs.tokios.com/guides/openai-codex.md)
[Cursor](https://docs.tokios.com/guides/cursor.md)
[Cline](https://docs.tokios.com/guides/cline.md)
[Aider](https://docs.tokios.com/guides/aider.md)
[View all clients →](https://docs.tokios.com/guides/compatible-clients.md)

Playbook
[Model fit finder](https://docs.tokios.com/guides/model-fit.md)
[Which model for which task](https://docs.tokios.com/guides/model-by-task.md)
[Hardware reference](https://docs.tokios.com/guides/hardware-reference.md)

Reference
[API endpoints](https://docs.tokios.com/reference/api-endpoints.md)
[Connector config](https://docs.tokios.com/reference/connector-config.md)
[FAQ](https://docs.tokios.com/reference/faq.md)
[Troubleshooting](https://docs.tokios.com/reference/troubleshooting.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.