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

# Luminy AI Providers: Connect 20+ Models and Services

> Luminy supports 20+ AI providers including local Ollama models, Anthropic, OpenAI, Gemini, GitHub Copilot, and more. Configure any provider in Settings.

Luminy connects to more than 20 AI providers — from frontier cloud models like Anthropic Claude and OpenAI GPT-4o to fully private local inference via Ollama — all through a single unified interface. You configure each provider once in Settings, then switch between any model mid-session using the model selector in the chat composer. Your chosen model becomes your default for future sessions automatically, and all API keys are stored locally on your device.

## Configuring a provider

<Steps>
  <Step title="Open Settings">
    Click the gear icon or press <kbd>⌘,</kbd> (macOS) / <kbd>Ctrl+,</kbd> (Windows/Linux) to open Settings.
  </Step>

  <Step title="Select your provider">
    Scroll to the provider's section — for example, **Anthropic**, **OpenAI**, or **Groq**.
  </Step>

  <Step title="Enter your API key">
    Paste your API key into the key field. For OAuth-based providers (GitHub Copilot, ChatGPT), click **Sign in** instead.
  </Step>

  <Step title="Save">
    Click **Save**. Luminy verifies the key and the provider's models become available immediately in the model selector.
  </Step>
</Steps>

## Selecting a model

Use the **model selector dropdown** in the chat input area to choose any configured model. The change takes effect immediately — even mid-session. The model you select becomes your default for all new sessions going forward; you can change it at any time.

<Tip>
  You can maintain different default models for your main chat session and for Luminy's background agent (the agent that works on tasks autonomously). Both are configurable in **Settings → Model**.
</Tip>

## Provider categories

<CardGroup cols={3}>
  <Card title="Local Models" icon="server" href="/providers/local-models">
    Run Ollama models entirely on your own hardware. No API key, no data sent to the cloud, complete privacy.
  </Card>

  <Card title="Cloud Providers" icon="cloud" href="/providers/cloud-providers">
    Access frontier models from Anthropic, OpenAI, Google Gemini, GitHub Copilot, OpenRouter, and 10+ more cloud providers.
  </Card>

  <Card title="Custom Endpoints" icon="plug" href="/providers/custom-endpoints">
    Point Luminy at any OpenAI-compatible or Anthropic-compatible API — LM Studio, vLLM, Azure OpenAI, private deployments, and more.
  </Card>
</CardGroup>

## Model ID format

Every model in Luminy is identified by a **`provider-prefix:model-name`** string. You will see these IDs in the model selector and in any exported session data.

```text theme={null}
anthropic:claude-opus-4-5
openai:gpt-4o
gemini:gemini-2.0-flash
groq:llama-3.1-70b-versatile
qwen2.5-coder:7b          ← Ollama models use bare model names (no provider prefix)
openrouter:anthropic/claude-3.5-sonnet
```

<Note>
  Ollama is the one exception to the prefix rule. Luminy displays local Ollama models by their bare model name — for example, `qwen2.5-coder:7b` — without any extra provider prefix in the chat UI.
</Note>

## All supported providers

| Provider                  | Model ID prefix     | API key required | Notes                                           |
| ------------------------- | ------------------- | ---------------- | ----------------------------------------------- |
| Ollama                    | *(bare model name)* | No               | Local inference on your machine                 |
| Anthropic                 | `anthropic:`        | Yes              | Prompt caching for lower costs on long sessions |
| OpenAI                    | `openai:`           | Yes              | Automatic prefix caching                        |
| Google Gemini             | `gemini:`           | Yes              | Automatic prefix caching                        |
| GitHub Copilot            | `copilot:`          | OAuth            | Sign in with your GitHub account                |
| ChatGPT                   | `chatgpt:`          | OAuth            | Uses chatgpt.com                                |
| OpenRouter                | `openrouter:`       | Yes              | Access 100+ models with one key                 |
| xAI (Grok)                | `xai:`              | Yes              | Grok model family                               |
| Mistral                   | `mistral:`          | Yes              | Mistral & Mixtral models                        |
| Groq                      | `groq:`             | Yes              | High-speed LPU inference                        |
| DeepInfra                 | `deepinfra:`        | Yes              | Hosted open-source models                       |
| Cerebras                  | `cerebras:`         | Yes              | Ultra-fast Cerebras inference                   |
| Cohere                    | `cohere:`           | Yes              | Command R+ and other Cohere models              |
| TogetherAI                | `togetherai:`       | Yes              | Broad open-source model catalog                 |
| Perplexity                | `perplexity:`       | Yes              | Online-search-augmented models                  |
| Alibaba DashScope         | `alibaba:`          | Yes              | Qwen model family                               |
| Venice AI                 | `venice:`           | Yes              | Privacy-focused inference                       |
| Fireworks                 | `fireworks:`        | Yes              | Fast serverless open-source models              |
| OpenCode Zen              | `opencode-zen:`     | No               | Free models, no key needed                      |
| Custom (OpenAI-compat)    | `openai-compat:`    | Optional         | Any OpenAI-compatible API                       |
| Custom (Anthropic-compat) | `anthropic-compat:` | Optional         | Any Anthropic Messages API-compatible server    |