> ## 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.

# Cloud AI Providers: Anthropic, OpenAI, Gemini, and More

> Connect Luminy to Anthropic, OpenAI, Google Gemini, GitHub Copilot, OpenRouter, and 15+ other cloud AI providers using your own API keys or OAuth.

Cloud providers give you access to the most powerful frontier models available today — Claude, GPT-4o, Gemini 2.5 Pro, and many more. You bring your own API key for each provider you want to use; Luminy stores it locally on your device and uses it directly when making inference requests. No key ever passes through Luminy's servers.

## Adding a cloud provider API key

<Steps>
  <Step title="Get your API key">
    Visit the provider's developer console and create an API key (see the per-provider instructions below).
  </Step>

  <Step title="Open Settings in Luminy">
    Click the gear icon or press <kbd>⌘,</kbd> / <kbd>Ctrl+,</kbd>.
  </Step>

  <Step title="Select the provider section">
    Scroll to the provider you want to configure — for example, **Anthropic** or **OpenAI**.
  </Step>

  <Step title="Paste your key and save">
    Paste the API key into the field and click **Save**. The provider's models appear in the model selector immediately.
  </Step>
</Steps>

<Note>
  API keys are stored locally on your device and are never transmitted to Luminy's servers.
</Note>

***

## Provider details

<AccordionGroup>
  <Accordion title="Anthropic" icon="a" defaultOpen>
    Anthropic's Claude models are best-in-class for code understanding, long-context reasoning, and instruction following.

    **Get your key:** [console.anthropic.com](https://console.anthropic.com)

    **Recommended models:**

    | Model ID                      | Notes                                |
    | ----------------------------- | ------------------------------------ |
    | `anthropic:claude-opus-4-5`   | Most capable, best for complex tasks |
    | `anthropic:claude-sonnet-4-5` | Balanced speed and capability        |
    | `anthropic:claude-haiku-3-5`  | Fastest and most cost-efficient      |

    **Prompt caching:** Luminy takes full advantage of Anthropic's prompt caching, which significantly reduces costs on long conversations and large codebase sessions. Repeated context — system prompts, file contents, project rules — is served from cache rather than counted as new input tokens each turn.
  </Accordion>

  <Accordion title="OpenAI" icon="robot">
    OpenAI's GPT and o-series models offer strong all-around coding performance and the broadest ecosystem support.

    **Get your key:** [platform.openai.com](https://platform.openai.com)

    **Recommended models:**

    | Model ID             | Notes                                 |
    | -------------------- | ------------------------------------- |
    | `openai:gpt-4o`      | Fastest GPT-4-class model             |
    | `openai:gpt-4o-mini` | Lightweight and cost-efficient        |
    | `openai:o3-mini`     | Strong reasoning for complex problems |

    **Automatic prefix caching:** OpenAI automatically caches common prefixes server-side, so repeated context in long sessions is handled without any extra configuration.
  </Accordion>

  <Accordion title="Google Gemini" icon="google">
    Gemini models from Google DeepMind excel at long-context tasks and multimodal inputs.

    **Get your key:** [aistudio.google.com](https://aistudio.google.com)

    **Recommended models:**

    | Model ID                  | Notes                               |
    | ------------------------- | ----------------------------------- |
    | `gemini:gemini-2.0-flash` | Fast and capable for everyday tasks |
    | `gemini:gemini-2.5-pro`   | Top-tier reasoning and code quality |

    **Automatic prefix caching:** like OpenAI, Gemini handles prefix caching automatically on the server side.
  </Accordion>

  <Accordion title="GitHub Copilot" icon="github">
    GitHub Copilot integration uses **OAuth** — no API key is needed. Luminy authenticates using your GitHub account, so your Copilot subscription covers usage.

    **How to connect:**

    <Steps>
      <Step title="Open Settings → GitHub Copilot">
        Navigate to the GitHub Copilot section in Luminy Settings.
      </Step>

      <Step title="Sign in with GitHub">
        Click **Sign in with GitHub**. A browser window opens for the OAuth authorization flow.
      </Step>

      <Step title="Authorize Luminy">
        Approve the authorization request. Luminy receives an OAuth token and stores it locally.
      </Step>
    </Steps>

    **Model ID format:** `copilot:gpt-4o`, `copilot:claude-3.5-sonnet`, etc. — Luminy fetches the list of models available to your Copilot subscription automatically after sign-in.
  </Accordion>

  <Accordion title="ChatGPT" icon="comment">
    The ChatGPT provider connects to `chatgpt.com` via OAuth, giving access to models through your ChatGPT account rather than the OpenAI API.

    **How to connect:**

    Navigate to **Settings → ChatGPT** and click **Sign in**. Follow the OAuth flow in the browser. No API key is required — your ChatGPT account subscription is used.

    **Model ID format:** `chatgpt:<model-id>`
  </Accordion>

  <Accordion title="OpenRouter" icon="arrows-split-up-and-left">
    OpenRouter provides a single API key that routes to 100+ models from dozens of providers — a great option if you want to experiment with many models without managing multiple keys.

    **Get your key:** [openrouter.ai/keys](https://openrouter.ai/keys)

    **Model ID format:** `openrouter:anthropic/claude-3.5-sonnet`, `openrouter:google/gemini-flash-1.5`, etc. — model IDs follow OpenRouter's `vendor/model` naming convention.

    <Tip>
      OpenRouter is the fastest way to try a wide variety of models with a single API key. Many models also have free tiers available.
    </Tip>
  </Accordion>

  <Accordion title="xAI (Grok)" icon="x">
    xAI's Grok models are configured with a standard API key.

    **Get your key:** [console.x.ai](https://console.x.ai)

    **Model ID format:** `xai:grok-3`, `xai:grok-3-mini`, etc.
  </Accordion>

  <Accordion title="Mistral" icon="wind">
    Mistral AI offers the Mistral and Mixtral model families, known for strong performance at efficient parameter counts.

    **Get your key:** [console.mistral.ai](https://console.mistral.ai)

    **Model ID format:** `mistral:mistral-large-latest`, `mistral:codestral-latest`, etc.
  </Accordion>

  <Accordion title="Groq" icon="bolt">
    Groq's LPU inference hardware delivers some of the fastest token generation speeds available in the cloud.

    **Get your key:** [console.groq.com](https://console.groq.com)

    **Model ID format:** `groq:llama-3.1-70b-versatile`, `groq:mixtral-8x7b-32768`, etc.
  </Accordion>

  <Accordion title="Other providers" icon="ellipsis">
    Luminy also supports the following providers — all configured the same way (Settings → provider section → paste API key → Save):

    | Provider          | Get your key                                                         | Model ID prefix |
    | ----------------- | -------------------------------------------------------------------- | --------------- |
    | DeepInfra         | [deepinfra.com](https://deepinfra.com)                               | `deepinfra:`    |
    | Cerebras          | [cloud.cerebras.ai](https://cloud.cerebras.ai)                       | `cerebras:`     |
    | Cohere            | [dashboard.cohere.com](https://dashboard.cohere.com)                 | `cohere:`       |
    | TogetherAI        | [api.together.xyz](https://api.together.xyz)                         | `togetherai:`   |
    | Perplexity        | [perplexity.ai/settings/api](https://www.perplexity.ai/settings/api) | `perplexity:`   |
    | Alibaba DashScope | [dashscope.aliyun.com](https://dashscope.aliyun.com)                 | `alibaba:`      |
    | Venice AI         | [venice.ai](https://venice.ai)                                       | `venice:`       |
    | Fireworks         | [fireworks.ai](https://fireworks.ai)                                 | `fireworks:`    |
  </Accordion>

  <Accordion title="OpenCode Zen (no key required)" icon="star">
    OpenCode Zen provides a set of free models that require no API key at all. They are always available in the model selector as soon as you launch Luminy.

    **Available models:**

    | Model ID                              | Display name           |
    | ------------------------------------- | ---------------------- |
    | `opencode-zen:big-pickle`             | Big Pickle             |
    | `opencode-zen:mimo-v2.5-free`         | MiMo-V2.5 Free         |
    | `opencode-zen:nemotron-3-ultra-free`  | Nemotron 3 Ultra Free  |
    | `opencode-zen:deepseek-v4-flash-free` | DeepSeek V4 Flash Free |

    <Tip>
      OpenCode Zen models are a great zero-cost option for quick tasks or for evaluating Luminy before committing to a paid API key.
    </Tip>
  </Accordion>
</AccordionGroup>

***

## Security note

<Note>
  Your API keys are stored locally on your device and used only for direct requests to the respective provider APIs. Luminy never proxies your keys through its own servers.
</Note>