Providers & models
Connect your own provider keys (OpenRouter, OpenAI, Anthropic, Google, xAI, Vercel AI Gateway, Volcengine Ark, or any OpenAI-compatible endpoint) and route a model to each feature.
Cordy is bring-your-own-key. You connect an API key for a provider you already use, and Cordy calls that provider directly from your browser — there is no Cordy proxy or account in between. You can connect several providers at once and assign a different model to each feature.
Built-in providers
Cordy ships with seven cloud providers built in. Each has a pre-filled default Base URL (which you can override) and a masked API-key field.
| Provider | Where to get a key | Notes |
|---|---|---|
| OpenRouter | openrouter.ai | One key, access to 100+ models across vendors |
| OpenAI | platform.openai.com | GPT models |
| Anthropic | console.anthropic.com | Claude models |
| aistudio.google.com | Gemini models (Google AI Studio) | |
| xAI | console.x.ai | Grok models |
| Vercel AI Gateway | vercel.com | One key in front of many providers; Base URL is fixed |
| Volcengine Ark | volcengine.com | China-region models; the Provider Center card is labeled 火山方舟 |
You don't need all of them — one is enough to start. OpenRouter is a good first choice because a single key unlocks many models.
Custom OpenAI-compatible providers
Beyond the built-ins, you can add your own OpenAI-compatible endpoint from the Custom Providers section (in the dashboard). Give it a display name, a Base URL, and an API key, then type the model IDs you want to use (one per line) — custom endpoints aren't auto-discovered, so you list their models yourself. This covers self-hosted gateways and any service that speaks the OpenAI API.
For local runtimes like Ollama or LM Studio over loopback, use the dedicated Local-Native Runtimes setup instead — see Local & on-device AI.
Adding a key
API keys are managed in the dashboard's Provider Center.
- Open the dashboard (from the side-panel header) and go to Settings → AI Config → API Providers.
- Find your provider's card. Paste your key into the API Key field (it's masked), and optionally adjust the Base URL.
- Click Detect to verify the connection. The status badge updates to Available, Unavailable, Checking, or Not configured, and a successful check refreshes the provider's model list.
- Repeat for any other providers you want.
If a provider shows as configured but its key later turns up missing or unreadable (for example, it was cleared with your browsing data), Cordy shows an inline warning asking you to re-enter it.
Per-feature model routing
Different jobs deserve different models — a big model for chat, a fast, cheap one for translation. Under Settings → AI Config → Scenario Model Routing, Cordy gives each feature its own slot:
- Chat — the main conversation model.
- Translation — used by the floating menu, command palette, and translation actions.
- Explanation — used by "explain."
- Summarization — used by "summarize."
- Bookmark classification — used to auto-categorize bookmarks. It has a Follow chat model switch (on by default); turn it off to give classification its own model.
- Read aloud (TTS) — the text-to-speech engine and voice (see Read aloud).
For each text slot you choose a provider and model, and optionally a context limit — Standard (200K) (the smaller of the model's window and 200K) or Auto max (the model's full window). A slot can point at a cloud provider, a custom endpoint, or a local runtime.
Switching models mid-chat
You don't have to open Settings to change models. The composer shows the current model — click it to search and switch for the current conversation. The model selector is searchable (Esc clears the search), and shows just the model name without the vendor prefix. The compact routing card in the side panel links to the full dashboard settings when you need to add a key.
Local & on-device models
You can route any slot to a model that runs on your machine instead of the cloud — Chrome's built-in Gemini Nano, in-browser Gemma models via WebGPU, or your own local runtime (Ollama, LM Studio, llama.cpp, vLLM, LocalAI) over loopback. Setup and requirements are in Local & on-device AI.
Key security
- Keys are encrypted and stored only on this device, through Cordy's secure storage — never in plain settings, never uploaded.
- Requests go directly to the provider you configured. Cordy runs no backend and never sees your traffic.
- Removing a key or the extension deletes it locally. Keys are not included in data backups, so you'll re-enter them after restoring a backup.
See Privacy & permissions for the full data model.
Troubleshooting
- "API Key Required" / no models listed. The provider isn't configured, or Detect hasn't succeeded. Re-check the key and Base URL.
- "No models available" after adding a key. Click Detect to refresh the catalog; for a custom endpoint, make sure you've typed model IDs manually.
- A model rejects a parameter. Some models don't support every option; try another model or provider.
- Key "missing" warning. Your stored key was cleared or corrupted — re-enter it in the Provider Center.