AI providers
Connect a hosted service or a server on your network and its models appear in the same picker as your local ones. Providers are optional and you add them yourself.
Add a provider
You can ask the agent to help add an AI provider; it opens the setup dialog so you enter the key there, rather than in chat. You can also open Settings → Connections and click Manage, then Add AI provider.
- Pick OpenAI, OpenRouter, or Custom compatible service for anything else that speaks the OpenAI API, such as a llama.cpp, vLLM or LM Studio server.
- Paste your API key. The dialog links to where you get one.
- Click Connect. LlamaBoss checks the key and loads the provider's model list.
For a local server with no key, choose No authentication under Advanced.
Sign in with ChatGPT
In the provider setup dialog, choose ChatGPT plan (Plus or Pro - sign in, no API key), then click Continue with ChatGPT. Your browser opens for sign-in and authorization. Complete that flow, return to LlamaBoss, and choose the models offered by the connection.
This connection uses your authorized ChatGPT plan rather than an OpenAI API key. Availability and usage limits depend on your account and the authorization granted. The API-key-based OpenAI connection remains a separate option. To disconnect, use the ChatGPT connection's sign-out control.
Choose models
Check the models you want in your picker. The search box filters long lists, and Refresh models reloads the catalog.
- Save keeps your checked models without changing the current chat.
- Save and use model also switches this chat to the highlighted model.
To add models later, open the provider again with Edit AI provider. It opens straight on the model list.
Add a model by exact ID
- Click the model pill and choose Add model....
- Select a saved provider and paste the exact model ID. You can give it a display name and choose its agent-tool or image-output options.
- Click Add model. The current chat keeps its model unless you select Use this model in the current chat.
The model does not need to appear in the provider's catalog. In the provider editor, Add ID also registers a model missing from search results. An existing ID keeps its saved settings rather than creating a duplicate. Cancel leaves the list unchanged.
With Agent Mode on, you can ask: Add this exact model ID to my saved OpenRouter provider and keep my current model selected. The agent can open guided provider setup when a connection is missing; enter credentials in the native dialog.
Adding an ID does not test availability, permissions, or API compatibility, and does not send a paid model test. Image-output options use LlamaBoss's supported chat-completions image flow; they do not add support for a provider's separate Images API. Test the model before relying on it.
Test a model
Test selected model sends two tiny requests: a plain chat message, and one that asks the model to call a test tool. It reports whether each worked. This button tests Chat Completions connections; for a model routed through OpenAI Responses, test by sending a normal chat message and then a tool request with Agent Mode on. You can pick a thinking level for the test. The provider charges its normal rate for these requests.
Advanced connection settings
| Setting | Use |
|---|---|
| Base URL and chat path | Where requests go. The dialog shows the full resolved URL. The chat path is normally /v1/chat/completions. |
| Authentication | Bearer token, x-api-key header, or no authentication for a local server. |
| Saved connection and key name | Use a key you've already saved instead of pasting a new one. |
| Tool protocol | Native function calls for providers with OpenAI-style tools. XML fallback for models that follow LlamaBoss's text tool format more reliably. |
| Reasoning format | How thinking settings are sent. Auto detects it from the host. Set OpenAI, OpenRouter or Chat template yourself for a custom server. |
For services without a model catalog, Enter model IDs without connecting lets you type the IDs yourself. The key isn't checked in that case.
Some OpenAI models, such as gpt-5.6-luna and gpt-6-astra, use OpenAI's newer Responses API in LlamaBoss so tools and thinking can work together. When you use them through api.openai.com, LlamaBoss switches to it automatically. Leave Allow agent tools enabled. If a custom service uses an explicit Responses path, compatibility depends on that service.
Model options
Select a checked model to set:
- Display name shown in the model picker.
- Allow agent tools. Turn this off for models that reject tool definitions; they'll still chat normally.
- Generate images for image models. LlamaBoss asks for image output and saves the returned images as files.
In Advanced: model IDs the same options are written one model per line:
provider/model-id = Friendly name
google/gemini-image-model = Image model [image]
some-model = Chat only [no-tools]Service keys for Skills
Settings → Connections → Manage service keys stores keys for other services your Skills use, such as Gmail or RunPod. Each key is either saved in LlamaBoss or read from a Windows environment variable. A Skill script receives a key as an environment variable named from the provider and key, like RUNPOD_API_KEY. From 0.1.23, a script gets only the keys its Skill's SKILL.md lists under ## Connections; see Skills that use API keys. In 0.1.21, every saved key, including AI provider keys, is passed to every script run. The persistent Python session never receives saved keys.
In Windows 0.1.21, saved API and service keys in %LOCALAPPDATA%\LlamaBoss\secrets.json are encrypted with Windows DPAPI for the current Windows user. ChatGPT sign-in tokens are protected separately in chatgpt_accounts.json. These files are not portable credentials for another Windows account or computer. The environment-variable option keeps the key value out of secrets.json. See Privacy & data for legacy-file migration and sharing precautions.
What's sent
When you chat with a provider's model, the request can include your message, recent conversation, Project and Skill instructions, tool definitions and results, and any images or document text needed for the task. The provider handles that under its own terms. Switch back to a local model to process chat locally. Tools and scripts can still use the network and send data to the services they call. See Privacy & data.