Creating an LLM Provider
How to use the built-in default provider or connect your own cloud or self-hosted LLM backend.
An LLM provider is a connection to a language model backend. It stores the information the platform needs to authenticate with and send requests to that backend - nothing more. Providers don't have personalities or prompts of their own; that customization happens one layer up, at the agent level.
Default provider
Every workspace already includes an internal default (system) provider. It is managed by the platform, marked with a System badge, and gives you instant access to a catalog of over 450 models through a single connection - no setup required.
- The system provider cannot be edited or deleted, and its API key is never exposed.
- To use it, simply create an agent and pick the system provider, then choose any of its models. Browse the full catalog with pricing and capabilities under Settings → AI → Models (see Models).
- Usage on the default provider is billed with prepaid credits: your administrator loads credit onto the workspace, and model calls draw down the balance. Track remaining credit, daily/weekly/monthly usage, and credit loads under Settings → Billing → Usage. When credit runs out, chat is paused until more credit is loaded.
Start with the default provider
If you are new to the platform, use the default provider. It is the fastest way to create your first agent and start chatting - you can add your own providers later if you need them.
Supported provider types
If you bring your own backend, the provider picker groups available backends into three categories:
Hosted APIs from major vendors:
OpenAIAnthropicGemini(Google)DeepSeek
No built-in model hosting
Apart from the managed default provider above, the platform itself does not run or host language models - your own providers connect out to backends you control. For self-hosted options, the provider's URL must point to an LLM server that's already running and reachable somewhere external to the platform (on your own infrastructure, a private network, or a cloud VM).
Creating your own provider
Open the LLM Providers section
Navigate to Settings → AI → LLM Providers and select Add Provider.
Choose a provider type
Select the backend you want to connect from the grouped list. The fields shown next are the same for every type, but the values differ.
Fill in connection details
- Alias (required) - a friendly label to identify this provider throughout the platform (e.g.
OpenAI - Support Team). - Base URL (required) - the API endpoint of the provider:
- For cloud vendors, use their standard API endpoint (e.g.
https://api.openai.com/v1). - For self-hosted servers, the externally reachable address of your running model server (e.g.
https://models.example.comor an internal network address the platform can reach).
- For cloud vendors, use their standard API endpoint (e.g.
- API Key (optional) - your secret key from the provider's dashboard. Required for cloud vendors; only needed on self-hosted servers that require authentication.
Reachability
The Base URL must be reachable from the platform. localhost or loopback
addresses won't work unless the platform itself is running on that same
machine or network.
Save and verify
Click Add to save the provider. To confirm everything works, start creating an agent with this provider: if the platform can reach the endpoint, the model list will populate automatically. If it doesn't, double-check the Base URL and API key.
Sharing API keys is at your own risk
When you create your own LLM provider, you store your third-party API key with us so the platform can call that backend on your behalf. Only add keys you are comfortable sharing, and consider using a dedicated key with spending limits so you can revoke or cap it independently of your other usage.
Prefer not to share your AI keys?
The safest option is to set up a gateway or proxy API of your own in front of
your model vendor, with its own custom credentials, and connect the platform
to that proxy instead of handing over your direct vendor API keys. For
example, point an OpenAI Compatible or OpenRouter provider at your proxy
URL and give it only the proxy credentials. That way your real vendor keys
never leave your infrastructure - but the choice is yours.
Using multiple providers for the same vendor
There's no restriction against creating several providers of the same type. A common pattern is registering two OpenAI providers with different API keys - for example, one per team or project - so that usage and cost can be monitored independently from OpenAI's own dashboard, rather than blending together under a single key. The same idea applies to any other vendor: each provider you create is a fully independent connection, even if they point at the same underlying service.