Agent Studio
AI Provider Keys
Path: Settings → AI Gateway → AI Provider Keys
AI Provider Keys are the LLM provider credentials your agents and task agents run on: your own OpenAI or Gemini key, or the built-in Foldspace key. Foldspace uses them to call the model on your behalf. A built-in Foldspace key ships by default, so everything works out of the box, and you can add your own key from a supported provider.
The keys list
Section titled “The keys list”Each row is a key, with:
| Column | What it shows |
|---|---|
| Name / Description | Your label for the key. |
| Provider | The key’s provider (Foldspace built-in, OpenAI, or Gemini). |
| Usage | The agents and task agents currently using this key. Open it to see the full list. |
| Default | A star marks the default key. |
| Created By / Created Date | Provenance. |
Foldspace includes a built-in Foldspace key (the “Default Foldspace Key”) so new accounts have a working model immediately.
Add a provider key
Section titled “Add a provider key”-
Click Create.
-
Fill in the key:
Field Purpose Provider The LLM provider: OpenAI or Gemini. Name A label for the key. Description Optional note. Secret Key The provider’s secret API key. Default When on, any new Agent or Task Agent automatically uses this key. -
Click Test Connection to verify the key reaches the provider, then Create.
Add keys for high availability
Section titled “Add keys for high availability”Failover can only route to keys you’ve added. Add a key on both providers, one OpenAI and one Gemini, so that when one provider is throttled or down, Foldspace can cross to the other on your own key instead of falling straight back to the built-in Foldspace key. Adding a second key for the same provider also lets failover spread load across your keys. See High Availability for the full fallback order.
The default key
Section titled “The default key”The starred key is the default: new agents and task agents automatically use it. You can change which key is default at any time. To see exactly which agents and task agents a key powers, open its Usage: it lists every Agent and Task Agent (with links) bound to that key.
Related
Section titled “Related”- High Availability: how failover routes across your provider keys.
- Token Quotas: cap token spend per agent, user, and tier.
- User Management: the AI Provider Key feature is one of the permissions you can grant per teammate.
- Cost & tokens: track spend and token consumption per model and provider.