AI providers

Who it is for: whoever manages the account

What it is for

AI agents run on the provider and model you choose. You use your own key: the provider bills the usage to your account.

Available providers

OpenAI, Anthropic, Google Gemini, xAI, DeepSeek, Groq and Mistral. Each one needs its own key and you can have several loaded at once.

Load the key

➡️
Step:Go to Settings > External APIs > AI providers (LLM).

OpenAI also lets you load an Admin Key, used to fetch the real cost (see below).

Choose each agent's model

When you create or edit an agent you choose the provider and the model. Only the providers you have already connected are offered. You can use different providers on different agents.

Agent editor with the AI provider and model selector open (no keys shown).

Per-agent parameters

On each agent you can adjust:

ℹ️
Note:Not every provider or model accepts everything. Reasoning models reject temperature, and the range changes by provider (for example, Anthropic goes up to 1 and OpenAI or Gemini up to 2). In those cases the screen only shows the controls the model supports.

Audio always uses OpenAI

Audio transcription (Whisper) is always done with OpenAI, even when the agent runs on another provider. If you want agents to understand audio, load an OpenAI key.

AI cost: real and estimated

On the dashboard you see AI cost per model (see AI traces and cost):

Common errors

ProblemFix
The provider returns no modelsCheck the key is complete, with no spaces, and the account has balance
The agent does not answerCheck that the agent's provider and model have a key loaded
Cut-off repliesRaise the agent's max tokens
Audio is not understoodThe OpenAI key is missing