Settings
Choose a model
Every AI Agent answers with the OrhanAI default model unless you choose another. OrhanAI picks it for good answers at a low cost, and the model picker names it. On a plan that includes model choice, open the AI Agent's Settings, General and pick its AI model. The choice is per AI Agent, so one can answer with Claude while another stays on the default.
Only the AI Agent's replies use the chosen model. Background work such as conversation summaries, sentiment, lead scoring, training and knowledge search stays on Gemini. Web search works only on Gemini, so an AI Agent with web search on and no model of its own answers with Gemini.
Models
Available models
OrhanAI default
Chosen by OrhanAI for good answers at a low cost, currently a fast GPT or Gemini model, with Gemini as the backup. Used by every AI Agent that has no other model chosen and by every plan; the model picker names it. Background work stays on Gemini.
Claude
Anthropic's Claude Haiku 5.5, Sonnet 5.5 and Opus 5.5, from fastest to most capable, and Claude Fable 5.1 on your own Anthropic key.
OpenAI GPT
GPT-6 Luna and GPT-6.1 Sol, from fastest to most capable, and GPT-6 Astra on your own OpenAI key.
Google Gemini
Gemini 3.8 Flash and Gemini 4 Argon, from fastest to most capable. Gemini is also the one model family that can search the web for an answer.
AI credits
AI credits per answer
On the OrhanAI key, a more capable model spends more AI credits for each answer it sends, because it costs more to run. The faster models spend one, like the default model, and the most capable ones spend several. The model picker in the AI Agent's settings shows how many each model spends today, and that number can change.
A very long conversation, or an answer that searches the web, costs more to write, so it can spend a few more AI credits than the number shown, never more than are left. When a provider raises a model's price, the number changes a day before, and the people who manage the AI Agents using it are told 7, 3 and 1 days ahead.
A model that spends more than one AI credit only answers while enough credits are left for it. Replies your team writes are always free.
Your key
Your own API key
- Someone who manages developer settings saves an Anthropic, OpenAI or Google Gemini API key under Settings, AI models.
- An AI Agent can then answer with that provider's models on your key. Those answers spend no AI credits; the provider bills your workspace directly.
- Keys are stored encrypted, and only their last four characters are ever shown again.
- If a saved key stops working, for example because it was revoked, the people who manage developer settings are told, and answers come from the default model until the key is fixed.
Fallback
When the default model answers
A visitor always gets an answer. When the chosen model cannot write one, the default model answers instead:
- Your own API key failed or was removed.
- The workspace is no longer on a plan that includes choosing a model.
- There are not enough AI credits left for a model that spends more than one.
- The visitor sent an image and the chosen model does not read images.
Data
Where conversations go
An AI Agent set to a Claude model sends the conversation it answers, with the trained knowledge retrieved for it, to Anthropic; one set to a GPT model sends it to OpenAI. Both are listed on the sub-processors page as used only when you choose one of their models.
Team and roles
Invite teammates, choose built in or custom roles, limit people to chosen AI Agents, transfer ownership, and see what each role can do.