How do I choose which AI model answers?
Click the model name next to the message box and pick one. Auto, first in the list, picks for you; the list also has Claude, GPT, Grok and Perplexity, plus DeepSeek, Kimi, Qwen and MiniMax. The choice lasts for the session, and Credits are charged for the model that actually answered.
Pick a model
- In chat, click the model name shown next to the message box.
- Models are grouped by maker, each with the country it comes from. Click a maker to see its models, then pick one.
- Send your message. The reply comes from that model, and it stays selected for the rest of the session.
- Claude by Anthropic, GPT by OpenAI, Grok by xAI and Perplexity, which searches the web as it answers: USA.
- DeepSeek, Kimi by Moonshot AI, Qwen by Alibaba and MiniMax: China. DeepSeek reads text only, not images.
Some tasks pick for you: Quick Search and Deep Research switch to a Perplexity model because they need live sources.
Auto
Auto is the first option in the list, marked Recommended. An Agent starts its chats on Auto unless you set it to a different model on its Edit page. Sagelyn picks the model for you, based on the task and the Agent rather than the wording of your message, and only ever picks US-built models:
- Quick Search and Deep Research use a Perplexity model, because they need live sources.
- The Social Media Manager and the AI Visibility Manager use Claude Opus 5.5.
- Everything else uses Claude Sonnet 5.5.
Every reply is labelled with the model that answered it, for example “Answered by Opus 5.5”, and Credits are charged for that model.
The Agent's default
Each Agent has a default model, set on its Edit page, and its new chats start on that model. Choosing a model in chat changes this conversation, not the Agent's default. An Agent still set to a retired model starts on Auto if it was a Claude model (such as Sonnet 5), or on the current GPT model if it was a GPT model.
Which model should I use?
Auto, the first option, marked Recommended. It picks the model for each agent: Claude Opus 5.5 for the Social Media Manager and the AI Visibility Manager, Claude Sonnet 5.5 for most other agents, and a Perplexity model for Quick Search and Deep Research. Each reply shows which model answered. Choose a specific model when you want that one.
What does the country next to each model mean?
It's where the model's maker is based: USA for Claude, GPT, Grok and Perplexity, China for DeepSeek, Kimi, Qwen and MiniMax. Auto only ever picks US-built models; the others answer only when you choose them.
An Agent was set to a model I can't find in the list.
Retired models are no longer listed, so there's nothing to fix. An Agent that was on Sonnet 5 now starts on Auto; one on a retired GPT model starts on the current GPT model.
Does switching models change what the Agent knows?
No. Instructions, knowledge files and your business memory are the same whichever model answers. The model is the brain; the Agent is the job.
Do different models cost different amounts?
Yes. Credits are charged for the model that produced the reply, so larger models cost more per message.