Which AI models does Pivra use?
The Fast, Balanced and Most capable models, which plans include them, what changed in October 2026, and where the Creativity setting applies.
Updated 8 Oct 2026
Pivra's chatbots run on OpenAI models. Across the product we call them by what they're for: Fast, Balanced and Most capable. This page is the one place that names the model behind each, so it's the page to check when a model changes.
The models
| Tier | Model | Plans | Creativity setting |
|---|---|---|---|
| Fast | GPT-6 Luna | Free, Starter, Pro and Agency. New chatbots start here. | Used |
| Balanced | GPT-5.4 Mini | Pro, Business and Agency. Founding and Business chatbots always run on it. | Used |
| Most capable | GPT-6.1 Sol | Not offered on self-serve plans | Not used |
Free and Starter chatbots run on the Fast model. On Pro and Agency you choose Fast or Balanced for each chatbot in Settings โ General โ AI Model. The pricing page names each plan's most capable tier โ "Balanced AI model" on Pro means Balanced is included, with Fast still selectable per chatbot.
Your knowledge sources are searched with OpenAI's text-embedding-3-small model on every plan.
Pivra sends the text a reply needs to OpenAI's API. Our privacy policy explains what is sent and how it's handled.
What changed in October 2026
OpenAI deprecated our previous Fast model on 1 October 2026 and will switch it off on 1 April 2027, and an older model it replaced switches off on 23 October 2026. So we moved every tier to a current model: Fast is now GPT-6 Luna, Balanced stays on GPT-5.4 Mini, and Most capable is now GPT-6.1 Sol, which isn't offered on self-serve plans.
Older model names map to these tiers
Older models can no longer be selected. A chatbot saved on one runs on the current model for its tier, within what your plan includes:
| Older model name (no longer used) | Tier it maps to | What the chatbot runs on now |
|---|---|---|
| GPT-5.4 Nano, GPT-4.1 Nano, GPT-4o mini, gpt-3.5-turbo | Fast | GPT-6 Luna (GPT-5.4 Mini on Founding and Business) |
| GPT-4.1 Mini | Balanced | GPT-5.4 Mini on Pro and higher plans and Founding; GPT-6 Luna on Free and Starter |
| GPT-4.1, GPT-4o, GPT-5.5, gpt-4, gpt-4-turbo | Most capable | GPT-5.4 Mini on Pro and higher plans and Founding; GPT-6 Luna on Free and Starter |
Do I need to do anything?
No. The switch is automatic. Your plan, price, message limits and knowledge sources stay the same, and you don't need to re-train anything.
If a chatbot was on an older model, Settings โ General โ AI Model shows a short notice. Saving the settings records the current model.
A new model can word things a little differently. It's worth asking your chatbot a few of your most common questions. For answers that must never vary, use refinements.
When the Creativity setting applies
Creativity (Temperature) in Settings โ General โ Response Tuning applies on the Fast and Balanced models, which covers every self-serve plan. Lower values keep answers consistent; higher values vary the wording more.
The Most capable model doesn't accept the setting, so Pivra doesn't send it there. It isn't offered on self-serve plans. See Improving chatbot responses.
Was this helpful?
If you have questions or suggestions, email us at support@pivra.ai .