Skip to content
๐Ÿค–Chatbot Settings

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

TierModelPlansCreativity setting
FastGPT-6 LunaFree, Starter, Pro and Agency. New chatbots start here.Used
BalancedGPT-5.4 MiniPro, Business and Agency. Founding and Business chatbots always run on it.Used
Most capableGPT-6.1 SolNot offered on self-serve plansNot 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 toWhat the chatbot runs on now
GPT-5.4 Nano, GPT-4.1 Nano, GPT-4o mini, gpt-3.5-turboFastGPT-6 Luna (GPT-5.4 Mini on Founding and Business)
GPT-4.1 MiniBalancedGPT-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-turboMost capableGPT-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 .