model field on a chatbot picks which AI model handles its conversations. Each model has its own quality/speed/cost trade-off — the table below is the source of truth for what you can send.
Picking a model
- Set
modelonPOST /chatbotsorPATCH /chatbots/{id}to one of the IDs below. - Leave
modelasnull(or omit it) to use the default,gpt-5.4-nano. - Unknown or disabled IDs fall back to the default — they won’t error.
Available models
Credit cost is per assistant message. A conversation is the sum of its
messages — a 10-turn chat on a 3-credit model spends roughly 30 credits.
Tooling and retrieval can adjust the total slightly; the dashboard’s usage
view is authoritative.
Plan limits
Model choice is plan-gated. On the free tier only single-credit models (gpt-5.4-nano, gemini-3.1-flash-lite) are available; paid plans unlock
every model. If a chatbot is set to a model the plan doesn’t include, it’s
served on the default single-credit model until the plan is upgraded — the
saved model value is preserved and re-applies automatically on upgrade.
Changing models on a live chatbot
PATCH /chatbots/{id} with a new model takes effect on the next conversation turn. Existing in-flight conversations stay on whatever model handled their last message until that turn completes.