BEATRICE Docs
Sections

Models

GET /v1/models lists the models available to your organization right now.

beatrice-flash

The general-purpose model: polished Italian, coding, reasoning.

FeatureValue
Idbeatrice-flash
Context262,144 tokens
Default output8,192 tokens plus the reasoning of the level
Maximum output (max_tokens)49,152 tokens
Reasoningyes, in reasoning_content
Tool callingyes, parallel too
  • Reasoning: the model thinks before answering. Its reasoning comes in the reasoning_content field (when streaming: delta.reasoning_content) and counts as output tokens. With a max_tokens too low the answer may stay empty because reasoning used all the room.
  • How much it reasons: set reasoning_effort. none answers at once, without reasoning (minimal is the same); low is the default; medium reasons more; high (or xhigh) reasons thoroughly, is slower and uses more tokens. Reasoning stops at 2,048 tokens with low, 8,192 with medium and 16,384 with high; without max_tokens the room for the answer (8,192 tokens) comes on top of the reasoning. Any other value is a 400 error. On the Free plan the model always answers without reasoning, whatever level is asked. On a short question, measured on 2026-10-03: about 1.5 seconds with none, 4 with medium, 20 with high.
  • Cached context: when you continue a conversation the model has already seen, the repeated part is read from the cache. It is faster and does not count as input towards your limits (see Limits and plans).

beatrice-flash-extreme

The same model, without our automatic red-line check. It answers on its own, with its own refusal training.

FeatureValue
Idbeatrice-flash-extreme
Modelthe same as beatrice-flash
Limitsidentical
Red linesno check of ours
  • What changes: our five questions are not asked on the request or the answer, so you never get finish_reason: "content_filter" from us. The 503 safety_unavailable error goes away too.
  • What does not change: the five red lines are still rules of use (Red lines) and on this model you answer for them. Violations are handled through reports and account suspension. Usage and limits are counted as on any other model.
  • When to use it: when the check gets a legitimate job wrong, for example security research or legal and clinical texts, or when the last milliseconds of latency matter.
  • Who can use it: verified organizations, that is students, professionals with a VAT number, companies, organizations and public bodies. You ask for the verification in the console, on the Plan page. On the paid plans it also needs the Extreme add-on; the Free plan does not include it. Without these, GET /v1/models does not list it and a request gets 403 model_not_allowed.

The public id stays stable even when the model behind it changes: updates and replacements are announced in advance.

l'amor che move il sole e l'altre stelle