Skip to main content
All three models share Enforce Content (POST /api/v3/content/validate). You pick a tier with model_engine in the request body. There is no separate Mini or Max route. The public name for the default tier is Flagship. The body value is anchor_3_0. Older internal notes called this Base; that name is not used in these docs. Pass anchor_3_0 whenever another document says Base or Anchor 3.0.

​
Mini

model_engine: "anchor_3_0_mini" Detection only. The response is a per-message yes/no verdict plus a per-message violation summary. There are no per-line violations, no fix.suggested_text, and no rewrite. The payload is roughly half of Flagship’s. Do not send validation_scope on Mini. Scope a Flagship or Max call instead. When to use. High-volume pre-checks, a first-pass flag before a Flagship or Max call, or any path that only needs “is this clean?” Mini skips the rewrite pass, so it returns sooner than Flagship or Max on the same input. When not to use. You need a compliant rewrite, per-line quotes, or a scoped rule set.

​
Flagship

model_engine: "anchor_3_0" (default) Per-line violations plus rewrite. This is the primary enforce model: detect, rewrite, and verify. Activated custom rules run without training. An optional adapter adds that policy’s judgment on top. Training Studio is Flagship-only at launch. When to use. Chat, email, and agent replies where you will apply fix.suggested_text or block. Start here unless you have a reason to pick Mini or Max. When not to use. You only need a detection flag (use Mini), or you want uploaded policies evaluated at inference on Max.

​
Max

model_engine: "anchor_3_0_max" Per-line violations plus rewrite, same shape as Flagship. Uploaded policies are evaluated at inference. There is no training step and no Training Studio charge. To run Max against a policy you uploaded:
  1. Import the document and wait for extraction.
  2. Activate the rules.
  3. Call enforce with model_engine: "anchor_3_0_max" and the import id in validation_scope.imports.
When to use. Custom policies you do not want to train, or a mix of managed rulepacks and uploaded rule text on one call. When not to use. You only need detection (use Mini), or you already have a Flagship adapter and want that adapter’s judgment (use Flagship).

​
Latency

Typical Flagship (Anchor 3.0) latency is 1.63 seconds. Mini is detection only, so it skips the rewrite pass and returns sooner. Flagship and Max run detection and then rewrite. Quality, precision, recall, F1, and latency are on the Anchor 3.0 benchmark. These are not SLOs; long content, cold starts, and fallback can take longer. Use mode: "sync" for short content and mode: "async" when you expect to wait.

​
Request shape

Same endpoint, same fields, different model_engine:
Replace anchor_3_0 with anchor_3_0_mini or anchor_3_0_max. Read the verdict from result on a completed job. See Act on Each Verdict for Pass / Fix / Block / Escalate. Mini responses omit per-line violations and rewrite fields. Handlers that read violations[].fix.suggested_text must branch on Mini or skip that tier.

​
Next