Sample data. Not a customer bill.

Policy editor

Planned

Right-size, cascade, cache, batch, automation, YAML and history.

Eval lab · eval_scored · version 3

Output and reasoning

Length, structured output and reasoning effort. Quality-gated before it can change a route.

Max output tokensReasoning effort

Require structured output

Eval backfill follows a cost-first policy.
A served response has to score at least 0.80 and finish inside 86,400,000 ms at p95.
Anything priced above $0.0100 a request is outside this policy.
Right-size is off, so Parezen keeps the model the app asked for.
Cascade is off, so there is no cheap-first attempt.
If the chosen model fails, fallbacks run in order: google/gemini-2.5-flash.
Output is capped at 400 tokens and must be structured, with reasoning effort none.
The route is marked async, so eligible work can take the provider's batch price.
Exact-match response cache is opt-in and on for this route.
Semantic cache is Planned and is not applied.
Automation may apply changes this policy already allows.

12 sample requests on this route.

This sample has no cascade escalations. When one happens, its cost is included, not hidden.
Exact-match cache is on. This sample has no exact-match hits yet, so the projection does not invent one.
Semantic cache is Planned and is excluded.