jev-fanout-bench: measure batching, billing and answer stability

A measurement harness compares many typed questions in one Jev request with the same questions asked separately. It varies state size and question count, repeats requests to estimate noise and publishes response-level usage, billing and latency evidence.

Notes

The September 23 run records 2,976 requests to jev-1.13-20260917 through OpenRouter, an inferred fixed overhead of 261 input tokens per request and serial eight-question latency savings of 7.7–8.6×.

source-backed — Public repository, docs or live artifact. About this label

Destinations

Availability & demo checks

Report a problem →

Also linked

• Published aggregate dataset ↗

Filed under

• #benchmark
• #evaluation
• #batching
• #cost

In collections

• Benchmarks & independent tests →