Agents: read the raw Markdown of this page, or start at llms.txt.

Cost ledger: published cost per Jev decision

TL;DR Across the builders' own runs a Jev decision costs roughly $0.000007 to $0.0004, from about 3x (GPT-5.6 Luna) to several hundred times less than the LLM or agent it was compared with. Most totals reconcile with input tokens × $0.042 per million, output free. Price your own workload as calls × state tokens × $0.042/M. Accuracy is on Head-to-head: Jev against other models and methods, Head-to-head: Jev inside agents, routers and tool gates and Head-to-head benchmarks: Jev on public datasets and suites. Split from head-to-head on 2026-09-25.

Community tier: the figures are the builders' own, and ÷ means our arithmetic: their total divided by their volume, or their per-1,000 figure divided by 1,000. Where a total does not reconcile with the price, the row says so. TypeSafe's docs win every conflict (Models, aliases, pricing, rate limits, context).

Published cost per decision

Per-decision figures are the source's, or ÷ where it publishes both numbers. Price is verified: $0.042 per million input tokens, output free (Models, aliases, pricing, rate limits, context). Independently, jev-fanout-bench (blowxian) found usage.cost equal to input tokens × $0.042/M on all 2,976 requests, with 122,844 output tokens not charged: verified.

The JevBench row is the v1.3.0 README's figure over the frozen v1.2 items; v1.4.2 keeps that basis (below).

Added 2026-09-25

How to read the ledger

• Reconciled rows are within rounding of input tokens × $0.042/M. Rows that don't reconcile are flagged: iammrduncan implies $0.040/Mtok; @voxmenthe's ~$0.0015 per query for ~18k tokens is on Head-to-head: Jev against other models and methods.
• Comparator prices are the builders' own at the time: cached or uncached, reasoning on or off, list or gateway price. Compare ratios, not absolute LLM costs.
• Gateways may add their own price or pass the list price through (OpenRouter billed list price above). Access routes: Platforms and gateways: Zapier, LangChain, Spring AI, Cloudflare, Netlify, Vercel, OpenRouter, Fly.io, Pydantic AI and other hosted routes to Jev.
• Cheap per call still adds up for repeated decisions over large state: price per hour (Failure reports: where Jev broke, lost, or was the wrong tool, cost surprises; Request mechanics: billing, limits, latency, calibration and stability).

Source links

Sorokin post; Greenberg; Robin; JevBench; Saplin; zhuyansen; QuicqDev; Dinh; Kumar; Bailey Jennings; OpenRouter; anisselbd; ipaulsmith; chepyle; TokenTrim; vclic; agentjournal; LiteLLM; iammrduncan; eugeniughelbur; World Monitor; ASSAY-001; typed-decisions card; Janus (FirasSX914); jev-rag-benchmark (erendikmenn); embodied-jev (FBddcz); tiershift (iamvatsalpatel); agent-chaperone; jevwire (Brainwires); jgrep and jsort (keltokhy); Sniff Test (DanRWilloughby); choosekit (NotXf1le); jev-ultralightspeed (collapseindex); jevscan-evm (devtooligan); jev-dataops (RenaGao); Bear Huddleston's study of anpicasso/hermes-jev-approvals.

Related

• Head-to-head: Jev against other models and methods, Head-to-head: Jev inside agents, routers and tool gates, Head-to-head benchmarks: Jev on public datasets and suites: what the money bought
• Request mechanics: billing, limits, latency, calibration and stability: billing, token overhead, packing; Models, aliases, pricing, rate limits, context: the official price

Sources

Raw captures listed in the frontmatter (private repo); original URLs above.