Radar / Ideas / ModelReceipts: proof that the model…

ModelReceipts: proof that the model you paid for is the model that answered

daily ideaambitiousJEV confidence 0.56JEV monetization 0.592026-11-12
OutcomeZero unverified API spend: every AI invoice a team pays carries proof of which model actually served each call, and any substitution is caught within a day.

The problem

Teams buy frontier models through resellers, gateways, and marketplaces — OpenRouter, relays, regional providers — and then have no way to verify what they got. The model string in the config says GPT-5 or Claude Opus; the backend may quietly serve a cheaper model, a heavy quantization, or a previous generation. A 2026 survey of 17 third-party wrappers found 45.8% had endpoint-level identity failures, including wholesale swaps like GPT-5 to GLM-4-9B, and OpenRouter users are already asking in public whether providers quietly serve cheaper models behind the name they pay for.

The idea

A continuous audit service for AI API spend. It sits as a proxy in front of a team's providers, fingerprints the model behind each endpoint with calibrated probes (text probes plus tool-call distribution tests), and samples calls for cryptographic proof where the provider supports it. Every invoice line gets a receipt: the model named, the model measured, and a confidence score. Substitution is flagged within a day, with the statistical evidence attached, before the next billing cycle.

Why now

Three things converged this month: Anthropic's FlashProve (2 Nov) made model identity cryptographically provable with zkSNARKs; the AgentProv paper (arXiv 2609.00052) showed tool-call distributions fingerprint a backend even when the text channel is discarded; and OpenRouter's Auto Router (6 Nov) made multi-provider routing a default — which means the substitution surface just grew, because every routed call is a call whose backend the buyer cannot see.

What it combines

FlashProve's cryptographic proof of model identity + OpenRouter Auto Router's multi-provider routing + Sarvam Prism's 44 ms decision scoring + GPUWorks' serving telemetry. Proofs without routing context have nothing to audit, routing without proofs is blind trust, and cheap per-call verdicts without either are just another log line — together they are a continuous audit: every call fingerprinted, sampled calls proven, and every invoice reconcilable.

MVP

Weekend MVP: a proxy that sits in front of one provider, runs calibrated text probes against a known reference for one model pair, and emits a daily pass/fail identity report with the statistical confidence attached. Skip: zk proofs, tool-call fingerprinting, multi-provider support, and invoice reconciliation.

How it makes money

Budget owner: the platform-engineering or FinOps lead, out of the existing LLM observability and API-spend budget. Pricing anchor: Helicone Pro at $79 per month (helicone.ai/pricing, Oct 2026) — teams already pay that for proxy observability that cannot prove identity, and ModelReceipts prices in the same band with a per-audit overage. Willingness-to-pay evidence: a CISPA paper accepted to ACM CCS 2026 ("Real Money, Fake Models") found 45.83% of fingerprint checks failed identity verification on shadow APIs used in 187 research papers, and the AgentProv paper documents wholesale backbone swaps in commercial wrappers — buyers are already paying for models they are not receiving.

The moat

Providers cannot credibly audit themselves — a reseller that offers its own "proof" is asking buyers to trust the party being checked, so the independent auditor is structurally necessary. Observability incumbents would have to rebuild around statistical identity testing and zero-knowledge proofs, a different architecture from request logging, and Helicone itself is in maintenance mode after its March 2026 acquisition, leaving the category leader stalled.

Distribution

B2B via API gateways and routers — an add-on audit inside OpenRouter, Portkey, and LiteLLM-style gateways, so every team routing through them gets receipts by default. Direct sale to platform-engineering and FinOps teams buying AI APIs through resellers.

Why it wins

Helicone, Langfuse, and LangSmith log requests, costs, and traces — none of them can tell you whether the backend was the model you bought. Fingerprinting papers exist as research, not as a product. ModelReceipts is the only service whose deliverable is an identity verdict per provider, not a prettier cost dashboard.

Risks

Biggest risk: false accusations — a fingerprint test that flags an honest provider destroys trust in the auditor faster than a missed substitution does. The MVP de-risks it by publishing the false-positive rate on known-honest controls alongside every verdict, and by starting with detection (flag for review) rather than automated billing disputes.

Build it with

Repo to start from

modelreceipts — a proxy that fingerprints the model behind any AI API endpoint and emits a daily identity verdict with statistical confidence.

Evidence

Get the week's best AI launches, plus 3 ideas worth building

One email every Saturday. Ranked by traction, not hype. Free.