Model Receipts — universal model-call proof

Signed proof for every AI model call.

Prompt through Hive to a model. Get the response plus a signed, verifiable receipt for the call path. The receipt captures which provider and model answered, a hash of the prompt, a hash of the response, the per-phase timing, and an Ed25519 signature that verifies against did:hive:hivemorph. Two providers are live today — Mistral and DeepInfra — with several DeepInfra models receipted per call; the adapter layer is built to target many more.

What a model receipt attests

A model receipt proves the model-call route: the provider and model, the prompt hash, the response hash, the timing, the signature, and the verification result. It does not attest that the model output is correct. "Universal" describes the architecture — adapters registered per provider/model — not a claim that every provider is wired today. Live now: Mistral Leanstral plus a set of registered DeepInfra OpenAI-compatible models. We list exactly which DeepInfra models are wired — this is not a claim of access to DeepInfra's entire catalog. The rest of this page is explicit about what is live versus what is on the roadmap.

— The flow

Route in. Response and receipt out.

1 · Route
A SmartAgent selects a registered provider / model adapter for the prompt.
2 · Call
The provider is called live. Round-trip latency is measured, not estimated.
3 · Hash
Prompt and response are SHA-256 hashed — the receipt binds content by hash.
4 · Sign
Run metadata is canonicalized and Ed25519-signed into one receipt.
5 · Verify
The receipt verifies against the issuer key — offline-checkable, ok.
— Live today

Mistral Leanstrallive

The first wired adapter is Mistral Leanstral 1.5 (labs-leanstral-1-5). It is called live on the backend, and every call is receipted and verified. The worked example walks one full run end to end.

End-to-end (latest run)
~690ms
One live run — dominated by the provider round-trip. Not a benchmark average; the widget below pulls the current number.
Hive receipt overhead
sub-ms
canonicalize + hash + sign + verify combined ran under a millisecond in the recorded run.
Verification
ok
Ed25519 signature verified against did:hive:hivemorph via /v1/receipt/verify.

See the full run, hashes, and signature on the Leanstral receipt example.

— Live status

Run it against the live backendlive

These controls call hivemorph.onrender.com directly from your browser. Each button does real work: list the registered adapters, receipt a live Leanstral run, or run a SmartMorph route comparison. If a fetch fails, the last-known verified values below still stand on their own, and copyable curl commands are provided further down.

GET /adapters  ·  GET /leanstral-demo  ·  SmartMorph route
Idle — auto-loading live status…
Registered adapters
Live run status
pending
Provider · model
Run ID
Receipt ID
Verification
pending
Algorithm · issuer
Response SHA-256
Timing (ms)
Backend commit
Response preview (model output — not a verified answer)
Last known verified runrecorded 2026-07-04
Status
ok · true
Provider · model
mistral · labs-leanstral-1-5
Verification
verified · ok against did:hive:hivemorph
Timing (ms)
provider_call 708.51 · canonicalize 0.034 · hash 0.004 · sign 0.114 · verify 0.136 · total 708.80
Response SHA-256
ff11617efb0ffc3c51bf292ca701cef6bf0658104cbe5b55d28fb59ef8d6ad4f
Backend commit
afb99469edca
— Provider roadmap

What is live, what is ready to wire, what is next.

Adapters are registered per (provider, model). Live today: direct adapters for Mistral Leanstral and a registered set of DeepInfra OpenAI-compatible models, plus routed adapters via OpenRouter for Claude, Gemini, Grok, GPT and DeepSeek. The "Run live adapter check" button above reflects the current backend state.

Live today — Mistral

Live · verified

Wired, called live on the backend, and receipted on every call.

Mistral · Leanstral 1.5

Live today — DeepInfra

Live · configured

Registered DeepInfra models on the OpenAI-compatible chat surface. Each is configured on the backend and returns a real signed receipt on call. This is the set we have wired — not a claim of access to DeepInfra's full catalog. Some models produce clean demo text on a generic prompt; others need a model-appropriate prompt, so the live check labels each honestly.

moonshotai · Kimi-K2.7-Code zai-org · GLM-5.2 Qwen3-Coder-480B-A35B-Instruct-Turbo deepseek-ai · DeepSeek-V3.1-Terminus stepfun-ai · Step-3.7-Flash

Live today — routed via OpenRouter

Live · verifiedRouted

Reached through OpenRouter's OpenAI-compatible surface and receipted on every call. A routed receipt proves the Hive→OpenRouter call path and the selected model idnot first-party provider direct custody. First-party Claude/Gemini/Grok custody is a separate roadmap path (see below), not claimed by these receipts.

Anthropic · Claude Sonnet 4 Google · Gemini 2.5 Flash xAI · Grok 4.3 OpenAI · GPT-4o mini DeepSeek · Chat v3.1

Ready to wire — OpenAI-compatible

Compatible · not yet live

These providers expose an OpenAI-compatible chat API, which is the same shape the live adapters use. They can be registered without new receipt code — but none are wired or verified live yet.

Baseten Parasail Novita Hyperbolic SiliconFlow GMI Lightning AI Fal Telnyx

First-party direct adapters

Roadmap · premium custody

Claude, Gemini and Grok are already receiptable today via OpenRouter (rail above). This rail is the separate first-party direct-custody path: calling each provider's own API on a first-party account, so a receipt attests direct provider custody rather than a routed hop. No first-party adapter is wired for these yet — listing them here is a direction, not a capability claim. The receipt layer is provider-independent: once a first-party account key and adapter are configured, the same signed-receipt path applies with no change to the proof format.

Anthropic Claude · direct OpenAI · direct Google Gemini · direct xAI Grok · direct Manus · agent platform
— SmartAgent vs SmartMorphAgent

One receipts the route. The other receipts the change of route.

Live today

SmartAgent — receipts the selected path

Picks a model, calls it, and captures the call as one signed receipt.

  • Provider and model actually used
  • Prompt hash and response hash (SHA-256)
  • Per-phase timing of the call
  • Ed25519 signature + verification result
Live demo

SmartMorphAgent — receipts the change of route

Compares candidate model stops on observed signals, chooses a route by explicit rule, and receipts both the morph decision and each model call.

  • Re-routes on cost, latency, or capability
  • Re-routes on jurisdiction or payment / x402 availability
  • Distinguishes each model-call receipt from the morph-decision receipt
  • Signs the morph decision and each call
Honest status

With direct and routed providers live — Mistral and DeepInfra as direct adapters, plus Claude, Gemini, Grok, GPT and DeepSeek routed via OpenRouter — a SmartMorph route comparison is demonstrable today: the "Run SmartMorph route demo" button above runs live model calls (which can mix direct and routed candidates), receipts each, and selects a route by explicit rule. When the selected stop is reached through OpenRouter, the morph-decision receipt records a routed_via caveat — proving the routed call path and selected model id, not first-party custody. It is economic-routing capable / a demo decision — it compares live call signals and signs the choice; it does not record an economic or physical state transition. When an actual route change or x402 settlement occurs, each becomes its own receipted event.

— For developers

Call it yourself

Read-only endpoints. Verification is free; the receipt round-trips the public /v1/receipt/verify. The demo-matrix and SmartMorph routes are additive — if the backend has not deployed them yet, the page falls back to /adapters + two live /run calls, so these still work.

Live demo — receipt a Leanstral call curl https://hivemorph.onrender.com/v1/model-receipts/leanstral-demo
List registered adapters (env var names only — no secrets) curl https://hivemorph.onrender.com/v1/model-receipts/adapters
Universal run — receipt a Mistral Leanstral call curl -X POST https://hivemorph.onrender.com/v1/model-receipts/run \ -H 'Content-Type: application/json' \ -d '{"provider":"mistral","model":"leanstral-1-5","prompt":"State the theorem add_comm for Nat."}'
Universal run — receipt a DeepInfra model call curl -X POST https://hivemorph.onrender.com/v1/model-receipts/run \ -H 'Content-Type: application/json' \ -d '{"provider":"deepinfra","model":"deepseek-ai/DeepSeek-V3.1-Terminus","prompt":"Reply with one short line: pick a route label for a low-latency code task."}'
SmartMorph route demo (additive — falls back to two /run calls if not yet deployed) curl https://hivemorph.onrender.com/v1/model-receipts/smartmorph-route-demo

Model facts: Mistral Leanstral 1.5 — mistral.ai announcement and the model card on Hugging Face.