Operational trust for AI

Every AI call
signed.
Verifiable.

One OpenAI-compatible endpoint in front of every frontier and open-weight model. Attestic policy-routes, meters real tokens, and writes a hash-chained, Ed25519-signed receipt for every call — provable offline, anytime.

attestic · provenance trace
Request
POST /v1/chat/completions
{"model":"gpt-5.5","stream":true}
Route
provider  → openai
model     → gpt-5.5
policy    → typed-config
Stream
…Hello, and welcome to…
Sign
ed25519   → a3f7c2…
entry     → sha256
chain     → +1 record
Receipt
x-attestic-receipt-id: b018e5…
x-attestic-entry-hash: 7795fe…
Hash chain
a3f7c2d1e5b8
04c9e7f2a1b3
ff12de9a0c44
0
Provider Families
0+
Open-weight Models
0%
Calls Receipted
$0
Per 1M Input Tokens

What Attestic actually does

Operational trust — provable, not claimed.

Policy routing

Send any model id, Attestic routes it to the right provider across OpenAI, Anthropic, Google, and 118+ NVIDIA open-weight models. Per-tenant overrides, rate limits, and monthly budgets enforced at the gateway.

Providers4
Open-weight118+

Ed25519 receipts

Every call is appended to a hash chain and signed with a persistent Ed25519 key. The receipt, request id, entry hash, signature, Merkle inclusion proof, is verifiable offline against the public key. No access to Attestic required.

SigningEd25519
ChainMerkle

Real metering

Token usage comes straight from each provider's stream, never estimated. Cost is computed from a web-verified price table. Unknown models meter as priced:false rather than guess. Usage, cost, and budget status available via API.

MeteringReal tokens
CostVerified

One base URL swap

If your app already uses the OpenAI SDK, you're 3 lines away.

your_app.py
from openai import OpenAI

client = OpenAI(
    base_url="https://atherion-gateway-924270273440.us-central1.run.app/v1",
    api_key="atk_your_key_here",
)

response = client.chat.completions.create(
    model="gpt-5.5",          # or claude-opus-4-8, gemini-3.1-pro-preview,
    messages=[{"role": "user", # meta/llama-3.3-70b-instruct, …
               "content": "Explain provenance in one sentence."}]
)
# Every call → signed receipt in x-attestic-receipt-id header

Prove what your AI did.

Every call audited, metered, and signed from the first request.