Ryvion V8 · live network
The verification layer for distributed AI compute.
Ryvion routes inference across named hardware and returns a signed, browser-verifiable receipt for every output. Ghost streaming and speculative decoding make the path faster without hiding uncertainty.
- Avg speedup
- 2.82×
- reference bench
- Receipt CID
- 100%
- gateway target
- Hardware
- 3
- vendors verified
▪ claims stay tied to receipts and live network metrics below
Live demo
▪ animation runs client-side · same protocol as production stream
Live network
Network telemetry
Real numbers from the production network
○ connecting
▪ The four moats
Properties most inference networks do not expose.
Most networks sell access to GPUs or model APIs. Ryvion sells proof. Each moat is a measurable, reproducible property of every request you send through the gateway.
Provisional → commit → rollback streaming
Tokens can appear before they are final. Speculative drafts ghost in, verified tokens commit, and rejected paths roll back instead of pretending uncertainty never happened.
RCOG receipts on every output
Each completion ships with a content-addressed TranscriptDigest CID. Ed25519-signed by the executing node, deterministic, replayable, and verifiable from any browser without auth.
Cross-node FuzzyTrace verification
Opt-in dual execution on Mac arm64 + Windows amd64 with calibrated numerical comparison. Audit classifier returns PASS · AMBIGUOUS · FAIL, with the tolerance disclosed.
Measured speculative speedup
Auto-paired drafter + target on nodes that have both models present. The receipt records acceptance, timing, and fallback state so speed claims stay inspectable.
Trust layer
The receipt is the product.
Every output emits a content-addressed dependency tree. Six receipts, one chain: prompt → policy → plan → assignment → transcript → signed result. Each node is an Ed25519-signed CID anyone can verify.
- Deterministic CIDs — same inputs, same hash, every time
- Ed25519 signatures by the executing node
- Verifiable from any browser — no API key, no auth
- EU AI Act Article 14 evidence-ready
hash binding · gemma-4-26b-a4b-it
parent of all receipts in this trace
max_tokens, temperature, sla · backend=llama-server
role=target_verifier_consumer · capability-typed
node 0e5125f14e7e…a71bc7 · RTX 4070 Ti Super
739 tokens · finish=stop
signed by 0e5125f14e…a71bc7 · Ed25519
not sampled · stochastic audit (p≈0.05)
▪ Heterogeneous fleet
Real hardware. Named.
Inference fleets are usually a black box of “GPU instances”. Ryvion shows the SKU, jurisdiction, vendor, and reputation tier of every node. Mac arm64, NVIDIA RTX, AMD RDNA — we verify across architectures so the answer doesn't depend on whose hardware happened to win the bid.
▪ Fleet snapshot
4 of 5 nodes online · 3 jurisdictions · Mac arm64 + NVIDIA + AMD
- DE
ryv-de-pri-01
RX 7900 XTX · 24GB
trusted● online - CA
ryv-ca-north-04
RTX 4070 Ti Super · 16GB
elite● online - FR
ryv-fr-lyon-02
RTX 4060 · 8GB
trusted● online - CA
ryv-ca-cpu-07
CPU node · 16GB
trusted● online - DE
ryv-de-prv-09
RTX 3090 · 24GB
watch○ offline
▪ Developer path
Switch the base URL. Keep the receipt.
The OpenAI SDK works untouched. You get streaming, tool-use, jurisdiction routing, and a signed receipt header — all without learning a new client.
from openai import OpenAI
client = OpenAI(
base_url="https://api.ryvion.ai/v1",
api_key="ryv_live_...",
)
stream = client.chat.completions.create(
model="phi-4",
stream=True,
messages=[
{"role": "user",
"content": "Why distributed inference?"},
],
extra_body={"jurisdiction": "CA"},
)
for chunk in stream:
print(chunk.choices[0].delta.content or "", end="")
# Receipt CID is on every response:
# X-Ryvion-Receipt-CID: ryv1:sha256:9c1e4d7f...
# Verify any CID at https://ryvion.ai/v8 — no auth required.▪ Versus the network
Same API. Different premise.
Most networks ask: how cheap can we rent the GPU? Ryvion asks: can you prove the answer? The OpenAI-compatible surface is the same. The artifacts you take home are different.
Ship today
Send the first request. Verify the receipt.
Create a workspace, point your SDK at api.ryvion.ai/v1, and inspect the lineage of every output. The free tier ships with speculative acceleration and signed receipts on day one.