ORVEX · runtime v1.0 · live

The runtime for AI,
distributed by design.

ORVEX routes every request through a global mesh of workers. Inference happens where it is cheapest, fastest and closest settled invisibly on-chain, delivered like software.

4 workers onlinep50 · 41ms1.2b tokens / day
/ runtime flow
streaming
REQUESTAPIROUTERWORKER · AWORKER · BBUSYWORKER · CSTREAMRESPONSE
/ 01 · thesis

Not a model. Not a chain. A runtime.

Models come and go. Chains settle value. In between lives the layer that actually runs the request: routes it, streams it, bills it, retries it. That layer has always belonged to one provider at a time. ORVEX rebuilds it as an open network.

Route

Every request, best path

Latency, price, availability and locality are evaluated on every call. The router picks the worker most likely to answer well, right now.

p50 latency41ms
p99 latency210ms
routing decisions / s4800
Execute

Workers you don't manage

Independent operators run inference on hardware they own. You get a single endpoint. They get paid per token served.

tokens/sec · last 24h
Settle

Blockchain, invisible

Solana handles settlement, quotas and receipts. You never see a wallet. Payment is in credits. On-chain is an implementation detail.

settlement380ms
finality2s
fees0-
/ 02 · developer surface

Ships like software. Runs like infrastructure.

One SDK. One key. Streaming from the first token. The network beneath it is elastic, distributed and priced per unit of work not per seat, not per model, not per month.

orvex · runtime · boot
booting
Install

One line, any language

$ npm i @orvex/sdk
$ orvex login
Call

Familiar shape, better runtime

// stream tokens from anywhere
const res = await orvex.chat({
  model: "orvex-1",
  stream: true,
  messages,
});
/ 03 · product

Experience ORVEX Runtime.

A real chat streaming against the same architecture you see above routed, executed and settled on the mesh in real time. This is what your users will feel.

orvex · runtime
user
runtime
worker
user
Ask the runtime…
workers
214
online
latency
41ms
p50
stream
idle
socket
api
200 · ok
gateway
credits
1,284
used · 24h
model
ORVEX Fast
route
/ compat
OpenAI compatible

Same client, same schema. Point your SDK at orbit nothing else changes.

/ stream
Streaming responses

Tokens flow from the first millisecond. No polling, no wait for the full body.

/ vision
Vision ready

Multimodal on the same endpoint. Send images alongside text with one call.

/ mesh
Global worker network

214 workers across 12 regions. Requests land on the closest healthy node.

/ privacy
Privacy first

Prompts and completions are never persisted. Zero retention by default.

/ routing
Low-latency routing

The router scores every path per call. You always get the fastest live worker.

/ 04 · observability

The infrastructure is the artwork.

No stock diagrams. No brains, no hexagons, no globes. Just the actual shape of the system nodes, edges, queues, streams. Alive on every page.

workers online
214
12 regions · 4 continents
p50 latency
41ms
rolling 5m
requests / sec
38
↑ 18% wow
credits processed
+17
last minute
uptime
99.994%
rolling 30d
ttft · warm
38ms
median
cost / 1m tokens
$0.42
orvex-1 · avg
tokens / day
1.20b
24h rolling
/ 05 · ship
ready when you are

Move your first request in an afternoon.

A drop-in SDK, an OpenAI-compatible endpoint, and a network that scales the moment you send traffic. No infra to provision. No chain to touch. Just a runtime.