Run your workload where
your users already are
Deploy any workload to the edge in one command. No clusters, no warm pools, no capacity planning — you pay for what you serve.
Serving 2.41B requests a month for engineering teams at
Latency is a distance problem before it is a compute problem
A workload answers in about 30 ms when it runs next to the user. Send that same request to a datacentre on another continent and back, and the round trip alone costs three times that. So we put the work next to the user instead.
Workloads stream, not deploy
Workloads are content-addressed and pulled on first request. A region that has never served yours is warm in under 400 ms and cached thereafter.
Route by residency, not by round-robin
Pin a workload to the EU, to a single country, or to hardware you own. The router honours it before it honours latency.
Scale to zero, honestly
No idle compute-hour billing and no warm-pool minimum. If nobody called your workload last month, the invoice says nothing.
iad1Ashburn, US11mssfo1San Francisco, US9mspdx1Portland, US12msord1Chicago, US13msdfw1Dallas, US12msatl1Atlanta, US14msewr1Newark, US10msyyz1Toronto, CA14ms One endpoint. The SDK you already import.
Argosy speaks the OpenAI wire format, so migration is a base URL and a key. Streaming, tool calls, structured output and vision all behave the way your client library expects.
import OpenAI from "openai"; const argosy = new OpenAI({ baseURL: "https://edge.argosy.dev/v1", apiKey: process.env.ARGOSY_KEY, }); // routed to the nearest warm region const stream = await argosy.chat.completions.create({ model: "llama-3.3-8b-instruct", stream: true, messages: [{ role: "user", content: "Summarise this ticket in one line." }], });
from openai import OpenAI import os argosy = OpenAI( base_url="https://edge.argosy.dev/v1", api_key=os.environ["ARGOSY_KEY"], ) # routed to the nearest warm region stream = argosy.chat.completions.create( model="llama-3.3-8b-instruct", stream=True, messages=[{"role": "user", "content": "Summarise this ticket in one line."}], )
curl https://edge.argosy.dev/v1/chat/completions \ -H "authorization: Bearer $ARGOSY_KEY" \ -H "content-type: application/json" \ -d '{ "model": "llama-3.3-8b-instruct", "stream": true, "messages": [ {"role":"user","content":"Summarise this ticket in one line."} ] }' # x-argosy-region: iad1 # x-argosy-cache: hit
data: [DONE]
Every request is a trace, not a line in a log file
You cannot tune what you cannot see. Argosy emits a span for each stage of the request — including the ones most platforms hide, like queue time and cache behaviour.
Queue time is reported separately
If your p99 is bad because you are rate-limited rather than because the workload itself is slow, the trace says so. No inferring it from wall clock.
Traces are OTLP
Ship them to whatever you already run. There is no proprietary agent and no second dashboard you are obliged to look at.
Three commands, then it is somebody else’s problem
Point it at a model
Any open-weights checkpoint from the registry, or your own from S3.
Choose where it may run
Regions, residency rules and spend ceilings live in one file.
residency: "eu-only"
max_spend: 2000
scale_to_zero: true
Send it traffic
Swap the base URL. Nothing else in your application changes.
-H "authorization: Bearer …"
p50, region with nothing cached yet
6 with dedicated, reservable capacity
Measured at the edge, not the origin
Than always-on reserved capacity at our median load
What moved recently
You pay for tokens. That is the whole model.
No per-seat fee, no reserved instances you forget to turn off, and no charge for a region simply existing.
Hobby
1M tokens a month, then usage rates. For side projects and evaluation.
✓All 31 regions✓Every open-weights model✓Community support✓Scale to zero
Team
Metered per token served, billed to the second. Most teams land here.
✓Residency & routing rules✓OTLP trace export✓Spend ceilings and alerts✓99.9% SLA
Dedicated
Reserved GPUs in named regions, or your own hardware under our control plane.
✓Reserved capacity✓Private networking✓99.99% SLA✓Named support engineer