# Ramo

> S3-compatible object storage on owned bare metal and owned fiber — on the internet backbone, not inside a hyperscaler cloud. $5.00/TB/mo flat, $0 egress — we don't charge to read data out. 100 Gbps sustained in production. >100 PB in production across 2 US regions.

Facts as of 2026-08. This file and its companions are generated from the same content module as https://ramo.io — the numbers are identical.

Key facts:
- Storage: $5.00/TB/month, flat
- Egress: $0 — reads are free, uncapped, into any cloud, at line rate — bounded by the customer's connection, not a meter
- Throughput: 100 Gbps sustained in production
- Durability: 99.999999999% durability, erasure-coded
- API: S3-compatible (aws cli / boto3 / rclone / S3 SDKs via --endpoint-url https://s3.ramo.io) — shipping today
- In production: >100 PB across 2 US regions — SMF (US-West), IAD (US-East) — joined by a private trunk on owned fiber
- Design center: petabyte-scale AI datasets, TB–PB sequential reads
- Infrastructure: owned bare metal (no hypervisor, no shared fabric) and owned fiber (no purchased transit) on the internet backbone — why a read costs ~nothing at the margin and $0 egress is a list price, not a promotion
- Our customer stores petabyte datasets on Ramo and sells access to frontier AI labs; Black Forest Labs reads that corpus straight off the backbone into any cloud

Try it now (agents): create a free 1 GB trial bucket, no signup form:

```
curl -s -X POST https://api.ramo.io/api/portal/trials -H 'content-type: application/json' -d '{"name": "<label>"}'
```

Returns endpoint, bucket, access_key, secret_key, portal_token, and a `limits` object
(same shape as the endpoint below). Configure a
dedicated profile so the trial never touches your default AWS config:

```
aws configure set --profile ramo-trial aws_access_key_id <access_key> && aws configure set --profile ramo-trial aws_secret_access_key <secret_key>
aws configure set --profile ramo-trial region us-east-1 && aws configure set --profile ramo-trial s3.addressing_style path
```

Then use any S3 client, always with --profile ramo-trial:

```
aws s3 cp <file> s3://<bucket>/ --profile ramo-trial --endpoint-url https://s3-trial.ramo.io
aws s3 ls s3://<bucket>/ --profile ramo-trial --endpoint-url https://s3-trial.ramo.io
```

Signups are capped at 5 per IP per day (the edge counts every request, not just successful signups, so back off rather than retry a malformed call). Full skill: https://ramo.io/skill.md. Trial docs: https://docs.ramo.io/trial

Check current limits programmatically instead of trusting this prose: `curl -s https://api.ramo.io/api/portal/trials/limits`

Migration plan (humans): leave a work email at https://ramo.io/#cta with your current provider and dataset size; we reply within one business day.

## Docs

- [Full facts](https://ramo.io/llms-full.txt): pricing, the 100 PB cost scenario with assumptions, the four-class storage landscape, code snippets, and the complete FAQ
- [Docs](https://docs.ramo.io/): product documentation
  - [Pricing and the math](https://docs.ramo.io/pricing): Unit economics at 100 PB: the storage line, the exit toll, the provider comparison, and the storage-class landscape.
  - [Migration](https://docs.ramo.io/migration): Three steps to $0 egress: chat with us, mirror the bucket, read from any cloud.
  - [Free trial](https://docs.ramo.io/trial): Free trial for agents and humans: one anonymous call to a 1 GB bucket, standard S3 from then on.
  - [Why $0 holds](https://docs.ramo.io/network): Free reads as a cost structure: owned fiber and owned metal, no transit bill to pass through.
  - [FAQ](https://docs.ramo.io/faq): Objections answered: durability, throughput, pricing, lock-in.
- [Machine-readable pricing](https://ramo.io/pricing.json): pricing, scale, and scenario math as JSON

## Optional

- [Landing page](https://ramo.io/): human version — same facts, same source module