Question 1

What is T0?

Accepted Answer

T0 sells hosted, sandboxed AI coding-agent sessions over a REST API. You create a session, push files into it, send it messages, and stream the agent working in real time. Each session is an isolated Linux workspace that persists between messages, so files the agent wrote, packages it installed and git state are all still there on the next message. T0 sells the runtime, not the model: isolation, persistence, orchestration and latency are the product. Base URL: http://localhost:18080/v1.

Question 2

How do I get an API key?

Accepted Answer

Create an account at http://localhost:13000/signup with an email and a password, verify the code we email you, and your key is shown once — copy it straight away. Send it as an Authorization: Bearer header on every /v1 request. Keys are the tenant boundary: they identify the account, authorize the request, and are what usage is metered against. Revoke one from the dashboard and it stops working within seconds.

Question 3

Do I need my own coding-agent subscription?

Accepted Answer

Yes. Sessions run on your own account with the maker of your coding agent, not on a key T0 holds. Add your coding agent token once in the dashboard — the long-lived headless token your coding agent's own CLI issues for exactly this — and T0 runs the agent inside your sandbox as you. It must be your own account, not a shared one, and your plan's own usage limits apply inside sessions. T0 does not resell model access, so nothing on your bill is a marked-up token — you pay us for compute time and storage only.

The token is encrypted at rest with AES-256-GCM, decrypted only at the moment a container is claimed, injected only into that sandbox, and never logged, never written to disk and never shown back by any endpoint.

Question 4

Which models can I use?

Accepted Answer

Two tiers, named by T0: core for everyday work and max for the hardest tasks. Set the tier when you create a session; core is the default. Because sessions run on your own subscription, the tier selects the class of model your account is used against, within its own limits.

Question 5

What persists between messages?

Accepted Answer

Everything inside /workspace, plus the agent process itself. The process stays alive for the life of the session, so conversation context stays resident and follow-up turns do not re-read everything from scratch. That is the single largest latency win in the system. When a session goes idle the container stops but its volume survives, so resuming is a start rather than a rebuild. Workspaces are also snapshotted to object storage, which is what makes a resume possible days later.

Question 6

What happens when a session goes idle?

Accepted Answer

After idle_timeout (10 minutes by default) the session moves to sleeping: the container stops, the workspace is kept, and a session.idle event is emitted. Sleeping costs nothing — metering counts awake seconds only. The next message wakes it. A resume inside the warm window is a container start; a colder resume restores the workspace from object storage first. Files can be downloaded from a sleeping session without waking it.

Question 7

How is usage metered?

Accepted Answer

A credit is one minute of awake session time. Sleeping sessions cost nothing. T0 meters awake session-seconds, peak workspace bytes and turns; token counts are recorded and shown to you for your own visibility but are not billed by T0 — model usage is between you and your own subscription.

Check live usage any time with GET http://localhost:18080/v1/usage.

Question 8

Is there a free plan?

Accepted Answer

Yes, permanently. Free is $0 for 300 credits a month (5 h of awake session time), 60 a day, 1 concurrent session, 2 GB of workspace storage and a 7-day retention window. No card required.

Question 9

What are the plans and quotas?

Accepted Answer

Free — $0: 300 credits/month (5 h), 60/day, 1 concurrent session, 2 GB storage, 7-day retention, 1 GB / 1 CPU sandbox.

Starter — $19/month: 3,600 credits/month (60 h), 600/day, 3 concurrent sessions, 25 GB storage, 30-day retention, 2 GB / 1.5 CPU sandbox.

Pro — $59/month: 18,000 credits/month (300 h), 2,400/day, 10 concurrent sessions, 100 GB storage, 90-day retention, 4 GB / 2 CPU sandbox.

Question 10

What happens when I hit a quota?

Accepted Answer

A hard stop with an upgrade prompt, never a surprise bill. Requests past a quota return 429 quota_exceeded naming the limit you hit and the next plan up; requests past the per-key rate limit return 429 rate_limited with a Retry-After header. Sessions already awake are not killed mid-turn.

Question 11

How do I stream a response?

Accepted Answer

POST a message to http://localhost:18080/v1/sessions/:id/messages — it returns 202 with a turn_id immediately — and read events from GET http://localhost:18080/v1/sessions/:id/events, which is Server-Sent Events. Events are ordered and sequence-numbered per session, so if the connection drops you reconnect with a Last-Event-ID header carrying the last sequence you saw and the stream resumes from there with nothing lost or repeated. If you would rather push and pull over one connection, http://localhost:18080/v1/sessions/:id/socket is a WebSocket that carries the same events and accepts messages and interrupts.

Question 12

How do I get files in and out?

Accepted Answer

Small files go straight to the API: PUT the raw body to /v1/sessions/:id/files/<path> and it is streamed into the live workspace. Bulk uploads go as a tar.gz to POST /v1/sessions/:id/files. Large transfers are handed a presigned object-storage URL so the bytes never pass through our servers. Every path is resolved and confined to /workspace before it reaches the container; traversal is rejected with 400 invalid_path.

Question 13

How isolated is a session?

Accepted Answer

Each session is its own container: read-only root filesystem, all Linux capabilities dropped, no-new-privileges, a seccomp profile, a pids limit, and hard memory and CPU ceilings set by your plan. It runs as a non-root user and never sees a Docker socket, a host mount or host networking. Egress is default-deny through an allowlist proxy that refuses every private network range, so a session can reach the model provider and — depending on plan — package registries, and nothing else. The proxy fails closed: if it is down, the sandbox has no network at all.

Question 14

Where do I see whether T0 is up?

Accepted Answer

The status page at http://localhost:13000 shows live component health — gateway, runner, warm-pool depth, queue depth and recent error rate — plus incident notes. It is served from its own host so it stays up when the stack it reports on does not.

Question 15

What does a first request look like?

Accepted Answer

curl -X POST http://localhost:18080/v1/sessions -H "Authorization: Bearer t0k_live_YOUR_KEY" -H "Content-Type: application/json" -d '{"name":"my-first-session"}' — that returns a session id and a stream URL, and the session is ready in under a second because it comes from a pool of pre-booted containers.

Pricing

Every limit, side by side

What a credit is

Metered, enforced, and not billed

Metered

Enforced

Not billed by T0

Shown to you anyway

Billing

Questions about plans

	Free	Starter	Pro
Price	$0	$19/mo	$59/mo
Credits / monthone credit = one minute awake	300 (5 h)	3,600 (60 h)	18,000 (300 h)
Daily capcredits per UTC day	60	600	2,400
Concurrent sessions	1	3	10
Workspace storagedurable, per account	2 GB	25 GB	100 GB
Live disk per sessiontechnical ceiling	5 GB	10 GB	20 GB
Retentionafter a session ends	7 days	30 days	90 days
Sandboxmemory / CPU	1 GB / 1 CPU	2 GB / 1.5 CPU	4 GB / 2 CPU