How to set a daily spending limit for an AI agent's API key

On Runtime, the server enforces the limit per key, over any 24 hours. So an agent that loops cannot spend past it, and no key can raise its own limit. A $25 limit buys a lot of agent time at Runtime's rates. That is 800 hours of a waiting 2 vCPU, 4 GiB sandbox at $0.03125 an hour. Or it is about 313 fully busy hours at $0.08 (rates checked 25 October 2026, pricing). There is no plan fee on top.

Set the limit

Two ways, both through a person:

• On the website. At API keys, set a limit when you create a key, or later from its row. Change or remove it there too.
• From a terminal, for a new key. runtime keys create makes it at once with the full-access key of an owner or admin saved on your machine; without one, or with --browser, a person approves it in the browser, with the limit on the approval page:

Terminalruntime keys create --name support-agent --daily-limit 25     # dollarsruntime keys create --name ci --daily-limit 10 | gh secret set RUNTIME_API_KEY

The key is printed once, alone, on standard output. So it pipes into a secret store (keys for CI). The member who made the key, or an owner or admin, can change its limit later. They can do that only on the website.

What the limit counts

What happens at the limit

A create, wake, extension or renewal that would pass the limit fails with HTTP 402 spending_limit_reached. Nothing is charged. The SDKs do not retry it.

• Running sandboxes keep the time they are already funded for. One whose next renewal would pass the limit pauses or stops at the end of that time, as its onLeaseEnd says; one that stops has the stopReason spending_limit.
• Paused sandboxes keep costing storage. If that storage cannot be paid for, you are notified, and after 30 days unpaid (seven in an account that never bought credit or saved a card) it is deleted. Set the limit above what the agent's paused sandboxes cost in a day (security).

Let the agent see what is left

Any key can read its own access and limit. No key can change them. An agent that checks before a large job can stop cleanly, instead of failing halfway.

TypeScriptimport { Runtime, RuntimeError } from "withruntime";const runtime = new Runtime();const { daily } = await runtime.limits.get();console.log(daily.limitMicros, daily.usedMicros, daily.remainingMicros);try {  await using sbx = await runtime.sandboxes.create();  await sbx.exec("python3 job.py");} catch (error) {  if (error instanceof RuntimeError && error.code === "spending_limit_reached") {    console.log("Daily limit reached; ask a person to raise it.", error.hint);  } else throw error;}

Pythonfrom withruntime import Runtime, RuntimeErrorwith Runtime() as runtime:    daily = runtime.limits.get()["daily"]    print(daily["limitMicros"], daily["usedMicros"], daily["remainingMicros"])    try:        with runtime.sandboxes.create() as sbx:            sbx.exec("python3 job.py")    except RuntimeError as error:        if error.code != "spending_limit_reached":            raise        print("Daily limit reached; ask a person to raise it.", error.hint)

Terminalruntime limits

Amounts are in microdollars, as strings. "25000000" is $25. limitMicros is null when no limit is set. runtime.limits needs withruntime 0.3.1 or later. Over HTTP, use GET /v1/limits. An agent on MCP calls runtime_account with limits.

Mistakes to avoid

• Making replacements in a loop. A refused create costs nothing, but a loop that retries it wastes the agent's turn: the limit counts the last 24 hours, so the answer stays the same until spending ages out.
• Asking the agent to lift it. No key can raise, remove or set a limit, and a key it makes never has more than it has. That is the point: tell the person the agent works for.
• One key for every agent. A limit is per key. Give each agent or application its own key, so a limit and the audit log both say which one spent.
• A limit below parked storage. An agent that keeps many paused sandboxes needs room for their storage every day, or they are deleted once the unpaid days run out.

Other controls

A daily limit bounds a key. To bound one sandbox, use maxTotalCostMicros (cap a sandbox's cost). To give a dashboard a key that cannot spend at all, use a read-only key. For an agent's full setup, see Claude Code in a sandbox.

Facts on this page were checked on 26 October 2026.