Anthropic's Agent SDK Credits: The June 2026 Rules, Explained

Anthropic now includes metered Agent SDK credits with Claude plans: $20 on Pro, $100 on Max 5x, $200 on Max 20x. What they permit, what stays prohibited, and the math.

In June 2026, Anthropic added metered Agent SDK credits to its consumer Claude plans: $20 of monthly credit on Pro, $100 on Max 5x, $200 on Max 20x. The credits cover personal programmatic use, meaning your own claude -p runs, the Agent SDK in your own projects, and Claude Code GitHub Actions, metered at Anthropic’s published API rates. They do not change Anthropic’s prohibition on third-party services offering Claude login or routing requests through plan credentials on behalf of users. This page lays out the rules, the numbers, and the arithmetic of a metered allowance.

The credit, by plan

PlanMonthly priceAgent SDK creditInteractive Claude Code
Claude Pro$20$20/modraws on plan usage windows
Claude Max 5x$100$100/modraws on plan usage windows
Claude Max 20x$200$200/modraws on plan usage windows

The credit equals the plan price at each tier and resets with the monthly cycle. Programmatic usage meters against it at Anthropic’s published API rates (anthropic.com/pricing), token by token, like an API budget that comes bundled with the plan. Interactive Claude Code sessions are a separate system: they keep drawing on the plan’s normal usage windows, not on the credit.

What the credits permit

Three uses, all personal:

  • claude -p from your own scripts, cron jobs, and pipelines.
  • The Agent SDK in projects you build and run for yourself.
  • Claude Code GitHub Actions in your own repositories.

The common thread is you, on your own account, for your own use. Before June 2026, Anthropic’s position was that subscription OAuth tokens could not be used in any product or service outside Anthropic’s own applications, which made even personal claude -p automation a violation of the consumer terms. The credits carve that personal shape back in, with a meter attached.

What stays prohibited

Anthropic’s Claude Code documentation states it “does not permit third-party developers to offer Claude.ai login or to route requests through Free, Pro, or Max plan credentials on behalf of their users” (code.claude.com/docs/en/legal-and-compliance). The credits sit inside that boundary, not across it.

Concretely: a hosted service signed in with your Claude subscription, a gateway exposing your Max plan as an API endpoint for an app someone else operates on your behalf, or any tool offering “log in with Claude” to its own customers remains out, regardless of who holds the credit. The credits restore personal programmatic Claude; they do not reopen the door for hosted services on subscription credentials.

How the rules got here

DateWhat changed
January 2026Server-side checks cut third-party tools (OpenCode, Cline, RooCode, Goose) off from subscription OAuth, without advance notice
February 2026Anthropic clarified that subscription OAuth tokens in any other product, tool, or service violate the Consumer Terms
June 2026Agent SDK credits added to Pro and Max plans, restoring metered personal programmatic use

The fuller history, including what the January enforcement looked like for the tools it hit, is in why we don’t support Claude Code.

The arithmetic of a metered allowance

A credit is a budget, not a window: it meters automation at API rates until it runs out, so cost tracks volume up to the cap and then bills per token. Take a nightly claude -p job that meters $4 per run, 30 runs a month, $120 of metered usage:

PlanCreditNights coveredOverflow at API rates
Claude Pro$205$100
Claude Max 5x$10025$20
Claude Max 20x$200all 30, $80 to spare$0

The planning consequence: the same plan covers a light job thirty times or a heavy one five times, and anything above the credit is ordinary API spend that belongs in the same budget line.

Two habits follow. Measure the per-run meter on a handful of real runs before scheduling anything, because token counts from a test prompt rarely match production documents. And watch the boundary as a project grows: automation that starts as your own tool stays inside the credit’s terms only while it serves you. The moment other people’s requests flow through your plan credentials, it has become the third-party shape Anthropic prohibits, whatever the credit balance says.

Where this sits next to the OpenAI side

The two vendors answered the same question differently, and both answers are deliberate. Anthropic meters programmatic subscription use through these credits and keeps third-party plan routing prohibited. OpenAI includes programmatic Codex inside ChatGPT plan windows, documents codex exec for scripts and CI, and documents device-code sign-in for headless machines; third-party use there runs under OpenAI’s normal account rules, intended functionality with OpenAI holding the final call. The full structural comparison, windows against credits against meters, is in Codex vs Claude Code: the cost structure comparison.

Our own position follows the policies as written: we do not offer Claude subscription routing, and Claude models pass through ProxyLLM only with your own API-side key. The OpenAI-side automation is what we run on flat plan windows; if that is the bigger line in your budget, the calculator shows what the flat structure does to it.

Frequently asked questions

What are Anthropic's Agent SDK credits?

A metered monthly allowance Anthropic added to consumer Claude plans in June 2026: $20 of credit on Pro, $100 on Max 5x, and $200 on Max 20x. The credits cover personal programmatic use of Claude, such as claude -p, the Agent SDK in your own projects, and Claude Code GitHub Actions, metered at Anthropic's published API rates.

What can I run against the Agent SDK credit?

Your own automation on your own account: claude -p in scripts and cron jobs, applications you build with the Agent SDK and run for yourself, and Claude Code GitHub Actions in your own repositories. The common thread is personal use under your own credentials.

Can third-party services use my Claude subscription now?

No. Anthropic's policy still states it does not permit third-party developers to offer Claude.ai login or to route requests through Free, Pro, or Max plan credentials on behalf of their users. The June 2026 credits restored personal programmatic use; the hosted-service shape remains prohibited.

What happens when the Agent SDK credit runs out?

Programmatic usage beyond the monthly credit meters at Anthropic's standard API rates, published at anthropic.com/pricing, and the credit resets with the monthly plan cycle. Interactive Claude Code sessions continue to draw on the plan's normal usage windows, which are separate from the credit.

Do the credits change ProxyLLM's position on Claude Code?

No. We do not run Claude Code against consumer Claude subscriptions, because Anthropic prohibits third-party services from doing so, and the credits do not alter that rule. Claude models remain available through ProxyLLM as a passthrough with your own API-side key, billed at provider rates.

More on Policies & limits
Codex Hosted · the main feature

Run your AI workloads on your ChatGPT subscription.

ProxyLLM runs OpenAI's Codex for you, signed in with your own ChatGPT account. Your apps call one OpenAI-compatible endpoint and the work bills to your flat plan instead of per-token API pricing.