Claude Agent SDK Gets Separate Billing on June 15 — D-28

#claudeagentsdk #claudecode #anthropic #automation

Claude Agent SDK gets separate billing on June 15 — D-28

Bottom line first. Even with Pro $20 or Max $200, your automation jobs get billed separately. The Claude Agent SDK billing split Anthropic announced back in April is now D-28 away. If you run cron jobs with claude -p, it's time to check ahead.

Effective: 2026/06/15 (D-28)
Plans: Pro $20 / Max5x $100 / Max20x $200
Affected: claude -p · Agent SDK · GitHub Actions

One pool splits into two

Through 6/14 — single pool (UNIFIED): interactive + automation share the same pool.

Usage	Pool
claude.ai chat	same pool
Claude Code interactive	same pool
`claude -p` scripts	same pool
Agent SDK jobs	same pool

From 6/15 — two pools (SPLIT): interactive and programmatic usage are separated.

Usage	Pool
claude.ai chat	subscription pool
Claude Code interactive	subscription pool
`claude -p` scripts	separate pool
Agent SDK jobs	separate pool

Automation pool amount by plan

Pro — $20/mo extra pool (same as subscription)
Max 5× — $100/mo extra pool (same as subscription)
Max 20× — $200/mo extra pool (same as subscription)
Once depleted — no deduction from the regular pool (API-rate billing via the extra-usage toggle)

The monthly pool expires at month's end if unused, and it won't fall back to your regular subscription pool either. If you need more, you have to flip on the "extra usage" toggle to get billed automatically at standard API rates — leave it off and requests just stop. Anthropic announced this change on May 13 via its official @ClaudeDevs account on X, and the next day InfoWorld, The Register, Axios, and VentureBeat all ran explainers. It's essentially April's third-party agent block policy reopened in the form of a credit pool.

Usage deducted from the new pool

Hits the separate pool from 6/15:

Claude Agent SDK calls — agents built with the Python · TypeScript SDK
claude -p (programmatic CLI) — calls from cron / launchd / shell scripts
Claude Code GitHub Actions — auto-review · auto-PR called from CI jobs
Third-party tools built on the Agent SDK — external harnesses like OpenClaw share the same pool

Still deducted from the existing subscription pool

Interactive usage that stays the same:

claude.ai web · app chat — conversations a human types directly
Claude Code interactive sessions — sessions a human launches in the terminal
Claude Cowork — team collaboration interface usage

In other words, the pool for "what a human clicks" and "what a script clicks" gets split apart. Call the same Opus 4.7, and which pool you draw from depends on who's making the call.

What actually changes for you

The era of "one subscription runs everything, automation included" ends on June 14. That said, for everyday users almost nothing changes. It's just a good moment to check where your own usage actually falls.

Heavily affected: anyone running claude -p automation on cron, Claude Code Actions inside CI, or an Agent SDK side project.
Barely affected: if you only use claude.ai chat and Claude Code interactive in the terminal. The separate pool just expires unused.

"Even when you call the same model at the same price, we're entering an era where who makes the call decides which pool you spend."

— Eddie · noted at D-28

If you're running claude -p, GitHub Actions, or the Agent SDK, it's worth a usage check before June 14. The subscription pool and the automation pool are separate from 6/15 on.

Sources & References

Anthropic official

Primary coverage

Disclaimer: Summarized from the official announcement and primary reporting. Confirm exact policy on Anthropic's official page as of the effective date. No ads · affiliates.

Original with full infographics and visual structure: https://jessinvestment.com/claude-agent-sdk-gets-separate-billing-on-june-15-d-28/