Anthropic spent May 13–14 rewriting the deal for every developer running agents on a Claude subscription. Starting June 15, anything programmatic — Agent SDK, claude -p, Claude Code GitHub Actions, and third-party agents like OpenClaw — leaves your usage pool for a separate monthly credit.
What the credit pool does
Pro gets $20/month. Max 5x $100. Max 20x $200 — each tier mirrors its own price. Credits are per-user, don’t pool across teams, don’t roll over, and drain before anything else. Run out and your agent falls through to API rates or just stops. Interactive Claude Code in terminal and IDE is untouched, and weekly limits there got a 50% bump for Pro/Max/Team/Enterprise through July 13.
Why this is really about Codex
OpenAI shipped Codex Mobile the same week. Anthropic is doing two things at once: kicking SDK-heavy users — the ones running hundreds of dollars of compute on a $20 plan via OpenClaw — onto real metering, while sweetening the deal for developers who live inside Claude Code. Theo Browne pegged the squeeze at roughly 40x less headroom for heavy third-party users.
Using it via the SDK
Nothing in your code changes. Same OAuth, same API key fallback — only the billing source shifts. Long-running coding agents, CI PR triage, headless claude -p jobs, anything OpenClaw routes to Claude all eat the new pool. Want overflow? Keep an API key on standby.
You Might Also Like
- Anthropics Claude Code Openclaw Restriction Policy 200 Month Users Push Back Openai Opens its Doors
- Oh my Claudecode Turns Claude Code Into a 32 Agent dev Team and 11 8k Stars Agree
- Openai Codex Claude md Auto Import Makes Switching From Claude Code a two Click Move
- Anthropic Just Launched Code Review in Claude Code and 54 of prs now get Real Feedback
- Claude Replay Turns Your Anthropic Claude Code Sessions Into Shareable Video Like Replays
Top AI Product 
Leave a comment