AI Tool Profile
GitHub Copilot AI Credit Session Limits
GitHub added public-preview AI credit session limits to Copilot CLI and the GitHub Copilot SDK on July 1, 2026.

Verification & Sources
- Status
- Verified
- Source links
- 3
- Freshness
- Verified July 9, 2026
- Last verified
- July 9, 2026
- Last updated
- July 9, 2026
Key source checks
Suggest a correction
What It Does
GitHub added public-preview AI credit session limits to Copilot CLI and the GitHub Copilot SDK on July 1, 2026.
Full Guide
GitHub Copilot AI Credit Session Limits is a product or capability from GitHub documented by first-party sources. GitHub added public-preview AI credit session limits to Copilot CLI and the GitHub Copilot SDK on July 1, 2026.
What it does
Interactive CLI users can inspect or change a session limit with the limits command, while noninteractive runs can use the max-ai-credits option. GitHub counts model calls, subagents, and background work across a session, then asks the agent to wrap up when the configured cap is reached.
Availability and pricing
GitHub says session limits require Copilot CLI 1.0.66 or later or Copilot SDK 1.0.5 or later and are available in public preview for Individual, Business, and Enterprise plans. The limit is a soft cap because a response already in progress can finish after the threshold is crossed; current plan pricing and AI credit terms remain authoritative.
Who it is for
Developers, automation teams, engineering leaders, and enterprise platform teams that need per-session controls for unattended or long-running Copilot agent work.
What teams should review
The feature is in public preview, the cap can be exceeded by a response already in flight, and organizations must still combine it with broader budgets, policy, monitoring, and workload-specific tests.
Official sources
Tool Links
Launch History
GitHub Copilot AI Agent Session Limits
GitHub added public-preview AI credit session limits to Copilot CLI and the GitHub Copilot SDK on July 1, 2026.
Copilot AI credit session limits are a practical governance control for unattended agent runs because they put a task-level boundary around model, subagent, and…