Coding Tools
GitHub Adds Token Breakdown to AI Usage Reports
GitHub Changeloghigh confidence
Why it matters
- →Provides transparency in AI usage and costs for users.
- →Helps users manage and potentially reduce AI-related expenses.
- →Facilitates better communication with stakeholders about AI costs.
GitHub has introduced a new feature in its AI usage reports that provides a per-model token breakdown. This allows users to see the specific input, output, cache read, and cache write tokens contributing to their AI credits. Previously, the reports only showed total AI credits, making cost management challenging. This update is available to admins on Copilot Business and Enterprise, and to individual Copilot users, offering greater transparency and control over AI expenses.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1GitHub Copilot to Implement Per-Token Pricing
AI News · May 1, 2026 · Related
- 2GitHub Copilot shifts to token-based billing
AI News · June 2, 2026 · Same story
- 3Microsoft's GitHub Copilot Pricing Sparks 'Tokenpocalypse' Concerns
TechCrunch AI · June 7, 2026 · Related
- 4GitHub Copilot App Now Supports Any Model Provider
Matt Wolfe · June 10, 2026 · Related
- 5GitHub Copilot API Adds AI Credit Tracking
GitHub Changelog · June 19, 2026 · Same story
- 6GitHub Copilot Enhances Usage Metrics Accuracy
GitHub Changelog · July 2, 2026 · Same story
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.316: Subagents and Gateway Budgets
Anthropic is tightening control over Claude Code's autonomous behavior with new environment variables that let you disable 'ultrathink' or cap subagent effort levels. For teams, the introduction of pooled group budgets on the gateway allows shared monthly spending limits across members, a practical fix for enterprise cost management. The release also patches critical bugs where shell commands would hang or crash on exit, stabilizing the developer experience significantly.
Claude Code Releases
Coding Toolscoding
llama.cpp b12022 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing ROCm 10.0 to Linux and Windows alongside CUDA 13.4, effectively closing the hardware gap for AMD users who were previously left behind. The inclusion of native Snapdragon support on Linux marks a significant step toward running local LLMs on ARM-based mobile chips without emulation overhead. While KleidiAI on Apple Silicon is disabled in this build, the broader expansion to diverse accelerators ensures that developers aren't locked into NVIDIA ecosystems anymore.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12023 fixes shared prefix bug
This release addresses a specific inference artifact where decision prefixes were incorrectly bleeding into output embeddings. By capping shared prefixes at the first output position, llama.cpp ensures that option tokens remain distinct for parent and child tasks. This is a targeted fix for multi-step reasoning or voting workflows rather than a performance boost. It stabilizes complex generation patterns without changing the underlying model architecture.
llama.cpp Releases