# Improving token efficiency for GitHub Copilot in VS Code

DevFeed: [Improving token efficiency for GitHub Copilot in VS Code](<https://devfeed.tech/articles/improving-token-efficiency-for-github-copilot-in-vs-code-4054.md>)

Original publisher: [Read original article](<https://code.visualstudio.com/blogs/2026/06/17/improving-token-efficiency-in-github-copilot>)

Author: Ryan Caldwell, Bhavya U

Published: 2026-06-17T00:00:00Z

Content type: article

Language: en

Sources: [Visual Studio Code - Code Editing. Redefined.](<https://devfeed.tech/sources/visual-studio-code-code-editing-redefined.md>)

Topics: [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [vs-code](<https://devfeed.tech/topics/vs-code.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Caching](<https://devfeed.tech/topics/caching.md>), [context window](<https://devfeed.tech/topics/context-window.md>), [Latency](<https://devfeed.tech/topics/latency.md>), [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [anthropic](<https://devfeed.tech/topics/anthropic.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>), [JSON](<https://devfeed.tech/topics/json.md>)

Tags: [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [blog](<https://devfeed.tech/tags/blog.md>), [caching](<https://devfeed.tech/tags/caching.md>), [coding](<https://devfeed.tech/tags/coding.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [cost](<https://devfeed.tech/tags/cost.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [json](<https://devfeed.tech/tags/json.md>), [latency](<https://devfeed.tech/tags/latency.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [openai](<https://devfeed.tech/tags/openai.md>), [vs-code](<https://devfeed.tech/tags/vs-code.md>)

## AI overview

This article explains how VS Code improves token efficiency in GitHub Copilot's agentic coding harness. It focuses on prompt-prefix caching and reducing tool-definition overhead to lower token usage, cost, and latency while preserving task success rates across OpenAI and Anthropic models.

## Source excerpt

Learn how we're improving token efficiency for GitHub Copilot to reduce costs and latency for VS Code users. Read the full article