# Getting more from each token: How Copilot improves context handling and model routing

DevFeed: [Getting more from each token: How Copilot improves context handling and model routing](<https://devfeed.tech/articles/getting-more-from-each-token-how-copilot-improves-context-handling-and-model-routing-67268.md>)

Original publisher: [Read original article](<https://github.blog/ai-and-ml/github-copilot/getting-more-from-each-token-how-copilot-improves-context-handling-and-model-routing/>)

Author: Joe Binder

Published: 2026-06-17T19:41:46Z

Content type: article

Language: en

Sources: [GitHub Blog](<https://devfeed.tech/sources/github-engineering.md>)

Topics: [Model Routing](<https://devfeed.tech/topics/model-routing.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-ml](<https://devfeed.tech/tags/ai-ml.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [developers](<https://devfeed.tech/tags/developers.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [routing](<https://devfeed.tech/tags/routing.md>), [token](<https://devfeed.tech/tags/token.md>)

## AI overview

GitHub describes improvements to Copilot's context handling and automatic model selection. Prompt caching and on-demand tool loading reduce repeated context, while Auto routes tasks using model availability and task requirements. The article also offers practices for keeping sessions efficient and describes planned expansions of Auto.

## Source excerpt

How GitHub Copilot is making more of each session go toward useful work, so your credits go further.