--- title: Bring Your Own Model Within the GitHub Copilot App description: A walkthrough demonstrates how to bring your own AI model into the GitHub Copilot app when you run out of tokens or credits, instead of upgrading your Copilot... canonical: https://daily.dev/posts/bring-your-own-model-within-the-github-copilot-app-stkdb7aco twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Bring Your Own Model Within the GitHub Copilot App | daily.dev og:description: A walkthrough demonstrates how to bring your own AI model into the GitHub Copilot app when you run out of tokens or credits, instead of upgrading your Copilot... og:url: https://daily.dev/posts/bring-your-own-model-within-the-github-copilot-app-stkdb7aco og:image: https://api.daily.dev/og/posts/stKDb7aCo.png og:image:alt: Bring Your Own Model Within the GitHub Copilot App og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Bring Your Own Model Within the GitHub Copilot App **[Microsoft Developer](https://daily.dev/sources/microsoftdeveloper)** · 14 min read · 0 upvotes · 0 comments ## Summary A walkthrough demonstrates how to bring your own AI model into the GitHub Copilot app when you run out of tokens or credits, instead of upgrading your Copilot plan. It covers setting up an Azure for Students account, using the Azure MCP server inside Copilot chat to create a Microsoft Foundry resource, deploying a GPT-5 mini model, and connecting it to Copilot via the model providers settings using an endpoint, API key, and wire type. It also shows troubleshooting a token-per-minute rate limit by raising the deployment's limit from 1,000 to 250,000. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How do I connect a custom model deployment to the GitHub Copilot app instead of using the default Copilot models? Add a model provider in GitHub Copilot's settings under model providers, choose Microsoft Foundry, and enter the base URL in the form project-name.services.ai.azure.com/openai/v1, set the wire type to responses, and paste in the API key from the Foundry resource. Then search the catalog for the deployed model, name it to match the deployment, and save to use it in a new session. _daily.dev surfaces guides like this for developers wiring custom models into their coding assistants._ ### Why does my custom model deployment in GitHub Copilot return an exceeded rate limit error? The Foundry deployment's default tokens-per-minute rate limit of 1,000 is too low because GitHub Copilot sends more than 1,000 tokens per session due to its tools and MCP servers. Editing the deployment and raising the tokens-per-minute limit, for example to 250,000, resolves the exceeded rate limit error and lets the model respond normally. _developers troubleshooting rate limit errors on custom Copilot model providers can find fixes like this on daily.dev._ ### How can students get free Azure credit to deploy a model in Microsoft Foundry for GitHub Copilot? Signing up for the Azure for Students offering grants a one-time $100 credit usable within Microsoft Azure, without requiring a credit card. That credit can fund creating a Microsoft Foundry resource and deploying a model such as GPT-5 mini, which can then be connected to GitHub Copilot as a custom model provider to avoid hitting Copilot's own usage limits. _students exploring free ways to power their coding assistant can track offerings like this on daily.dev._ ## Similar posts on daily.dev - [Using Microsoft Foundry Models with GitHub Copilot After the New Billing Model](https://daily.dev/posts/using-microsoft-foundry-models-with-github-copilot-after-the-new-billing-model-lok8wnksg) · gitconnected · 2 upvotes · 0 comments - [Using GitHub Copilot CLI with Azure AI Foundry \(BYOK Models\) – Part 2](https://daily.dev/posts/using-github-copilot-cli-with-azure-ai-foundry-byok-models-part-2-lhzu8fgjp) · We Are .NET · 0 upvotes · 0 comments - [Bring your own model to GitLab Duo Self-Hosted with Microsoft Foundry](https://daily.dev/posts/bring-your-own-model-to-gitlab-duo-self-hosted-with-microsoft-foundry-zqrd4iliy) · GitLab · 0 upvotes · 0 comments --- Tags: [#github](https://daily.dev/tags/github), [#azure](https://daily.dev/tags/azure), [#mcp](https://daily.dev/tags/mcp), [#ai-inference](https://daily.dev/tags/ai-inference) [View this post on daily.dev](https://daily.dev/posts/bring-your-own-model-within-the-github-copilot-app-stkdb7aco) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Bring Your Own Model Within the GitHub Copilot App","url":"https://daily.dev/posts/bring-your-own-model-within-the-github-copilot-app-stkdb7aco","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/bring-your-own-model-within-the-github-copilot-app-stkdb7aco"},"datePublished":"2026-08-21T19:14:19.691Z","dateModified":"2026-09-13T20:46:41.976Z","description":"A walkthrough demonstrates how to bring your own AI model into the GitHub Copilot app when you run out of tokens or credits, instead of upgrading your Copilot...","image":"https://i.ytimg.com/vi/PuuF4_ngRNE/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/PuuF4_ngRNE/sddefault.jpg","isAccessibleForFree":true,"articleSection":"Microsoft Developer","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Microsoft Developer","logo":"https://media.daily.dev/image/upload/s--xZzU3zUq--/f_auto/v1746714872/logos/microsoftdeveloper","url":"https://daily.dev/sources/microsoftdeveloper"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/bring-your-own-model-within-the-github-copilot-app-stkdb7aco","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"github,azure,mcp,ai-inference","timeRequired":"PT14M","video":{"@type":"VideoObject","name":"Bring Your Own Model Within the GitHub Copilot App","description":"A walkthrough demonstrates how to bring your own AI model into the GitHub Copilot app when you run out of tokens or credits, instead of upgrading your Copilot...","thumbnailUrl":"https://i.ytimg.com/vi/PuuF4_ngRNE/sddefault.jpg","uploadDate":"2026-08-21T19:14:19.691Z","duration":"PT14M","url":"https://api.daily.dev/r/stKDb7aCo","embedUrl":"https://www.youtube.com/embed/PuuF4_ngRNE"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Microsoft Developer","item":"https://daily.dev/sources/microsoftdeveloper"},{"@type":"ListItem","position":3,"name":"Bring Your Own Model Within the GitHub Copilot App"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/bring-your-own-model-within-the-github-copilot-app-stkdb7aco#faq","mainEntity":[{"@type":"Question","name":"How do I connect a custom model deployment to the GitHub Copilot app instead of using the default Copilot models?","acceptedAnswer":{"@type":"Answer","text":"Add a model provider in GitHub Copilot's settings under model providers, choose Microsoft Foundry, and enter the base URL in the form project-name.services.ai.azure.com/openai/v1, set the wire type to responses, and paste in the API key from the Foundry resource. Then search the catalog for the deployed model, name it to match the deployment, and save to use it in a new session. daily.dev surfaces guides like this for developers wiring custom models into their coding assistants."}},{"@type":"Question","name":"Why does my custom model deployment in GitHub Copilot return an exceeded rate limit error?","acceptedAnswer":{"@type":"Answer","text":"The Foundry deployment's default tokens-per-minute rate limit of 1,000 is too low because GitHub Copilot sends more than 1,000 tokens per session due to its tools and MCP servers. Editing the deployment and raising the tokens-per-minute limit, for example to 250,000, resolves the exceeded rate limit error and lets the model respond normally. developers troubleshooting rate limit errors on custom Copilot model providers can find fixes like this on daily.dev."}},{"@type":"Question","name":"How can students get free Azure credit to deploy a model in Microsoft Foundry for GitHub Copilot?","acceptedAnswer":{"@type":"Answer","text":"Signing up for the Azure for Students offering grants a one-time $100 credit usable within Microsoft Azure, without requiring a credit card. That credit can fund creating a Microsoft Foundry resource and deploying a model such as GPT-5 mini, which can then be connected to GitHub Copilot as a custom model provider to avoid hitting Copilot's own usage limits. students exploring free ways to power their coding assistant can track offerings like this on daily.dev."}}]} ```