Adding custom endpoint

Bypassing the Parser: Connecting Azure AI Foundry to VS Code Copilot via BYOK

The "vibe-coding" era just took a massive hit.

As of June 1, 2026, GitHub completely dismantled its old request-based model for Copilot and transitioned to a strict Usage-Based Billing Model powered by GitHub AI Credits.

For developers riding on the GitHub Copilot Student plan, the reality is harsh: while basic inline code completions remain unlimited, Copilot Chat and agentic features are now heavily restricted. To make matters worse, top-tier reasoning models have been completely stripped from the Student tier self-selection menu to keep the free tier sustainable.

But if you are a student with an Azure for Students subscription, you hold a massive golden ticket in your hands: Free Azure cloud credits.

By using the Bring Your Own Key (BYOK) feature inside VS Code, you can deploy cutting-edge coding models on your own Azure instance and route them straight into your IDE, falling into three distinct tiers:

• Cloud-Hosted Enterprise Models (Azure AI Foundry & OpenAI)
• External Third-Party API Gateways (DeepSeek, OpenRouter & Anthropic)
• Fully Offline Local Models (Ollama, vLLM & Foundry Local)

Here is how to trick the system, bypass the budget limits, and build your own autonomous development environment.

Table of Contents

• Prerequisites: Snagging Your Azure Student Subscription
• Step-by-Step Configuration Blueprint
  • Step 1: Open Your Configuration Matrix
  • Step 2: Inject the Custom Schema Mapping
  • Step 3: Clear the IDE Cache Layers
• The Mechanics: Why This Layout Succeeds
  • 1. Swapping Vendor Flags to Prevent Parser Rejections
  • 2. Trimming the Target Trailing Paths
  • 3. Restricting Maximum Output Thresholds
• The Result: Infinite Coding Freedom

---

Prerequisites: Snagging Your Azure Student Subscription

Before touching VS Code, you need a valid Azure subscription with active credits to host your models. If you don't have one yet, Microsoft offers a dedicated Azure for Students tier that gives you free cloud credits annually with no credit card required.

• If you already have an account: Log into the Azure Portal or Azure AI Foundry, create a new Hub/Project, and deploy your model of choice (like gpt-5.3-codex). Copy your endpoint URL and API keys from the resource dashboard.

• If you need to create one: Head over to the official Azure for Students Portal, sign in using your academic university email address (.edu or institutional domain), and verify your student status. Your cloud sandbox and free credit allotment will provision instantly.

🛠️ Step-by-Step Configuration Blueprint

Instead of using the broken native Azure option, we are going to configure your connection as a generic, open-standard OpenAI-Compatible gateway, while preserving the specialized Responses API handling that modern Foundry models require.

Step 1: Open Your Configuration Matrix

1. Open VS Code.
2. Open the Command Palette (Ctrl+Shift+P on Windows/Linux, Cmd+Shift+P on Mac).
3. Search for and select Chat: Manage Language Models.
4. Click the gear icon next to your custom providers to open your user chatLanguageModels.json file.

Step 2: Inject the Custom Schema Mapping

Replace the contents of that file entirely with the configuration block below. Make sure to swap out the placeholder with your actual hidden workspace secret key ID:

json
[
    {
        "name": "Azure AI Foundry (BYOK)",
        "vendor": "customendpoint",
        "apiKey": "${input:chat.lm.secret.YOUR_SECRET_ID}",
        "apiType": "responses",
        "models": [
            {
                "id": "gpt-5.3-codex",
                "name": "GPT-5.3 Codex (Foundry)",
                "url": "[https://theaiagentproject.services.ai.azure.com/openai/v1](https://theaiagentproject.services.ai.azure.com/openai/v1)",
                "toolCalling": true,
                "vision": true,
                "maxInputTokens": 128000,
                "maxOutputTokens": 4096
            }
        ]
    }
]