Master CodeGPT with our step-by-step tutorial, detailed feature walkthrough, and expert tips.
Explore the key features that make CodeGPT powerful for ai agent builders workflows.
BYOK means CodeGPT does not resell model usage — instead, you connect your own API keys from providers like OpenAI, Anthropic, Google, or run local models via Ollama, and pay those providers directly for token usage. The $8/month CodeGPT subscription covers the IDE extension, agent platform, and indexing features, while model costs are billed separately by your chosen provider. The benefit is access to any model the day it launches, the ability to mix cheap and premium models per task, and full control over which vendor sees your code.
CodeGPT ships extensions for Visual Studio Code and the JetBrains IDE family (IntelliJ IDEA, PyCharm, WebStorm, GoLand, Rider, PhpStorm, and others). It runs on Windows, macOS, and Linux wherever those IDEs are supported. There is no standalone desktop application — CodeGPT augments the editor you already use rather than replacing it.
Yes. CodeGPT supports local model runtimes including Ollama and LM Studio, so you can route chat, completions, and agent tasks to models running on your own hardware. This keeps source code on-device and is well suited to regulated environments or proprietary codebases. You will need a machine with sufficient GPU or unified memory to run capable coding models locally.
Copilot is $10/month flat, with model usage included. CodeGPT BYOK is $8/month plus whatever your chosen provider charges for tokens. For light users on inexpensive models, total cost can be lower than Copilot; for heavy users on top-tier models like Claude Opus or GPT-4 class, BYOK can exceed Copilot's flat fee. CodeGPT's edge is model choice and agent flexibility rather than absolute cost.
Chat answers questions or generates code for a single prompt. Agentic mode lets CodeGPT operate over multiple steps — reading files, editing several at once, running terminal commands, and iterating toward a goal you describe in natural language. It is suitable for tasks like 'add a new API endpoint with tests' or 'migrate this module from Mocha to Vitest', where a one-shot completion is not enough. Agentic capabilities are still evolving and work best when scoped narrowly.
Now that you know how to use CodeGPT, it's time to put this knowledge into practice.
Sign up and follow the tutorial steps
Check pros, cons, and user feedback
See how it stacks against alternatives
Follow our tutorial and master this powerful ai agent builders tool in minutes.
Tutorial updated March 2026