GitHub's AI coding assistant with code completion, chat, agent mode, a CLI and pull request review inside GitHub and major IDEs. The Free plan has 2,000 completions; Pro is $10 a month.
GitHub Copilot is an AI coding assistant made by GitHub. It offers inline code suggestions, chat in the editor and on GitHub.com, an agent mode that plans and edits across multiple files, cloud agents that work on tasks in the background, and a command-line interface. It also reviews pull requests, including ones from authors without a Copilot license when an administrator enables the feature.
Copilot works in Visual Studio Code, Visual Studio, JetBrains IDEs, Xcode, Neovim, Vim, Eclipse, Azure Data Studio, the terminal through the GitHub CLI, GitHub.com, GitHub Mobile and Raycast. Because it lives on the platform where the code is hosted, review comments appear directly in the pull request and in the editor diff view.
The plans page lists four individual plans on monthly pricing. Free costs $0 and is limited to 2,000 completions and 50 chat requests, with a limited allowance of GitHub AI Credits and no code review. Pro is $10 per month, Pro+ is $39 and Max is $100, and each of these includes pull request review on GitHub and diff review in editors. The Copilot page also shows Business at $19 and Enterprise at $39 per user per month for organizations.
Users who receive Pro through a verified student, faculty, open source or MVP route can choose the Free plan instead. The pages read do not describe compliance certifications or data residency, so check GitHub's trust documentation for those details.
Yes, a Free plan exists with 2,000 completions and 50 chat requests, plus a limited allowance of AI credits. It does not include code review.
Pro, Pro+ and Max include pull request review on GitHub and diff review in code editors. The Free plan does not.
Pro is $10 per month on the plans page. Business is listed at $19 and Enterprise at $39 per user per month.
Website: https://github.com/features/copilot
Company: GitHub, Inc.
Broad AI coding assistant with PR review on paid tiers. Free plan has 2,000 completions and no code review; Pro at $10 a month adds it. Suits teams already hosted on GitHub; reviews cost more under newer credit rules.
| Pricing model | Freemium |
|---|---|
| Free tier | Yes · 2,000 completions and 50 chat requests; limited AI credits; no code review. |
| Starting price | $10 / month |
| Data residency | Not verified |
| Compliance (as stated by vendor) | Not verified |
| Integrations | Visual Studio Code, Visual Studio, JetBrains IDEs, Xcode, Neovim, Eclipse, Raycast |
| Public API | Not verified |
| Self-hostable | Not verified |
| Official site | Not verified |
| Can a general AI assistant replace it? | A general LLM can review pasted code but cannot comment in the PR or edit your repo. Copilot is integrated with GitHub and IDEs for that. |
| Last verified | 2026-10-10 by editor |
Open Interpreter is an open-source terminal agent, forked from Codex, that reads and edits files and runs commands inside an OS-level sandbox with approvals. It is free under Apache 2.0 and works with local models through Ollama or LM Studio.
Together AI is a cloud platform for running open models through a per-token serverless API, plus dedicated endpoints, GPU clusters and fine-tuning. Hosted GLM-5.3-Flash, for example, is listed at $0.15 input and $0.50 output per million tokens.
Kimi is Moonshot AI's assistant and model family, offered as the kimi.com agent workspace and as a pay-as-you-go API. The Kimi K2.7 Code model is listed at $0.95 input and $4.00 output per million tokens.
Z.ai offers the GLM model family through a chat app and a developer API billed per million tokens. GLM-5.3-Flash is listed at $0.15 input and $0.50 output, and the API is compatible with the OpenAI SDK.
The Gemini API and Google AI Studio let developers build with Google's Gemini models for text, code, images, video and speech. A free tier covers some models; paid use is billed per million tokens, such as $0.30 in and $2.50 out on Gemini 3.5 Flash-Lite.
The Claude API is Anthropic's developer platform for building apps and agents on Claude models, billed per million tokens. Rates run from Claude Haiku 5.5 at $0.10 input and $0.50 output up to Claude Fable 5.1 at $10 and $50.
Need the outcome rather than the software?