GitHub Copilot vs Sourcegraph Cody: pricing, features and which to choose

GitHub Copilot is GitHub’s AI coding assistant, developed with OpenAI and introduced in technical preview in 2021 before general availability in June 2022. It now supports inline completions, next-edit suggestions, chat, agent mode, code review, pull-request summaries, vulnerability fixes, and a cloud coding agent that can plan work, edit repositories, run tests, and open pull requests. Copilot works across VS Code, Visual Studio, JetBrains, Xcode, Vim, Neovim, terminal, web, mobile, Slack, and Teams. Current model choices include GPT-5.3-Codex, GPT-6 variants, Claude Sonnet and Opus models, Gemini, Grok, Kimi, and others, depending on plan and client. Free access is limited, while Pro costs $10 monthly, Pro+ $39, and Max $100; Business is $19 per seat and Enterprise $39. Cursor, Windsurf, and Claude Code can feel stronger for specialized agent workflows, but Copilot is the best fit for GitHub-centered teams.

A typical Copilot session starts with inline completions or next-edit suggestions, then expands into chat for explaining files, drafting functions, refactoring, testing, and documentation. Agent mode can modify several files and run approved terminal commands, while GitHub’s cloud coding agent researches issues, creates plans, implements changes, runs tests, and opens pull requests. Its strongest advantage is context: repositories, issues, pull requests, Actions, CI/CD, security findings, and review history inform suggestions beyond an editor’s open files. Developers can also use pull-request summaries, Copilot Autofix, custom instructions, prompt files, content exclusion, Spaces, MCP, the CLI, and desktop app across many clients. The trade-off is required oversight: generated code can be inaccurate, insecure, outdated, or license-sensitive, so testing and human review remain essential.

Copilot’s chief strength is its GitHub-centered workflow, connecting inline suggestions, chat, agent mode, code review, pull requests, issues, Actions, security tooling, and repository context across VS Code, JetBrains, Visual Studio, terminal, web, mobile, and other clients. Its multi-model catalog includes GPT, Claude, Gemini, Grok, Kimi, and MAI options, although availability depends on plan, client, feature, and provider. Free and Student tiers impose tighter model and credit limits; Pro costs $10 monthly, Pro+ $39, Max $100, Business $19 per assigned seat, and Enterprise $39, with included AI-credit pools and paid overage controls. Output can be inaccurate, insecure, incomplete, outdated, or license-sensitive, requiring testing and review. GitHub-focused developers should choose Copilot, while editor-first teams should compare Cursor or Windsurf, and terminal-oriented users should consider Claude Code.

Sourcegraph Cody is an AI coding assistant made by Sourcegraph for organizations working with large codebases. Sourcegraph introduced Cody in Sourcegraph 5.0 in March 2023, and Cody 1.0 became generally available in December 2023. Cody uses Sourcegraph code intelligence to answer questions, generate code, and suggest editor completions. Cody Free and Cody Pro ended July 23, 2025, while Cody Enterprise continued. Sourcegraph and Amp became separate companies in December 2025. Sourcegraph focuses on code search and enterprise infrastructure, while Amp focuses on frontier coding agents. Cody remains an enterprise capability, rather than a current self-serve developer subscription. Its positioning therefore centers on governed access, repository scale, and organizational deployment rather than casual individual experimentation or a low-cost personal plan.

Cody handles questions, completion requests, and edits inside supported editors and Sourcegraph interfaces. Sourcegraph retrieves relevant code snippets and enforces the user’s read permissions during retrieval. Cody supports completions, chat, code explanations, documentation, unit-test generation, quick fixes, and natural-language code search. Agentic chat can gather context from code search, files, the terminal, the web, and OpenCtx providers. Terminal commands are among the available tools for agentic context gathering. Enterprise administrators can control access through Sourcegraph’s role-based controls, and Cody supports multi-repository context for up to 10 repositories. This combination lets teams apply existing repository permissions while giving developers contextual assistance across larger software estates.

Cody is a poor fit for an individual seeking a current free assistant or transparent monthly pricing. The FAQ says there is no public-facing Cody API, and self-hosted deployments still send snippets to a third-party cloud service for model interactions. GitHub Copilot has a clearer self-serve route, while Cursor and Claude Code target accessible local coding workflows. Cody’s strongest case is permission-aware, multi-repository context combined with Sourcegraph Search and enterprise deployment choices. Choose Cody Enterprise when repository governance and centralized administration matter most. Choose Copilot, Cursor, or Claude Code when individual access and local agentic workflows matter more. Organizations should also weigh provider handling, contract terms, and deployment requirements before adoption.