Copilot, Codex or Claude Code? The subscription prices are closer than the usage limits

A 1 October 2026 comparison of GitHub Copilot, OpenAI Codex and Claude Code shows entry prices from $8 to $20 a month, but very different usage limits. The AI coding tools buying question has moved from price to how you use them.

Searches for “Codex vs Claude Code vs Copilot” keep climbing, and a comparison checked against vendor documentation on 1 October 2026 gives the clearest current picture of what each AI coding tool costs.

The headline prices

Entry plans are cheap and close together. GitHub Copilot Pro is $10 a month, OpenAI Codex starts at $8 (Go) or $20 (Plus), and Claude Code starts at $20 (Pro). At the heavy end, Copilot’s top tier is $100, while Codex Pro and Claude Max run $100 to $200.

Where they really differ

The pricing page is only half the story. Copilot now works on AI credits at $0.01 each, with $15 included on Pro and $200 on its top plan. Codex meters by model: on the Plus plan you get roughly 5 to 45 messages per five-hour window with the flagship GPT-6 Astra, but 250 to 2,000 with the lighter Luna. Claude Code uses a rolling five-hour window, which Anthropic doubled on 6 May 2026.

On performance the gap is thin. In September’s Terminal-Bench 4.0, Codex with GPT-6 Astra scored 58.2% and Claude Code with Fable 5.1 scored 57.9%.

What the comparison concludes

Its recommendation is practical: keep Copilot for in-editor flow, add Codex or Claude Code for delegated, hands-off tasks, and start from whichever subscription you already pay for.

So what

For a founder, the subscription price is the least important number here. It is a rounding error next to the cost of a build that is badly scoped or insecure. What matters is how a team uses these tools: how work is split between humans and agents, who reviews the output, and what happens when a usage limit changes mid-project, as several have this year. Ask any developer or agency which tools they use, on which plans, and who checks the code. If you want that approach applied to your own product, see our AI-assisted development service, or start a project.

← All research

More research.

GitHub Copilot adds Supabase, Webflow, Wix and five more connectors in public preview

GitHub Copilot now connects to eight more services, including Supabase, Webflow, Wix and Mixpanel, through verified MCP connectors in public preview. They join more than 25 existing ones.

Read ›

Gemini 4 Neon is generally available in GitHub Copilot, aimed at lower-cost agentic coding

Gemini 4 Neon is now generally available in GitHub Copilot for agentic coding. Google says its quality is close to Gemini 4 Carbon at a lower token cost per task.

Read ›

Claude Code 2.1.328 brings auto mode to Bedrock, Vertex and Foundry, and narrows /code-review to bugs

Claude Code 2.1.328 extends auto mode to Claude Opus 4.6 and Sonnet 4.6 on Amazon Bedrock, Google Cloud and Microsoft Foundry. /code-review now reports only bugs and CLAUDE.md violations.

Read ›

GitHub Copilot Evals: repeatable tests for AI agents, now in public preview

GitHub Copilot Evals lets teams write repeatable tests for AI coding skills, custom agents and MCP tools. It checks both the result and the path the agent took, and is in public preview.

Read ›

GitHub Copilot can now drive your browser: browser use enters public preview

GitHub Copilot browser use lets an AI coding agent control Chrome to debug web apps and run browser tests. It is in public preview across the CLI, the Copilot app, VS Code and JetBrains.

Read ›

Claude Code 2.1.327 refuses some symbolic links and lists broken setup in /status

Claude Code 2.1.327 tightens file and package permissions again and adds a /status list of broken agent, skill and hook settings. A short read for teams using AI coding tools on a live product.

Read ›

Start a project

Building with AI? Let's talk.

Tell us what you are building. We'll give you an honest view of the right approach.

Start a projectSee our work