# AI coding agents compared, November 2026

> As of 4 November 2026, most AI coding agents start at $20 a month and top out at $200. GitHub Copilot Pro is the cheapest full plan at $10, and Cline is free if you bring your own API key. The bigger difference is how each one meters usage: five-hour limits, credits or API prices.

- This page: https://finderatlas.com/blog/ai-coding-agents-compared
- Published: 2026-11-04
- Facts last checked: 2026-11-04

## All coding agents at a glance

Monthly US prices for individual plans, from each vendor's pricing page on 4 November 2026.

**AI coding agent plans, checked 4 Nov 2026**

| Agent | Works in | Free plan | Entry plan | Top plan |
| --- | --- | --- | --- | --- |
| [Claude Code](https://finderatlas.com/tools/claude-code.md) | Terminal, IDE, desktop, web | No | Claude Pro, $20 | Claude Ultra, $200 |
| [OpenAI Codex](https://finderatlas.com/tools/openai-codex.md) | Terminal, IDE, desktop, cloud | Limited, desktop app | ChatGPT Plus, $20 | ChatGPT Pro, $500 |
| [Cursor](https://finderatlas.com/tools/cursor.md) | Editor, cloud agents | Limited | Plus, $8 | Ultra, $200 |
| [GitHub Copilot](https://finderatlas.com/tools/github-copilot.md) | IDE, terminal, cloud agent | Yes, 2,000 completions | Pro, $10 | Max, $100 |
| [Devin](https://finderatlas.com/tools/devin.md) (incl. Devin Desktop) | Cloud agent, editor, terminal | Light quota | Pro, $20 | Max, $200 |
| [Google Antigravity](https://finderatlas.com/tools/google-antigravity.md) | Desktop IDE, terminal | Yes, weekly limits | Google AI Plus, $4.99 | Google AI Ultra, $199.99 |
| [Kiro](https://finderatlas.com/tools/kiro.md) | IDE, terminal, web | 50 credits | Pro, $20 | Power, $200 |
| [Cline](https://finderatlas.com/tools/cline.md) | VS Code, JetBrains, terminal | Open source; pay for models | ClinePass, $9.99 (optional) | Enterprise, custom |
| [Augment Code](https://finderatlas.com/tools/augment-code.md) | Cloud agents, IDE, terminal | No | Standard, $20 | Business, $100 |
| [Factory](https://finderatlas.com/tools/factory.md) | Desktop, terminal | No | Pro, $20 | Max, $200 |

_Codex Free and Go use one model in the desktop app only. Cursor Plus runs Cursor's own and Grok models only; third-party models start on Premium ($30)._

## What changed in 2026

- **Google Jules is shutting down.** Google's changelog (29 Oct) says sessions can be finished until 11 November 2026; Jules is then read-only until it closes on 31 December. Google points users to [Antigravity](https://finderatlas.com/tools/google-antigravity.md).
- **Claude's Max 20x plan is now Ultra** (30 Oct), still $200 a month, with 10x Pro usage per week and no five-hour limit for verified accounts.
- **Cursor joined xAI's X Subscription** (12 Oct). New plans are Plus $8, Premium $30, Super $100 and Ultra $200, with a weekly usage pool shared with Grok. Old Pro and Pro+ plans keep working as legacy plans.
- **Windsurf became Devin Desktop** (2 Jun) and now shares Devin's plans. Windsurf for JetBrains continues as a separate product.
- **GitHub Copilot moved to AI credits** (1 Jun). Each credit is $0.01; completions are free, while agent mode, code review, the cloud agent and the CLI use credits. Copilot Max ($100) launched the same day.
- **Devin cut its team price** (14 Apr). The $500-a-month Team plan became Teams at $80 a month plus $40 per developer seat, and the old pay-as-you-go plan became Free.

## Which AI coding agent is cheapest?

- **Free with your own key:** [Cline](https://finderatlas.com/tools/cline.md) is open source. You pay your model provider directly, at their API prices.
- **Free plan:** [Google Antigravity](https://finderatlas.com/tools/google-antigravity.md) has a free individual plan with weekly limits and unlimited Tab completions. [GitHub Copilot](https://finderatlas.com/tools/github-copilot.md) Free includes 2,000 completions a month.
- **Cheapest paid:** Google AI Plus ($4.99) gives a limited Antigravity plan. Cursor Plus ($8) is cheap but limited to Cursor's own and Grok models. Copilot Pro ($10) includes 1,500 AI credits and premium models.
- **Already paying for a chatbot:** ChatGPT Plus includes Codex and Claude Pro includes Claude Code, both at $20, so there may be nothing extra to buy.

## How is usage billed?

Two $20 plans can give very different amounts of work. This is how each vendor meters it:

**Usage model by agent**

| Agent | What you get | When you run out |
| --- | --- | --- |
| Claude Code | Limits per five hours and per week | Wait, upgrade, or use an API key |
| OpenAI Codex | Messages per five hours; OpenAI estimates 15–160 on Plus with GPT-6.1 Sol | Buy credits |
| Cursor | A weekly pool for Cursor and Grok models | Third-party models are billed at API list price |
| GitHub Copilot | AI credits: 1,500 on Pro, 7,000 on Pro+, 20,000 on Max | Credits at $0.01 each |
| Devin | Daily and weekly quotas | Extra usage at API pricing |
| Kiro | Credits: 1,000 on Pro up to 10,000 on Power | Add-on credits at $0.04 |
| Augment Code | Usage worth the plan price | Model API price plus a 40% fee |
| Factory | Credits with five-hour, 7-day and 30-day limits | A free open-model pool, then prepaid usage |

## Terminal, editor or cloud agent?

- **Terminal-first:** [Claude Code](https://finderatlas.com/tools/claude-code.md) and [OpenAI Codex](https://finderatlas.com/tools/openai-codex.md) run in your shell and also ship IDE extensions and desktop apps.
- **Editor-first:** [Cursor](https://finderatlas.com/tools/cursor.md), Devin Desktop, [Antigravity](https://finderatlas.com/tools/google-antigravity.md) and [Kiro](https://finderatlas.com/tools/kiro.md) are full editors with an agent built in. Kiro writes a spec (requirements, design, tasks) before it codes.
- **Inside your current IDE:** [GitHub Copilot](https://finderatlas.com/tools/github-copilot.md) and [Cline](https://finderatlas.com/tools/cline.md) are extensions for VS Code and JetBrains.
- **Background agents:** [Devin](https://finderatlas.com/tools/devin.md), [Augment Code](https://finderatlas.com/tools/augment-code.md), [Factory](https://finderatlas.com/tools/factory.md), Codex Cloud and Copilot's cloud agent take a task and return a pull request.

For head-to-head details, see [Claude Code vs Cursor](https://finderatlas.com/compare/claude-code-vs-cursor.md), [Claude Code vs Codex](https://finderatlas.com/compare/claude-code-vs-openai-codex.md) and [Cursor vs GitHub Copilot](https://finderatlas.com/compare/cursor-vs-github-copilot.md), or browse [all coding AI tools](https://finderatlas.com/categories/coding-ai.md).

## Team plans

**Team prices, monthly billing**

| Plan | Price | Notes |
| --- | --- | --- |
| GitHub Copilot Business | $19 per seat | 1,900 AI credits per user; Enterprise is $39 |
| Claude Team | $25 per seat | $20 billed annually; Premium seats $125 |
| ChatGPT Business (Codex) | $25 per seat | $20 billed annually |
| Cursor Teams | $30, $100 or $200 per seat | Plus $0.25 per million tokens on third-party models |
| Devin Teams | $80 plus $40 per seat | Up to 200 users |
| Factory Teams | $60 plus $40 per seat | Up to 10 seats |
| Augment Code | $20 or $100 flat | No per-seat charge, up to 50 seats |

## What about benchmarks?

There is no current neutral leaderboard. The newest entry in the official SWE-bench Verified data is from February 2026, so it predates every model these agents now use. Vendor-published scores test models, not the agent around them, and each vendor picks its own settings. Treat them as claims and try two agents on your own code instead: most have a free plan or a $20 tier you can cancel.

## How we checked

Every plan and price comes from the vendor's pricing page or documentation, opened on 4 November 2026. None of the vendors publish exact quota numbers except where stated. For subscription prices of the chat apps that include these agents, see [AI subscription prices](https://finderatlas.com/blog/ai-subscription-prices.md).

## Frequently asked questions

**What is the cheapest AI coding agent?**

Cline is free and open source if you pay your model provider directly. Among paid plans, Google AI Plus ($4.99) includes a limited Antigravity plan, Cursor Plus costs $8 with Cursor and Grok models only, and GitHub Copilot Pro costs $10 with premium models.

**Is Claude Code free?**

No. Claude Code is not on Claude's free plan. It comes with Pro ($20 a month), Max, Ultra and Team, or you can pay per token with an Anthropic API key.

**What happened to Windsurf?**

Cognition renamed the Windsurf editor Devin Desktop on 2 June 2026. It uses Devin's plans: Free, Pro at $20 and Max at $200. Windsurf for JetBrains continues separately.

**Is Google Jules shutting down?**

Yes. Google says Jules sessions can be finished until 11 November 2026, after which it is read-only until it closes on 31 December 2026. Google points users to Antigravity.

**What is the difference between Cursor Plus and Premium?**

Plus ($8) runs only Cursor's own and Grok models, with no cloud agents. Premium ($30) adds third-party models such as Claude and GPT, cloud agents and Bugbot code review, with 4x the Plus usage.

## Sources

- [Claude pricing](https://claude.com/pricing)
- [Codex pricing (OpenAI)](https://learn.chatgpt.com/docs/pricing)
- [Cursor pricing](https://cursor.com/pricing)
- [xAI: X Subscription](https://x.ai/news/x-subscription)
- [GitHub Copilot plans](https://docs.github.com/en/copilot/get-started/plans)
- [GitHub changelog: Copilot billing, 1 June 2026](https://github.blog/changelog/2026-06-01-updates-to-github-copilot-billing-and-plans/)
- [Devin pricing](https://devin.ai/pricing)
- [Windsurf is now Devin Desktop](https://devin.ai/blog/windsurf-is-now-devin-desktop)
- [Cognition: new self-serve plans for Devin](https://cognition.com/blog/new-self-serve-plans-for-devin)
- [Google Antigravity pricing](https://antigravity.google/pricing)
- [Jules changelog](https://jules.google/docs/changelog/)
- [Kiro pricing](https://kiro.dev/pricing)
- [Cline pricing](https://cline.bot/pricing)
- [ClinePass docs](https://docs.cline.bot/getting-started/clinepass)
- [Augment Code pricing](https://www.augmentcode.com/pricing)
- [Augment token-based pricing](https://docs.augmentcode.com/models/token-based-pricing)
- [Factory pricing](https://docs.factory.com/pricing/individuals.md)
- [SWE-bench leaderboard data](https://raw.githubusercontent.com/SWE-bench/swe-bench.github.io/master/data/leaderboards.json)