AI coding tools

AI coding tools now range from autocomplete in your current editor to agents that work on tasks in the cloud while you do something else. This grid compares popular tools side by side on the practical things that decide a purchase: where they run, what a plan really costs, which models and agent features you get, and how your code is handled. The real trade-off is power against predictability and control: the most capable agents cost more, often bill by usage, and need more care over privacy and review.

Last updated

How to choose

Start with how you work, then check cost and your code's privacy before comparing features.

1. Decide where you want the AI

  • Keep your current editor: look at Product type IDE plugin and the Editors supported row.
  • Move to an AI-first editor: AI code editors give the deepest agent features but you change tools.
  • Work in the terminal or hand off tasks: terminal and cloud agents suit scripts, servers and background work (Terminal command line, Background cloud agents).
  • Prototype an app from a prompt: App builders are fastest for demos, with less control of the codebase.

2. Rule out deal-breakers

  • Private or regulated code: check Trains on your code, Zero data retention option, SOC 2 report, Single sign on and Self hosted option.
  • Your operating system and editor must be supported.

3. Understand the real cost

  • Headline prices hide usage limits. Pricing model shows whether you pay a flat fee or credits that agents can burn quickly.
  • Compare the Cheapest paid plan with the Top individual plan: heavy agent users often need the top tier.
  • For a team, compare Team plan per user and any base fee.
  • Free plans are good for trials but their limits run out fast.

4. Compare what you will actually use

  • Daily work: Code completion and Chat in editor.
  • Bigger tasks: Agent mode, Codebase context, MCP support and Pull request review.
  • Flexibility: Model choice, Bring your own API key and Open source reduce lock-in.

5. Try before you commit

  • Test two or three tools on a real task in your own codebase, and review every AI change before you merge it.
  • Prices, plans and even product names change often. Avoid long prepaid commitments.

Answer

Browse the table. Filter to what matters.

Use the filters below, then sign in if you want to shortlist and decide with friends.

Sign in to vote

Sign in to vote, hide services and features, and reorder.

Verified: hover a cell and click its green dot for the source Estimate: no cited source Not stated: the company doesn't publish it

FeatureService ⠿ ⠿
Links
⠿ ⠿ ⠿ ⠿
Amp
Amp
Links
⠿ ⠿ ⠿
Links
⠿ ⠿
Links
⠿
Zed
Links
⠿
Links
⠿
Links
⠿
Links
⠿ ⠿ ⠿ ⠿ ⠿ ⠿
v0
Links
⠿ ⠿ ⠿
⠿
Price
$20/month
$8/month
Doesn't apply
Doesn't apply
$10/month
$20/month
$20/month
$20/month
$8/month
$20/month
$20/month
$10/month
$20/month
$20/month
$19.99/month
$9.99/month
$19/month
$20/month
$25/month
$25/month
$30/month
$10/month
$10/month
$20/month
⠿
Product type
Terminal agent
Terminal agent
Terminal agent
Terminal agent
Terminal agent
Cloud agent
Cloud agent
Terminal agent
AI code editor
AI code editor
AI code editor
AI code editor
Terminal agent
AI code editor
AI code editor
IDE plugin
IDE plugin
App builder
App builder
App builder
App builder
IDE plugin
IDE plugin
IDE plugin
⠿
Free plan
No
Yes
No
Yes
Yes
Yes
Yes
No
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
No
⠿
Free plan limits
Doesn't apply
Light coding tasks; GPT-6 Luna in desktop app, subject to rollout
Doesn't apply
No Aider caps; you pay your model provider
Bundled free models, no account needed; other providers cost extra
Pay as you go for cloud orb time; free on your own runners
Light agent quota, limited models; unlimited Tab and inline edits
Doesn't apply
Limited AI usage, limited agent and chat requests
Light agent quota, limited models; unlimited Tab and inline edits
50 credits per month; open weight models and Claude Sonnet 4.5, rate limited
No Zed-hosted models; AI only via your own API keys or external agents
Limited cloud agents; extra agent usage pay-as-you-go; bring your own inference
Auto model only, limited usage, 5,000 autocompletions per month
Basic weekly rate limits; unlimited Tab completions and command requests
No plan caps; you pay for inference used
Free models only where available; others at provider rates
Daily Agent credits, Lite build only, one published app (expires after 30 days)
5 build credits per day, up to 30 per month
1M tokens per month, 300K per day
7 messages per day
2,000 completions a month; limited chat and agent use from an AI credit allowance; auto model selection only
3 AI credits per 30 days (1 credit = $1 of usage); not in Community editions
Doesn't apply
⠿
Top individual plan
$200/month
$500/month
Doesn't apply
Doesn't apply
$40/month
$20/month
$200/month
$200/month
$200/month
$200/month
$200/month
$10/month
$200/month
$200/month
$199.99/month
$9.99/month
$199/month
$100/month
$2,250/month
$25/month
$100/month
$100/month
$30/month
$100/month
⠿
Team plan per user
$25/user/month
$25/user/month
$22.80/user/month
Doesn't apply
$20/user/month
$0/user/month
$40/user/month
$40/user/month
$30/user/month
$40/user/month
$20/user/month
$30/user/month
$50/user/month
Not stated
$30/user/month
Not stated
$15/user/month
Doesn't apply
Doesn't apply
$30/user/month
$30/user/month
$19/user/month
$20/user/month
Doesn't apply
⠿
Pricing model
Subscription with usage limits, optional extra credits
Subscription plus usage credits
Pay as you go (API key) or Code Assist license
Bring your own key
Free client; optional Go subscription (top-up credit available), or bring your own key
Subscription with orb minutes; pay as you go on free tier; BYOK
Subscription plus extra usage at API pricing
Subscription with rolling usage limits
Subscription plus usage credits
Subscription plus usage credits
Subscription plus usage credits
Subscription plus usage credits
Subscription plus usage credits
Subscription plus usage credits
Subscription plus usage credits
Bring your own key or usage billing; optional flat ClinePass
Free platform; pay-as-you-go inference, BYOK or Kilo Pass credits
Subscription plus usage credits
Subscription plus usage credits
Subscription with monthly token allowance
Subscription plus usage credits
Subscription plus usage credits (monthly AI credits, extra billed per credit)
Subscription plus usage credits (monthly AI credits, buy more)
Flat team subscription with included usage; token-based top-ups plus 40% fee
⠿
Models offered
Anthropic (Claude)
OpenAI
Google (Gemini)
Any: OpenAI, Anthropic, DeepSeek, Google, local models
200+ providers via Models.dev, incl. local models
OpenAI, Anthropic, others
OpenAI, Anthropic, Google, SpaceXAI, open source, own SWE-2
Anthropic, OpenAI, Google, xAI, open models
OpenAI, Anthropic, Google, SpaceXAI (Grok)
OpenAI, Anthropic, Google, SpaceXAI, open source, own SWE-2
Anthropic, OpenAI, open weight (DeepSeek, MiniMax, GLM, Qwen)
Anthropic, OpenAI, Google, Mistral, DeepSeek, local Ollama and more
OpenAI, Anthropic, z.ai and more
OpenAI, Anthropic, Google, DeepSeek
Google Gemini, Anthropic Claude, OpenAI GPT-OSS
Anthropic, OpenAI, Google, open models, local
500+ models: Anthropic, OpenAI, Google, open-weight, local
Anthropic, OpenAI, Moonshot (Kimi)
Not disclosed; Lovable picks the model
Not disclosed; Bolt picks the model
v0 Mini, Pro, Max models (Vercel)
Anthropic, OpenAI, Google, xAI, Microsoft, Moonshot
Anthropic, OpenAI, Google; own keys or local models
Anthropic, OpenAI, Google, xAI, Moonshot, Zhipu, own Prism ensemble
⠿
Model choice
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
No
No
Yes
Yes
Yes
Yes
⠿
Bring your own API key
Yes
Yes
Yes
Yes
Yes
Yes
No
Yes
Yes
Yes
No
Yes
Yes
Yes
No
Yes
Yes
No
No
No
No
Yes
Yes
Yes
⠿
Code completion
No
No
No
No
No
No
Yes
No
Yes
Yes
Yes
Yes
Yes
Yes
Yes
No
Yes
Yes
No
No
No
Yes
Yes
No
⠿
Chat in editor
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
⠿
Agent mode
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
⠿
Terminal command line
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
No
Yes
No
Yes
Yes
Yes
No
No
No
No
Yes
Yes
Yes
⠿
Background cloud agents
Yes
Yes
No
No
Yes
Yes
Yes
Yes
Yes
Yes
Yes
No
Yes
Yes
Yes
Yes
Yes
Yes
Yes
No
Yes
Yes
Yes
Yes
⠿
Codebase context
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
⠿
MCP support
Yes
Yes
Yes
No
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
⠿
Pull request review
Yes
Yes
Yes
No
Yes
Yes
Yes
Yes
Yes
Yes
Yes
No
Yes
Yes
Yes
Yes
Yes
No
No
No
Yes
Yes
Yes
Yes
⠿
Open source
No
Yes
Yes
Yes
Yes
No
No
No
No
No
No
Yes
Yes
No
No
Yes
Yes
No
No
Yes
No
Yes
No
No
⠿
Editors supported
Terminal, VS Code, Cursor, JetBrains, desktop app, web
VS Code, Cursor, Windsurf, own desktop app, CLI
Terminal; VS Code companion
Terminal; works alongside any editor or IDE
Terminal, desktop app; VS Code, Cursor, any IDE with a terminal
Own app (web, macOS, iOS, Android), CLI
Own editor (Devin Desktop), web, CLI
Own desktop app, CLI, SDK; VS Code, Cursor, Windsurf, JetBrains, Zed
Own editor (VS Code-based); also CLI, web
Own editor; plugins for VS Code, JetBrains, Eclipse, Xcode, Visual Studio
Own editor (VS Code-based); CLI, web
Own editor
Own terminal; Agent CLI works in any terminal
Own editor (VS Code-based)
Own IDE; extensions for VS Code, Visual Studio, JetBrains, Zed, Xcode
VS Code, JetBrains, Cursor, Windsurf, desktop app
VS Code and forks, JetBrains, CLI, Slack
Own editor (browser, desktop app, mobile app)
Own editor (web app)
Own editor (web app)
Own editor (web app, iOS app)
VS Code, Visual Studio, JetBrains, Xcode, Eclipse, Vim, Neovim, Zed, plus CLI and GitHub
JetBrains IDEs (IntelliJ IDEA, PyCharm, WebStorm and more), Android Studio; Junie CLI in terminal
VS Code, JetBrains IDEs, Vim and Neovim; Auggie CLI
⠿
Operating systems
Windows, macOS, Linux
Windows, macOS, Linux
Windows, macOS, Linux
Windows, macOS, Linux
Windows, macOS, Linux
macOS, Linux, Windows
Windows, macOS, Linux
Windows, macOS, Linux
Windows, macOS, Linux
Windows, macOS, Linux
Windows, macOS, Linux
macOS, Linux, Windows
macOS, Windows, Linux
macOS, Windows, Linux
macOS, Windows, Linux
Windows, macOS, Linux
Windows, macOS, Linux
Web, Windows, macOS, Linux
Web
Web
Web
Windows, macOS, Linux
Windows, macOS, Linux
Windows, macOS, Linux
⠿
Trains on your code
Opt-out
Opt-out
No by default
No by default
No by default
Opt-in
Opt-out
No by default
Opt-out
Opt-out
Opt-out
Opt-in
No by default
Opt-out
Opt-out
No by default
No by default
Opt-out
Opt-out
Opt-out
Opt-out
Opt-out
Opt-in
No by default
⠿
Zero data retention option
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
No
Yes
Yes
Yes
No
Yes
Yes
No
No
No
No
Yes
Yes
Yes
⠿
SOC 2 report
Yes
Yes
Yes
No
No
Yes
Yes
No
Yes
Yes
No
No
Yes
Yes
No
No
No
Yes
Yes
Yes
Yes
Yes
Yes
Yes
⠿
Single sign on
Yes
Yes
Yes
No
Yes
Yes
Yes
Yes
Yes
Yes
Yes
No
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
Yes
⠿
Self hosted option
Yes
Yes
No
Yes
Yes
Yes
Yes
Yes
No
Yes
No
Yes
Yes
No
Yes
Yes
Yes
Yes
No
No
No
Yes
Yes
Yes

Why these features matter

  • Price ($/month)

    The entry cost for a regular developer.

  • Product type

    Decides where you work: inside a new editor, inside your current IDE, in a terminal, or in the browser.

  • Free plan

    Lets you try the real product without paying.

  • Free plan limits

    Free limits often run out within days for real work.

  • Top individual plan ($/month)

    Heavy agent use often needs the top tier.

  • Team plan per user ($/user/month)

    What a company pays per developer.

  • Pricing model

    Usage-based pricing can make the real bill far higher than the headline price.

  • Models offered

    Model choice affects quality, speed and cost.

  • Model choice

    Lets you match a model to the task and switch if one regresses.

  • Bring your own API key

    Avoids markups and rate limits, and lets you use a company account.

  • Code completion

    The fastest everyday help, separate from chat and agents.

  • Chat in editor

    Lets you ask about code without leaving the editor.

  • Agent mode

    Agents do bigger tasks but need careful review.

  • Terminal command line

    Suits scripts, remote servers and CI use.

  • Background cloud agents

    Lets you hand off work and review later.

  • Codebase context

    Whole-project awareness cuts wrong guesses in big codebases.

  • MCP support

    Lets it reach your issue tracker, database and docs.

  • Pull request review

    Catches bugs and style problems before merge.

  • Open source

    Lets you inspect and modify it; matters for security reviews.

  • Editors supported

    Determines whether you can keep your current setup.

  • Operating systems

    Whether it works on your machine.

  • Trains on your code

    A top concern for company or private code.

  • Zero data retention option

    Needed for many regulated or confidential codebases.

  • SOC 2 report

    A common procurement requirement for business use.

  • Single sign on

    Required by most companies to manage access.

  • Self hosted option

    Needed for air-gapped or strict data-control environments.

About the services

  • Claude Code · Anthropic

    Anthropic's agentic coding tool for the terminal, IDEs, desktop and web, included in Claude Pro, Max, Team and Enterprise plans. Suits developers who want a strong autonomous agent; it is Claude-only and usage-limited by plan.

  • Codex · OpenAI

    OpenAI's coding agent across CLI, IDE extension, desktop app and cloud, bundled with ChatGPT plans (including a free tier) with shared usage limits. The CLI is open source; models are OpenAI only.

  • Gemini CLI · Google

    Google's open-source terminal agent for Gemini models. Since June 2026 free individual and Google One users have been moved to Antigravity CLI, so it now suits API-key and Code Assist license users.

  • Aider · Aider

    Free, open-source terminal pair programmer that works with almost any model using your own API key and commits changes to git. Development has slowed (last release August 2025) and it has no MCP or cloud agents.

  • OpenCode · Anomaly

    Open-source (MIT) coding agent for terminal, desktop and IDEs that works with 75+ providers, including your existing Claude, ChatGPT or Copilot subscriptions. Free with bundled models; optional Go and Zen paid model access.

  • Amp · Amp

    Multi-model coding agent with CLI, desktop and mobile apps and cloud "orbs" that keep working after you close your laptop. Free to start with pay-as-you-go orb time; closed source.

  • Devin · Cognition

    Cognition's autonomous cloud software engineer, now sold with the Devin Desktop editor under one set of plans from free to Max. Suits teams delegating tasks to background agents; extra usage bills at API rates.

  • Factory Droid · Factory

    Factory's Droid agents run in desktop, CLI and cloud with model choice and bring-your-own-key support, aimed at teams and enterprises. No free plan; paid from $20 a month.

  • Cursor · Anysphere

    AI code editor (VS Code fork) with agents, Tab autocomplete, a CLI and cloud agents. Now sold as part of the X Subscription alongside Grok; the $8 Plus tier is Grok-models only, and third-party models bill at API rates on higher tiers.

  • Devin Desktop (formerly Windsurf) · Cognition

    Windsurf was renamed Devin Desktop in June 2026: an AI IDE with a local Devin agent, cloud delegation and an agent command center. Free tier with unlimited Tab; paid quotas refresh daily and weekly, extra use bills at API prices.

  • Kiro · Amazon

    AWS agentic IDE built around spec-driven development, with CLI, web and cloud agents. Credit-based plans from free to $200; free tier is small (50 credits) and paid plans are per user.

  • Zed · Zed Industries

    Fast open source (GPL-3.0) native editor written in Rust with an agent panel and edit predictions. Free tier has no hosted AI (use your own keys or external agents); Pro is $10 with $5 of tokens, then usage billing. No SSO yet.

  • Warp · Warp

    Agentic terminal plus a standalone Agent CLI and cloud agents. Credit-style plans at $20 and $200 with agent usage at API rates; SOC 2 Type 2, SAML SSO and zero data retention. The terminal is not a code editor.

  • TRAE · ByteDance

    ByteDance AI IDE with Builder/SOLO agents and cloud tasks. Free tier is Auto-model only with 5,000 completions a month; paid plans $20 to $200 are usage-based. Privacy terms are less clear than rivals, so check them for company code.

  • Antigravity · Google

    Google's agent-first platform: desktop app, IDE, CLI and IDE extensions. Free for individuals with weekly rate limits; more capacity comes with Google AI Pro/Ultra plans. Prompts are collected by default on consumer plans.

  • Cline · Cline Bot Inc.

    Open-source coding agent for VS Code, JetBrains, Cursor and Windsurf, plus a CLI and desktop app. Free to use with your own API keys or its free models; adds an optional $9.99 ClinePass subscription. No inline autocomplete, and pricing is usage-based unless you take ClinePass.

  • Kilo Code · Kilo Code

    Open-source (MIT) coding agent for VS Code, JetBrains and the terminal with cloud agents and code review. Free platform; you pay for AI usage at provider rates, with your own keys, or via optional Kilo Pass credits. SOC 2 Type I only, so check procurement needs.

  • Replit Agent · Replit

    Browser-based app builder: describe an app and Agent builds, hosts and publishes it. Free Starter plan is limited (Lite build, one published app); paid plans add monthly credits and usage charges. No local editor or CLI, and content is used for model improvement unless you are on Pro and opt out.

  • Lovable · Lovable

    Chat-based builder for web apps and sites, aimed at non-developers and prototypers, with hosting and a database included. Free plan gives 5 build credits a day (30 a month); paid plans are credit tiers priced from $25 a month, shared by all workspace members. The Business plan (from $50 a month) is a flat workspace price, not per seat.

  • Bolt.new · StackBlitz

    Browser-based builder for web and mobile apps with built-in hosting, databases and AI agents. Free plan has 1M tokens a month; Pro adds 10M tokens, custom domains and MCP connectors. Heavy use depends on token allowances, which larger projects burn faster.

  • v0 · Vercel

    Vercel prompt-to-app builder for React/Next.js apps with one-click deploy to Vercel and GitHub sync. Free plan is capped at 7 messages a day; paid plans use a credit allowance per user plus pay-as-you-go credits. Business plan adds training opt-out; SAML SSO is Enterprise only.

  • GitHub Copilot · GitHub

    GitHub's assistant for VS Code, JetBrains, Visual Studio and other editors, plus a CLI and cloud agent on GitHub. Suits teams already on GitHub; it has the widest model menu here, but Pro, Pro+ and Max plans meter agent and chat use in AI credits, and individual plans may be used for training unless you opt out.

  • JetBrains AI Assistant (with Junie) · JetBrains

    AI chat, completion and the Junie coding agent built into IntelliJ-based IDEs, with a separate Junie CLI. Best for developers who stay in JetBrains tools; paid tiers include a small monthly credit allowance (the free tier is 3 credits) and extra credits cost more.

  • Augment Code · Augment Code

    Context-engine-driven agent for VS Code, JetBrains, Vim and a CLI, now sold mainly through the Cosmos team platform. Plans are flat team prices (up to 50 seats) with included usage, there is no free plan, and inline completions ended for non-Enterprise plans in March 2026.

Suggest a change

You’ll sign in or create a free account to send it. We’ll keep what you typed.

Related comparisons