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, 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
| Feature | ⠿ | ⠿ | ⠿ | ⠿ | ⠿ | ⠿ | ⠿ | ⠿ | ⠿ | ⠿ | ⠿ | ⠿ | ⠿ | ⠿ | ⠿ | ⠿ | ⠿ | ⠿ | ⠿ | ⠿ | ⠿ | ⠿ | ⠿ | ⠿ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
⠿
Price
|
Doesn't apply
|
Doesn't apply
|
||||||||||||||||||||||
|
⠿
Product type
|
||||||||||||||||||||||||
|
⠿
Free plan
|
|
|||||||||||||||||||||||
|
⠿
Free plan limits
|
Doesn't apply
|
Doesn't apply
|
No Aider caps; you pay your model provider
|
Doesn't apply
|
No plan caps; you pay for inference used
|
Doesn't apply
|
||||||||||||||||||
|
⠿
Top individual plan
|
$200/month
|
Doesn't apply
|
Doesn't apply
|
|||||||||||||||||||||
|
⠿
Team plan per user
|
$22.80/user/month
|
Doesn't apply
|
Doesn't apply
|
Doesn't apply
|
Doesn't apply
|
|||||||||||||||||||
|
⠿
Pricing model
|
Subscription with rolling usage limits
|
|||||||||||||||||||||||
|
⠿
Models offered
|
OpenAI, Anthropic, Google, DeepSeek
|
Google Gemini, Anthropic Claude, OpenAI GPT-OSS
|
Anthropic, OpenAI, Moonshot (Kimi)
|
Not disclosed; Lovable picks the model
|
Not disclosed; Bolt picks the model
|
|||||||||||||||||||
|
⠿
Model choice
|
||||||||||||||||||||||||
|
⠿
Bring your own API key
|
|
|
|
|
|
|
|
|||||||||||||||||
|
⠿
Code completion
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|||||||||||
|
⠿
Chat in editor
|
|
|
||||||||||||||||||||||
|
⠿
Agent mode
|
|
|||||||||||||||||||||||
|
⠿
Terminal command line
|
|
|
|
|
|
|
||||||||||||||||||
|
⠿
Background cloud agents
|
|
|
|
|
|
|
||||||||||||||||||
|
⠿
Codebase context
|
|
|
||||||||||||||||||||||
|
⠿
MCP support
|
|
|
||||||||||||||||||||||
|
⠿
Pull request review
|
|
|
|
|
|
|
|
|
||||||||||||||||
|
⠿
Open source
|
|
|
|
|
|
|
|
|
|
|||||||||||||||
|
⠿
Editors supported
|
Own editor (VS Code-based); also CLI, web
|
Own editor (VS Code-based)
|
Own editor (web app)
|
|||||||||||||||||||||
|
⠿
Operating systems
|
Web, Windows, macOS, Linux
|
Web
|
Windows, macOS, Linux
|
Windows, macOS, Linux
|
||||||||||||||||||||
|
⠿
Trains on your code
|
Opt-out
|
No by default
|
No by default
|
|||||||||||||||||||||
|
⠿
Zero data retention option
|
|
|
|
|
|
|
|
|
|
|
|
|
||||||||||||
|
⠿
SOC 2 report
|
|
|
|
|
|
|
|
|
|
|
||||||||||||||
|
⠿
Single sign on
|
|
|
|
|||||||||||||||||||||
|
⠿
Self hosted option
|
|
|
|
|
|
|
|
Why these features matter
-
Price ($/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
Related comparisons
-
AI search enginesAI search tools read the web for you and answer in a few paragraphs with links, instead of giving you ten blue links. This grid compares popular AI answer engines, search engines that now add AI answers, and the developer APIs that power AI apps, on what decides a choice: what is free, what paid plans cost, whether answers cite sources, how deep the research goes, who runs the search index, and what happens to your queries. The real trade-offs are convenience against privacy, and speed against how much you can trust and verify an answer.
-
AI meeting assistantsAI meeting assistants listen to your calls, write the transcript, summarise the discussion and pull out action items so you can pay attention instead of typing. This grid compares popular tools side by side on what decides a choice: how they capture the meeting (a visible bot, a quiet device recording, or the meeting platform itself), what the free plan covers, what paid plans cost per person, and how your meeting content is protected. The real trade-offs are convenience against privacy, and a cheap personal tool against a platform-wide one your company can control.
-
AI chatbotsAI chatbots now do much more than answer questions: they search the web, write reports, create images, talk, remember you and carry out tasks. This grid compares popular chatbots side by side on what decides a choice: what you get free, what each paid plan costs, which models and tools are included, and how your chats are treated. The real trade-off is capability against price and privacy: the strongest features sit on higher-priced plans, and many chatbots use your conversations to improve their models unless you opt out.
-
AI voice generatorsAI voice generators turn text into natural speech and can clone or design voices. The market splits three ways: developer platforms sold by the character, creator apps sold by the month, and open-weights models you run yourself for free. This grid compares popular products side by side on what decides a choice: price and allowance, languages and voices, cloning and emotion control, speed for live conversation, commercial rights and consent safeguards. The real trade-offs are quality and polish against cost, and convenience against control.
-
AI image generatorsAI image generators turn a text prompt or a reference picture into a finished image. This grid compares popular tools side by side on what decides a choice: what you can do for free, what the paid plans really include, which model powers each one, whether it edits and keeps characters consistent, and what rights you get to use the results commercially. The real trade-offs are quality and control against price, and ease of use against how open and legally safe the output is.
-
AI video generatorsAI video tools turn a prompt, a picture or a script into a finished clip, and the field splits into three kinds: general text-to-video models, avatar presenters that read your script, and AI editors that cut and polish footage you already have. This grid compares popular tools side by side on what decides a choice: what is free, what the paid plans really include, how long and sharp the clips are, whether they come with sound, and what rights you get. The real trade-offs are quality against credits (video burns credits fast) and creative control against ease of use.