Free tool · Table
AI Coding Assistant Comparison (2026)
Every major AI coding tool by price, billing model, form, and features: Cursor, GitHub Copilot, Claude Code, Cline, Aider, Zed, JetBrains Junie, Replit, Amazon Q Developer, Augment Code, Gemini Code Assist and Google Antigravity. Filter by tool, billing, or open-source. Some prices re-read on the vendor's own page 2026-11-02; the other 32, last read as far back as 2026-09-03, are named under the table.
What each tool costs to start: its free tier, then its cheapest paid plan.
Cursorfrom $8/mo
Free · Plus: Cursor's own models only · Cursor, read 23 October 2026
GitHub Copilotfrom $10/mo
Free · Pro · GitHub, read 23 October 2026
Claude Codefrom $20/mo
No free tier in the table · via Claude Pro · Anthropic, read 23 October 2026
Clineyour own key
Open-source / BYO-key ($0) · no priced plan; you pay the model provider for your own key · Cline, read 23 October 2026
Aideryour own key
Open-source / BYO-key ($0) · no priced plan; you pay the model provider for your own key · Aider, read 31 October 2026
Zedfrom $10/mo
Personal (Free) · Pro · Zed, read 23 October 2026
JetBrains Juniefrom $10/mo
AI Free · AI Pro · JetBrains, read 31 October 2026
Replitfrom $20/mo
Starter (Free) · Core · Replit, read 31 October 2026 (free tier read 3 September 2026)
Amazon Q Developerfrom $19/user/mo
Free · Pro · Amazon, read 23 October 2026 (free tier read 31 October 2026)
Augment Codefrom $20/mo
No free tier in the table · Standard · Augment Code, read 23 October 2026
Gemini Code Assistfrom $19/user/mo
No free tier in the table · Standard, yearly commitment · Google, read 23 October 2026
Google Antigravity$0
Individuals (Free) · no paid plan in the table · Google, read 2 November 2026
US-dollar prices per month, as each vendor lists them; a price that needs a yearly commitment is marked. Cursor, JetBrains Junie and Replit also list a lower price when paid yearly (see the table). Each was read on the vendor's own page on the date shown. This page compares prices and plans, not benchmark scores such as unit-test pass rates.
All, Any billing. 33 of 33 plans listed.
- AiderOpen-source / BYO-keyFreefree/BYO-keyCLIopen-source
Terminal pair programmer, edits + auto-commits to your git repo, repo map, 100+ languages, OSS
- Models: Any LLM (Claude, GPT, DeepSeek, local)
- Best for: Terminal-first devs wanting free, model-agnostic pair programming
- Amazon Q DeveloperFreeFreeusage/creditsextension
50 agentic requests/mo (Q&A chat, agentic coding), IDE plugins + CLI, latest Claude models, AWS Console Q&A, 1,000 lines/mo of Java upgrade transformation
- Models: Amazon-managed (latest Claude models)
- Best for: AWS devs trying agentic coding free
- ClineOpen-source / BYO-keyFreefree/BYO-keyextensionopen-source
Autonomous agent (plan/act), codebase context, MCP, terminal+browser, Apache-2.0
- Models: 30+ providers incl. local (Ollama/LM Studio)
- Best for: Full control + BYO key, no platform markup
- CursorFreeFreesubscriptionIDE
Agent and Chat with limited usage, no card
- Models: Cursor's own models, limited
- Best for: Trying Cursor / light use
- GitHub CopilotFreeFreeusage/creditsextension
2,000 completions/mo, limited chat and agent usage, CLI, MCP
- Models: Claude Haiku 4.5, GPT-5 mini
- Best for: Casual / student use in your editor
- Google (Antigravity)Individuals (Free)FreesubscriptionIDE
Agent-first IDE: plan/execute/verify across editor+terminal+browser; unlimited tab completions and command requests; basic weekly rate limits. Google AI Pro and Ultra raise the limits and add Claude Sonnet/Opus 5.5 (on Pro: paid, non-trial plans only)
- Models: Gemini 3.8 Flash. Google's page marks Claude Sonnet 4.6, Claude Opus 4.6 and GPT-OSS-120b for removal on 2 November 2026
- Best for: Google's agent-first IDE, free with no subscription
- JetBrains (AI / Junie)AI FreeFreeusage/creditsIDE
Unlimited AI completion in JetBrains IDEs, 3 monthly AI credits (no rollover); not in IntelliJ IDEA without Ultimate or PyCharm without Pro, nor Android Studio
- Models: JetBrains completion model + own providers/keys
- Best for: Basic in-IDE AI for JetBrains users
- ReplitStarter (Free)Freeusage/creditsweb
Free daily agent usage, 1 live published project, built-in database, 1 background task
- Models: Claude (Replit Agent) + frontier
- Best for: Trying Replit Agent without a card
- ZedPersonal (Free)Freefree/BYO-keyIDEopen-source
No Zed edit predictions (Pro only; use Copilot or a local model), unlimited BYO-key AI and external agents, fast native editor, MCP
- Models: BYO key or external agents (Claude Code)
- Best for: Fast native editor with BYO-key AI
- CursorPlus$8/mosubscriptionIDE
Agent at fixed settings, Grok Chat/Voice/Imagine/Build and the Grok API; no Auto, cloud agents, Bugbot, third-party models or BYOK; $80/yr
- Models: Cursor's own models only (Grok 4.7, 4.6, 4.5, Composer 2.5)
- Best for: Cheap agent use on Cursor's own models
- GitHub CopilotPro$10/mousage/creditsextension
Unlimited completions, agent mode, cloud agent, ~$15 credits, MCP
- Models: Claude, GPT-5, Gemini (picker)
- Best for: Individual devs in VS Code / JetBrains
- JetBrains (AI / Junie)AI Pro$10/mousage/creditsIDE
Junie, Claude Agent, Codex, Gemini; unlimited AI completion; 10 monthly AI credits (1 credit = USD 1.00, no rollover), top-ups; $10/mo or $100/yr personal
- Models: OpenAI, Anthropic, Gemini, xAI models + Junie
- Best for: JetBrains devs wanting Junie
- ZedPro$10/mousage/creditsIDEopen-source
Unlimited edit predictions, $5 hosted credits, overage at API+10%
- Models: Zed-hosted + BYO key
- Best for: Hosted models without managing keys
- Amazon Q DeveloperPro$19/seatper-seatextension
Higher limits, Java/.NET transforms, AWS integration, security scans, MCP
- Models: Amazon-managed (Claude on Bedrock)
- Best for: AWS teams modernizing codebases
- GitHub CopilotBusiness$19/seatper-seatextension
Org policy, IP indemnity, agent mode, 1,900 AI credits/user (~$19), MCP
- Models: Claude, GPT-5, Gemini (org-managed)
- Best for: Teams already on GitHub
- Google (Gemini Code Assist)Standard$19/seatper-seatextension
Unlimited completions, chat, agent, GCP integration, codebase context; $19/user with a yearly commitment, $22.80 month-to-month
- Models: Gemini 2.5 / 3 family
- Best for: Teams building on Google Cloud
- Anthropic (Claude Code)via Claude Pro$20/mosubscriptionCLI agent
Agentic terminal coding, full codebase context, MCP, subagents, hooks, plan mode
- Models: Claude Sonnet 5.5 + Opus 5.5
- Best for: Most individual Claude Code users
- Augment CodeStandard$20/mousage/creditsextension
Flat $20/mo, no per-seat charge, up to 50 seats; $20/mo of usage included, then LLM at provider list price + a 40% fee
- Models: Frontier (Claude, GPT, Gemini)
- Best for: Small teams trying Augment before Business
- ReplitCore$20/mousage/creditsweb
$20/mo toward more powerful models, up to 30 hours of Free Mode chat, up to 60 Free Mode projects, unlimited workspaces; $18/mo if billed annually
- Models: Claude (Replit Agent) + frontier
- Best for: Build + ship apps from the browser
- CursorPremium$30/mousage/creditsIDE
4× Plus usage, cloud agents and automations, Bugbot, Origin code hosting, Grok Bot; third-party models billed from prepaid credit; $300/yr
- Models: Cursor's models + third-party (Claude, GPT, Gemini) at API list price
- Best for: Most working developers
- CursorTeams$30/seatper-seatIDE
Premium, Super or Ultra seats at $30/$100/$200 per user/mo; admin, SSO, team rules; $0.25/M-token Cursor Token Rate on third-party models
- Models: Cursor's models + third-party at API list price
- Best for: Teams needing admin + shared context
- JetBrains (AI / Junie)AI Ultimate$30/mousage/creditsIDE
Junie, Claude Agent, Codex, Gemini; unlimited AI completion; 35 monthly AI credits, 5 bonus AI credits (1 credit = USD 1.00, no rollover), top-ups; $30/mo or $300/yr personal
- Models: OpenAI, Anthropic, Gemini, xAI models + Junie
- Best for: Heavy JetBrains + Junie users
- ZedBusiness$30/seatper-seatIDEopen-source
Org AI policies, data governance, RBAC, unlimited predictions, BYOK
- Models: BYO key (no extra charge)
- Best for: Teams needing AI governance
- GitHub CopilotPro+$39/mousage/creditsextension
Unlimited completions, 7,000 AI credits/mo (~$70), premium models
- Models: All premium models incl. Opus
- Best for: Heavy users wanting all premium models
- GitHub CopilotEnterprise$39/seatper-seatextension
Everything in Business + 2,000 more AI credits/user, ~$39 credits in total, priority access to new models and features; for GitHub Enterprise Cloud organisations
- Models: Claude, GPT-5, Gemini (org-managed)
- Best for: Large orgs standardized on GitHub
- Google (Gemini Code Assist)Enterprise$45/seatper-seatextension
Full GCP integration, admin controls, codebase customization, security; $45/user with a yearly commitment, $54 month-to-month
- Models: Gemini 3 family
- Best for: Enterprises on GCP
- Anthropic (Claude Code)via Claude Max 5×$100/mosubscriptionCLI agent
5× Pro usage, priority access at high traffic times, $100/mo API credits, agentic + MCP
- Models: Sonnet 5.5 + Opus 5.5 (more Opus)
- Best for: Daily heavy Claude Code users
- Augment CodeBusiness$100/mousage/creditsextension
Flat $100/mo, no per-seat charge, up to 50 seats; $100/mo of usage included, then LLM at provider list price + a 40% fee
- Models: Frontier (Claude, GPT, Gemini)
- Best for: Teams on large codebases (flat price)
- CursorSuper$100/mousage/creditsIDE
15× Plus usage, priority model access at peak times; $1,000/yr
- Models: Cursor's models + third-party at API list price
- Best for: Heavy individual agent users
- GitHub CopilotMax$100/mousage/creditsextension
Unlimited completions, 20,000 AI credits/mo (~$200), MCP
- Models: All premium models
- Best for: Heaviest individual Copilot users
- ReplitPro$100/mousage/creditsweb
$100/mo toward most powerful models, up to 15 collaborators, database rollback up to 28 days; $90/mo if billed annually
- Models: Claude (Replit Agent) + frontier
- Best for: Shipping several apps a month from the browser
- Anthropic (Claude Code)via Claude Max 20×$200/mosubscriptionCLI agent
20× Pro usage, priority access, $200/mo API credits, parallel agents
- Models: Sonnet 5.5 + Opus 5.5
- Best for: Power users running agents all day
- CursorUltra$200/mousage/creditsIDE
50× Plus usage, earliest access to new features; $2,000/yr
- Models: Cursor's models + third-party, earliest access to new ones
- Best for: All-day agentic coding
USD, individual/standard tier unless marked /seat. 1 of 33 plans were re-read on the vendor's own pricing page 2026-11-02; the rest were last read earlier, as far back as 2026-09-03 (Cursor (6 plans), GitHub Copilot (6 plans), Anthropic (Claude Code) (3 plans), Cline, Aider, Zed (3 plans), JetBrains (AI / Junie) (3 plans), Replit (3 plans), Amazon Q Developer (2 plans), Augment Code (2 plans) and Google (Gemini Code Assist) (2 plans)). AI coding prices move monthly. Most “subscription” prices are now a FLOOR, not a cap: Cursor, Replit, Augment, Zed Pro, JetBrains, Copilot and others meter agent/premium-model usage against an included credit allowance, so heavy users pay overages. “Open-source” = the editor/agent license (Cline, Zed), not the AI models (all proprietary); Claude Code is source-available. Confirm on the vendor's page before buying.
Want the verdict, not just the table?
The table lays out every plan; these head-to-heads add the opinionated pick, which to choose for your workflow, and why.
Frequently asked
Do I need a separate subscription for Claude Code?
No. Claude Code has no standalone subscription; it's included on every paid Claude plan. Claude Pro ($20/mo, or $200 billed annually) covers most individuals with Sonnet 5.5 and Opus 5.5 in the terminal, IDE, web, and desktop. Max 5× ($100/mo) and Max 20× ($200/mo) raise the shared usage limits to 5× and 20× Pro's for heavy or all-day agentic use. You can alternatively pay-as-you-go via the Anthropic API, but the subscription plans are the value path for most developers.
What changed with GitHub Copilot pricing in 2026?
On June 1, 2026, every Copilot plan moved to usage-based billing. Each plan (Free, Pro $10, Business $19/user, Pro+ $39, Enterprise $39/user, Max $100) now includes a monthly allowance of GitHub AI Credits (1 credit = $0.01) that fund premium model/agent requests; once exhausted, paid plans can buy more. Code completions and next-edit suggestions stay unlimited and don't consume credits on any paid plan. So the monthly price is now a floor: heavy agent/premium-model users can incur overages.
Which AI coding tools are actually open source vs. just free to use?
Genuinely open source: Cline (Apache-2.0 agent, BYO key), Aider (Apache-2.0 terminal pair programmer that commits to your git repo) and the Zed editor (GPL/AGPL, though Zed's hosted AI credits are a paid add-on). 'Free to use' but closed source: Cursor Free, GitHub Copilot Free, JetBrains AI Free, Replit's Starter tier, Amazon Q Free and Google Antigravity for Individuals are all $0 but proprietary. Claude Code's CLI is source-available (you can read it) but not OSI open-source, and the underlying models are closed everywhere.
What's the cheapest way to get an agentic coding tool in 2026?
For $0: Cline (open-source, BYO API key; you only pay model providers, often pennies per task), Google Antigravity (free for individuals, with Gemini 3.8 Flash. Google's page marks Claude Sonnet 4.6, Claude Opus 4.6 and GPT-OSS-120b for removal on 2 November 2026), Copilot Free, or Replit's free Starter tier. Cursor now starts at $8/mo (Plus, Cursor's own models only), with Premium at $30/mo for third-party models at API price. For a flat ~$20/mo with hosted models included: Claude Pro (Claude Code), or Replit Core ($20), or Augment Standard ($20, one flat price for a team of up to 50). Watch for usage/credit overages: most $20 plans meter agent and premium-model usage beyond an included allowance.
How do Replit Agent, Cursor and Augment Code compare on price?
Replit lists Core at $20/mo and Pro at $100/mo, read 31 October 2026; Starter (Free), read 3 September 2026. Cursor lists Free, Plus at $8/mo, Premium at $30/mo, Teams at $30/user/mo, Super at $100/mo and Ultra at $200/mo, read 23 October 2026. Augment Code lists Standard at $20/mo and Business at $100/mo, read 23 October 2026. Replit Agent comes with each Replit plan above rather than as a separate line in the table. Cursor's Plus runs Cursor's own models only (Grok 4.7, 4.6, 4.5, Composer 2.5); Premium runs Cursor's models and third-party (Claude, GPT, Gemini) at API list price. On paid plans the table marks usage/credits, the monthly price buys an allowance, and heavy use can cost more.
Cursor vs GitHub Copilot vs Cline: what does each cost?
Cursor lists Free, Plus at $8/mo, Premium at $30/mo, Teams at $30/user/mo, Super at $100/mo and Ultra at $200/mo, read 23 October 2026. GitHub Copilot: GitHub lists Business at $19/user/mo and Enterprise at $39/user/mo, read 31 October 2026; Free, Pro at $10/mo, Pro+ at $39/mo and Max at $100/mo, read 23 October 2026. Cline lists Open-source / BYO-key ($0), read 23 October 2026. Cursor's Plus runs Cursor's own models only (Grok 4.7, 4.6, 4.5, Composer 2.5); Premium runs Cursor's models and third-party (Claude, GPT, Gemini) at API list price. Cline itself costs nothing; you bring your own API key and pay that model provider directly. On paid plans the table marks usage/credits, the monthly price buys an allowance, and heavy use can cost more.
Which GitHub Copilot plan includes 20,000 AI credits a month?
Max, at $100/mo (GitHub, read 23 October 2026), includes 20,000 GitHub AI Credits a month, worth about $200 at 1 credit = $0.01. Other Copilot plans: Pro at $10/mo includes about $15 of credits, read 23 October 2026; Business at $19/user/mo includes 1,900 AI credits per user (~$19), read 31 October 2026; Pro+ at $39/mo includes 7,000 AI credits (~$70), read 23 October 2026; Enterprise at $39/user/mo includes about $39 of credits, read 31 October 2026. GitHub lists unlimited completions on Pro, Pro+ and Max.
What happened to Windsurf?
Windsurf is now part of Devin, Cognition's coding agent. windsurf.com redirects to devin.ai and there is no separate Windsurf pricing page any more, so the plans this table used to list can no longer be bought under that name. The figures it carried could no longer be checked against any Windsurf page, so they have been removed rather than left to age. If you were choosing Windsurf for its agentic editor, the closest picks still on sale here are Cursor and Cline.
What happened to Tabnine?
Tricentis announced on 30 July 2026 that it had acquired Tabnine, and tabnine.com and its pricing page now redirect to tricentis.com with no public price. So Tabnine is a sales-led enterprise purchase now, and this table no longer lists its plans. If you wanted it for privacy controls, compare Copilot Business, Zed Business, or the open-source, bring-your-own-key agents (Cline, Aider).