All AI coding tools

Eight assistants, profiled from their vendors' published data — pricing tiers, free-tier terms, platforms — checked October 22, 2026. Six have standing free tiers and are queued for our hands-on benchmark; two are data-only for now, and each profile says which and why.

Free tier · test scheduled

GitHub Copilot

AI pair programming as an add-on for the editor you already use.

Free: Yes — 2,000 completions/mo + AI Credits allowance
Entry paid: $10/mo (Pro)

Free tier · test scheduled

Cursor

An AI-first editor — a VS Code fork — built around agent workflows.

Free: Yes — limited Agent/Chat requests (limits not published)
Entry paid: $8/mo (Plus, Grok models only)

Free tier · test scheduled

Windsurf (Devin Desktop)

The editor formerly known as Windsurf — renamed Devin Desktop by Cognition in June 2026.

Free: Yes — unlimited completions + a lightweight agent allowance
Entry paid: $20/mo (Pro)

Free tier · test scheduled

Kiro

AWS's spec-driven agentic IDE — you write the spec, the agent builds to it.

Free: Yes — 50 credits/mo, incl. Claude Sonnet 4.5
Entry paid: $20/mo (Pro, 1,000 credits)

Free tier · test scheduled

OpenAI Codex

OpenAI's coding agent, bundled into ChatGPT plans instead of sold separately.

Free: Yes — included with ChatGPT Free (limits not published)
Entry paid: $8/mo (ChatGPT Go) · $20/mo (Plus)

Free tier · test scheduled

Replit (Agent)

The zero-install option: browser IDE, agent and hosting in one web app.

Free: Yes — daily Agent credits; publish 1 app
Entry paid: ≈$20/mo (Core; price moves often)

Data profile only

Claude Code

Anthropic's terminal-first coding agent, bundled with Claude subscriptions.

Free: No free tier
Entry paid: $20/mo (Claude Pro)

Data profile only

Tabnine

The privacy-first assistant, built for private deployment inside your own walls.

Free: No free tier (14-day trial, no card)
Entry paid: $39/seat/mo (annual)

How these profiles are built

Every profile starts from the data layer: pricing and free-tier terms read from the vendor's official pricing page (linked and dated on each profile), re-checked monthly because this category reprices often. Hands-on benchmark results are added to the same profile as the runs complete — the method is published on the How We Test page, and no profile claims hands-on experience it does not have.