# ToolTier.ai full tier data > Generated 2026-11-20 from the same data as the site. Money never changes a tool's tier. Prices on the existing lists were last checked Oct 18, 2026. AI Code Review prices were checked Oct 19, 2026. AI Workflow prices were checked Oct 26, 2026. MCP Servers prices and limits were checked Nov 9, 2026. Factory Droid prices were checked Nov 2, 2026. ## App Builders Best overall: Lovable. Best for fast previews: Bolt.new. ### S · Lovable Most polished output for non-coders, with hosting and a backend included. Apps can now call GPT-Live, Claude, Gemini, Perplexity and Firecrawl right from the builder, and Growth tools plan SEO and Google or Meta ad campaigns from the same chat. You can now import an app from Replit, Bolt, Base44, v0 or a ZIP (first build of your first import is free). Nov 6: app AI features can use GPT Image 2.6 Flare (faster) and GPT Image 2.6 Sunburst (detailed), including short animated GIFs and transparent PNG or WebP; they use credits and are not available with EU inference. Nov 4: Dreaming tidies project memory and AGENTS.md rules in the background on paid plans, does not change app code, and uses no credits. Nov 5: you can report a problem to Lovable from the AI client connected to the Lovable MCP server (free). New app and chat connectors for Fortnox, Mailchimp, and Mailchimp Transactional. Apps can use Topaz Starlight Fast 2 (topazlabs/starlight-fast-2) to restore blurry or low-res clips to 1080p or 4K; it runs in the background, can take hours, uses credits, and admins enable TopazLabs in Connectors first. Nov 6: a Connectors Activity tab shows each connector request's status and timing, with Fix with Lovable on failures; people outside an internally published app's audience can request access; ActiveCampaign and Supermetrics connectors; app AI features can use GPT-6.1 Terra. Nov 7: Enterprise workspaces can require admin approval before a project turns on Lovable's built-in backend. Nov 8: a PayPal connector for checkouts, refunds, and order details. Nov 9: Jira and Mailjet app and chat connectors, the Sentry connector now also reports your app's errors and performance data, and you can connect Resend by signing in with your Resend account instead of pasting an API key. Nov 11: Automations (Free, Pro, and Business) run recurring work you ask for in Chats, like a morning check of your published sites, and each run counts as chat usage; workspace and project invitations must now be accepted by hand. Nov 12: Deel and Retool connectors, and paid workspaces alert admins by email when daily run usage rises sharply (usage is not blocked). Nov 15: an Intercom connector lets apps search and reply to support conversations, manage contacts and tickets, and search and publish help center articles. Add it from Connectors, or ask Lovable in a project to connect it. Nov 16: on projects using the built-in backend, a draft has its own backend filled with example data, so you can test a change that stores new information without touching the live app. Accepting the draft applies the change to the live database before you publish and leaves the test data behind. Chats can also be archived, and Business and Enterprise admins can set SSO sessions to 30 days or Indefinite. Nov 14: on sign up, log in, or reset with email and password, Lovable checks the password against known data leaks and asks you to replace a leaked one. If your password is found at log in, Lovable logs you out on all devices and asks for a reset, and connected apps and tools need to reconnect. Nov 16: an Attio connector lets apps search, create, and update people, companies, and deals, add records to lists, and attach notes and tasks, with per-user access so each person using your published app connects their own Attio workspace. Nov 17: AI clients connected to the Lovable MCP server, such as ChatGPT and Claude, can create a draft of your project and build in it (standard build usage, uses credits). Business and Enterprise admins can require IP allowlists on every workspace API key; keys without one stop working until an allowlist is added. Enterprise editors can request disabled connectors from admins. Nov 19: Adyen and Airwallex connectors let apps take card and local payments, share payment links, and handle refunds, subscriptions, or invoices. - Price: Free (5 credits/day) · Pro from $25/mo - Best for: Polished apps for non-coders - Site: https://lovable.dev - ToolTier: https://tooltier.ai/tools/lovable.html ### S · Bolt.new Fastest prompt-to-preview, flexible stacks. Review security before shipping. Forge preview ended Oct 14; Lite keeps Forge-only access. - Price: Free · Lite $9/mo (Forge only) · Pro from $25/mo · Teams $30/member - Best for: Fastest prompt-to-preview - Site: https://bolt.new - ToolTier: https://tooltier.ai/tools/bolt-new.html ### A · Replit Full browser IDE, agent, DB and deploys in one place. OpenAI is now the default partner powering Replit Agent, though you can still pick Claude and other models. Enterprise Bring Your Own Cloud (AWS, Azure, Google Cloud) is in preview. The new Monitoring Agent investigates production alerts, tests a fix and emails you a summary; auto-publishing fixes is opt-in. Eligible top-up customers can now keep published apps running at zero credits up to an overage limit, and Chroma (ChromaDB) agreed to join Replit on Oct 23. New Cloud Agents (Pro and Enterprise) let teammates outside engineering describe a change, have it tested in a cloud sandbox, and send it as a PR with video for engineers to approve. Nov 13: Agent can create Google Ads campaigns (Agentic Ads). Managed accounts need Replit Pro, a personal Workspace, and auto-reload, and you approve spend before ads run. Agentic commerce checkout uses Stripe Link and needs explicit approval. Performance Agent scans for slowdowns on a paid plan if you have edit access. Enterprise can share with individual Viewers. Microsoft Fabric apps get richer CRUD. Nov 16: the Microsoft Fabric integration is generally available. Build apps with Replit Agent on governed data and deploy them into your organization's Fabric tenant. Nov 17: Replit Missions coordinates a swarm of agents toward an outcome you define, within a spending limit and approval rules you set. An independent AI judge checks results against your success criteria, and work stops if the budget runs out first. The launch post does not list pricing or plan availability. - Price: Free · Core $20/mo · Pro $100/mo - Best for: Browser IDE, agent, database, and deploys - Site: https://replit.com - ToolTier: https://tooltier.ai/tools/replit.html ### A · v0 Best-in-class React/shadcn UI. Strongest on the Vercel stack. ChatGPT Business plans now work in v0 alongside Plus and Pro (Nov 10), so eligible responses from supported OpenAI models count toward your ChatGPT plan instead of v0 credits. Ask v0 to run a security review (paid plans, uses v0 credits) and it checks your changes for issues like missing auth checks, injection, and SSRF, with a severity and suggested fix for each. - Price: Free · paid from $30/user/mo - Best for: React and shadcn UI on Vercel - Site: https://v0.app - ToolTier: https://tooltier.ai/tools/v0.html ### B · Base44 All-in-one builder with built-in data and auth, aimed at internal tools. Apps created from Oct 18 have a database size cap set by plan (200 MB per app on Free, 2 GB on Starter, up to 50 GB on Business), so check the limit before you pick a plan for a data-heavy app. From Nov 11, connectors (Gmail, Slack, Google Calendar and more), backend functions, and payments through Base44 Payments or Stripe work on every plan, including Free; workflows, custom OpenAPI integrations, and MCP connections still need Builder or higher. Apps can also take PayPal payments with no Base44 fee, and Hooks (rolling out) let you allow or block an app action before it runs (Nov 10). Nov 17: GPT-6.2 Sol and GPT-6.2 Astra are live in Base44, Base 1 (Base44's own model) gets effort levels from Low to Max in the AI chat, and apps can generate music through the AI gateway. - Price: Free · paid from $16/mo (annual) - Best for: Internal tools with data and auth - Site: https://base44.com - ToolTier: https://tooltier.ai/tools/base44.html ## Deploy & Hosting Best overall: Vercel. Best for static sites: Netlify. ### S · Vercel The default home for Next.js and v0 apps. Git push, then live. Sandbox Drives (persistent, forkable storage for agents) and WebSockets in Functions are now GA. Pro teams can now set a spend budget from the CLI with vercel budgets and pause production at 100%. A plain root Dockerfile now deploys on the Container runtime (beta, Active CPU pricing). Vercel CI (beta, Oct 28) runs Turborepo tasks tagged ci on every push for $0.0035 per CPU minute on Pro. Node.js 26 LTS is now the default runtime, and built-in fetch uses HTTP/2. Data Cache is moving to Runtime Cache, which bills reads and writes that used to be free (Hobby teams migrate Nov 29). Builds on every plan now block known malicious npm package versions before and during install. Security Review (public beta, Pro and Enterprise, Nov 3) checks every GitHub push for vulnerabilities and can open a fix PR with Vercel Agent; reviews are free until Nov 10, then billed per token. Schedules, the successor to Cron Jobs, is in public beta (Nov 5): recurring or one-time jobs in vercel.json or at runtime, targeting a private Function, an HTTP path, or a Queue topic, with enable, disable, and run on demand and no redeploy. Pro and Enterprise start at $5 per 1M runs and $10 per 1M creations; Hobby includes 500 creations and 5,000 runs a month. Existing Cron Jobs still work. AI Gateway added Tencent Hy4 at 50% off through Dec 31 (Nov 3), more ZDR providers for Kimi K3.1 Pro (Nov 4), and google/gemini-omni-1.2-flash for text-to-video (Nov 5). Token Pass credit now applies automatically to included model usage for Token Pass subscribers on Pro teams (Nov 6). Tracing is GA on all plans (Nov 6): KQL span search, no setup on new Next.js 16.5 projects, traces kept up to 14 days, pricing unchanged from the beta. AI Gateway adds DeepSeek Search and Fetch for any tool-calling model via one key, no DeepSeek account needed (AI SDK 6.0.321+ on v6 or 7.0.160+ on v7). Nov 6: vercel deploy --delete-project-after 1d sets a new project to be deleted automatically (durations 1h, 1d, 1w, 2w, 30d). It only applies when the deploy creates the project; existing projects get a warning and no change. Remove the expiration with vercel project keep . Needs Vercel CLI v65.12.0 or later. Nov 7: AI Gateway serves DeepSeek V4.1 Flash 1017 Ultrafast (deepseek/deepseek-v4.1-flash-1017-ultrafast) through Fireworks, upwards of 1,000 tokens per second, with a 1M-token context, in public preview with no waitroom or session time limit. AI Gateway passes through provider pricing with no markup. Nov 9: build disk space on Basic and Standard machines doubled from 32 GB to 64 GB on every plan at no extra charge, Sandbox snapshots are created up to 10x faster (median under 0.4s), and AI Gateway added Claude Fable 5.2 and Meta's Muse Ember. Nov 10: AI Gateway added Gemini 4 Carbon (google/gemini-4-carbon) at 50% off through Nov 30, and Speed Insights and Web Analytics now support custom environments. Nov 13: Vercel Sandbox starts up to 4x faster outside iad1 through regional image caching. In Seoul, startup went from about 3.5s to 1.05s. Also Nov 13: Token Pass now includes $150 of monthly tokens (up from $80) for the same $30 per team per month, for featured open-weight models on AI Gateway such as Kimi K3.1 Pro, GLM 5.3, and DeepSeek V4.1 Flash. It is an Early Access add-on for Pro teams with no rollover. The build cache limit rose to 5 GB at no extra charge, and Security Review no longer needs a linked Vercel project. Nov 15: Qwen4-Max is on AI Gateway (one API key, automatic fallbacks, spend tracking, and traces). Nov 13: Daemons (background workers) can send OpenTelemetry traces to Vercel Tracing, and Parallel Decisions is on AI Gateway for free through Nov 23 (web-grounded decisions with cited sources). Nov 16: Spend Management supports budgets for single projects and products alongside team budgets. A project budget can pause that project's production deployments when reached without pausing others. Alerts at 50%, 75%, and 100%. Also manageable with vercel billing budgets in the Vercel CLI. Included at no extra cost for Pro and Enterprise teams on Flexible Commitment plans. AI Gateway Private Inference lets enterprises run fine-tuned and self-hosted models next to catalog models with the same API key and logs. Nov 17: new Pro and Enterprise teams no longer include a Standard build slot, so Standard builds are usage-based ($0.014 per build minute on Pro, covered by the monthly usage credit first). A new Ignored Build Step preset skips preview builds for branches without an open pull request. Vercel Blob can delete files automatically with ttlDays (1 to 730 days), and GPT-6.2 Astra and Sol are on AI Gateway. eve 1.0, Vercel's open-source framework for production agents, is generally available. Nov 18: Vercel Board (experimental, all plans) is a shared message board where agents and people coordinate tasks, with channel permissions and two-way sync to Slack and GitHub through Vercel Connect. Gemini 4 Neon is on AI Gateway, Parallel web search in fast mode is free on AI Gateway and eve through Jan 31, 2027, cold reads from Vercel Drives are up to 6x faster, and instant deployments now cover static sites with CSS, images, and fonts. Nov 19: vercel billing in the CLI shows your billing overview, lists and downloads invoices, and previews upcoming charges, with --json output for scripts and agents. - Price: Hobby free · Pro $20/mo (+$20/dev seat) - Best for: Next.js and v0 apps - Site: https://vercel.com - ToolTier: https://tooltier.ai/tools/vercel.html ### S · Netlify Great for static and full-stack sites, with a generous free tier and an AI Gateway. netlify.toml now has a JSON schema (Nov 4), so your editor or agent can catch config mistakes before a deploy, and Netlify MCP shows recent deploys as a card in ChatGPT and other MCP Apps clients (Nov 3). Heads-up: for the Nov 3 Next.js security release, upgrade next to 16.4.5 or 15.5.29 and redeploy; the auto-installed Netlify Next.js adapter 5.16.6 covers the Middleware cookie case. Netlify Server (Early Access, Nov 10) runs your backend as a long-lived Node.js server that scales to zero, holds WebSockets, and runs Express, Hono, Fastify, or Koa apps as-is. It is free during Early Access on credit-based plans (Next.js, Astro, and Nuxt not supported yet). Gemini 4 Carbon is in Netlify's AI Gateway and Agent Runners. Heads-up: Visual Editor is deprecated as of Nov 10 and reaches end of life Feb 8, 2027. Nov 13: Agent Runners can read review comments on pull requests they created, so you can ask one to address the comments on the PR. Nov 16: on projects connected to public repos, Deploy Previews from forks opened by people outside your Netlify team now wait for a team member to approve them by default. The sensitive variable policy is renamed the untrusted deploys policy and moved to Project configuration, Developer settings, Continuous deployment. Projects that chose another option keep it. Nov 17: Agent Runners can use more than 150 connectors (Linear, Notion, Snowflake, Stripe, and more) on credit plans and Enterprise plans with credits, and each person's connections stay private to them. Netlify CLI 27.18.0 stores login tokens in your OS keychain instead of a plain text file (local Netlify MCP needs @netlify/mcp 1.22.1 or later). GPT-6.2 Astra and Sol are in AI Gateway and Agent Runners. Nov 18: a redesigned Netlify experience is rolling out, starting with most new users (others can join a waitlist). Every way of working (agent prompts, Git, CLI, Netlify Drop) lands in the same app, each change becomes a version with a preview, and settings use plain language. Netlify also flagged seven React Router vulnerabilities; update if your site uses React Router 6, 7, or 8 (including Remix 2 and Hydrogen). - Price: Free · Personal $9/mo · Pro $20/mo - Best for: Static and full-stack sites - Site: https://www.netlify.com - ToolTier: https://tooltier.ai/tools/netlify.html ### A · Railway One-click backends, workers and databases. Feels like magic. Heads-up: on Oct 21 Railway disclosed that an attacker may have accessed customer environment variables, some decrypted, and told all users to rotate secrets stored there. It also invalidated all API tokens. Builds are back on every plan, and its preliminary report puts possible exposure at up to 1.85% of workspaces. Nov 6: railway trace CLI is in preview for everyone (dashboard Traces needs Priority Boarding), HA Postgres, MySQL, and Redis can regenerate passwords without Priority Boarding, and admins can review and revoke workspace tokens. Nov 13: Cloud Agent tasks hand a coding task to a Railway cloud agent through MCP, railway ca task run, or the public API. Tasks run in the background and support follow-ups and webhooks. A fresh agent creates a billed VM. The railway ca thread view was reworked, and Agent Connectors are generally available with no Priority Boarding required. Nov 17: Linked billing with the Claude Platform lets you pay for Claude through your Claude organization inside Railway, with your existing spend limits and no API token. - Price: $5 trial credit · Hobby $5/mo · Pro $20/mo - Best for: Backends, workers, and databases - Site: https://railway.com - ToolTier: https://tooltier.ai/tools/railway.html ### A · Cloudflare Workers Edge compute with a huge free tier, at very low cost per request. Nov 13: you can set spending limits for Workers and Durable Objects (Billing > Spend limits, or the cf CLI) that block usage at a dollar cap, or email alerts that let apps keep running. Reporting lags, so recorded spend can pass the limit. - Price: Free · Paid from $5/mo - Best for: Low-cost edge compute - Site: https://workers.cloudflare.com - ToolTier: https://tooltier.ai/tools/cloudflare-workers.html ### B · DigitalOcean App Platform is the easy path; Droplets give you a cheap VPS if you don't mind running servers yourself. - Price: App Platform: free static sites · apps from $5/mo - Best for: Simple app hosting or a VPS - Site: https://www.digitalocean.com - ToolTier: https://tooltier.ai/tools/digitalocean.html ### B · Render Heroku-style PaaS for services, cron jobs and Postgres. Render Sandboxes (public beta, Nov 11) give agents isolated, ephemeral compute up to 8 CPU and 16 GB RAM, with outbound network controls and snapshots, managed from the Render CLI or the TypeScript and Python SDKs. From Nov 18, previews cover every PR in a GitHub stacked-PR chain. Nov 18: fine-grained API keys are GA; new keys are scoped to one workspace with per-area permissions (services and deploys, environment variables, workflows, sandboxes, logs). - Price: Free tier · usage-based instances - Best for: Services, cron jobs, and Postgres - Site: https://render.com - ToolTier: https://tooltier.ai/tools/render.html ## Backend, DB & Auth Best overall: Supabase. Best for reactive TypeScript: Convex. ### S · Supabase Postgres, auth, storage and edge functions. The vibe-coder default. Stripe Data Pipeline can now sync your Stripe data straight into your Supabase database. Coding agents can now run scheduled production checks (errors, security, slow queries) through ready-made prompts and a read-only logs tool. Supabase Compute (private alpha, waitlist, us-west-2 only) runs agents, long jobs and Dockerfile services inside your project. Heads-up: from Oct 30, new tables in public aren't exposed to the Data API until you add an explicit GRANT, so tell your AI builder to add grants with RLS. Supabase CLI v3 (Nov 4) is a breaking change: it targets your local stack by default, asks before changing a hosted project, and removes deprecated commands, so update CI before upgrading or pin v2. Correlated Logs (beta, Nov 10) links Studio log events by request, trace, and user ID into one timeline, and the Supabase MCP query_logs tool accepts the same IDs. Account Security now offers backup sign-in (Nov 13): add a password if you only use GitHub or another OAuth provider, and get 10 single-use MFA recovery codes. Nov 17: register any OIDC provider for third-party auth from the Dashboard by adding its issuer URL on the Third-Party Auth page. Custom issuers added through the Management API can be managed or deleted there too. Nov 18: Supabase is one of the new GitHub-verified connectors for GitHub Copilot (public preview), so Copilot can check your schema before it writes a migration. - Price: Free (2 projects) · Pro from $25/mo - Best for: Postgres, auth, storage, and edge functions - Site: https://supabase.com - ToolTier: https://tooltier.ai/tools/supabase.html ### A · Convex Reactive TypeScript backend that AI agents write really well. Convex 1.51.0 (Nov 18): Node actions can run with 2048 MiB of memory (the default stays 512 MiB), billed for action compute at the memory size you set. - Price: Free · Pro $25/dev/mo - Best for: Reactive TypeScript backends - Site: https://www.convex.dev - ToolTier: https://tooltier.ai/tools/convex.html ### A · Firebase Google's battle-tested BaaS, good for mobile and realtime apps. Nov 17: an official Firebase plugin for Codex brings Firebase expertise and tooling into Codex sessions. Nov 18: Firebase AI Logic supports Gemini 4 Neon (gemini-4-neon) through the Gemini Developer API or the Agent Platform Gemini API, and it needs the pay-as-you-go Blaze plan. Nov 19: Crashlytics for web (public preview) alerts you to new or returning JavaScript errors in Next.js, React, and Angular apps and points to the spot in your code. It is built on Google Cloud Observability and OpenTelemetry. - Price: Spark free · Blaze pay-as-you-go - Best for: Mobile and realtime apps - Site: https://firebase.google.com - ToolTier: https://tooltier.ai/tools/firebase.html ### A · Neon Serverless Postgres with instant branching for every preview. Realtime live SQL queries are in free public beta. Nov 19: Postgres 19 is available on Neon, including the Free plan, the day it reached GA. Postgres 18 stays the default, and Postgres 19 does not support the Data API yet. - Price: Free · usage from $0.106/CU-hr - Best for: Serverless Postgres with branching - Site: https://neon.com - ToolTier: https://tooltier.ai/tools/neon.html ### B · Clerk Drop-in auth UI, the fastest way to add login. - Price: Free (50k MRU/app) · Pro $25/mo ($20/mo annual) - Best for: Drop-in login - Site: https://clerk.com - ToolTier: https://tooltier.ai/tools/clerk.html ## AI Coding IDEs Best overall: Cursor. Best if you already live in VS Code: GitHub Copilot. ### S · Cursor The default AI editor: best agent, best tab, now bundled with cloud agents and code review. Cloud agents can now build live apps (Nov 5): scaffold the web app, set up Postgres if needed, configure auth behind Cursor SSO, provision hosting, run security checks, and publish to a unique link, on all paid plans with cloud agents enabled. They can also build interactive canvases (dashboards, reports) you share by link, and the Origin App Marketplace adds CI, deploy, and review integrations. Heads-up: on Oct 29 malicious copies of Anthropic's Claude Code extension (2.1.312 and 2.1.313) sat in the cache behind Cursor's extension marketplace for about 11 hours, reaching at most 5,000 users. Cursor's Nov 13 incident update says it started with an access key Cursor had issued to Fireworks: the attacker copied coding agent traces (mostly from 2025, from sessions not in Privacy Mode), and credentials left in a few of them led to some internal tools, support data, and archived non-production code. Fewer than 0.01% of customers had API credentials exposed, affected customers were contacted directly, inference was moved off that vendor, and the last attacker activity Cursor saw was blocked on Nov 1. If you installed either version, follow Cursor's security notice, since uninstalling alone may not be enough. Voice chat (Nov 6) is a realtime two-way call with your agents in the Agents Window, the IDE, on the web, and in Cursor for iOS. It runs on Grok Voice, uses zero data retention with Privacy Mode on, and is separate from dictation. Projects is now multiplayer (beta for all users, Nov 10): invite teammates into a Project with a shared task board and shared context (docs, diagrams, specs), and teammates' agents message each other to sort out overlapping work. Nov 18: Gemini 4 Neon is in Cursor at $3 / $15 per 1M tokens; Cursor says it scores 63.7% on CursorBench 4.1 at default effort, up from 57.3% for Gemini 4 Hydrogen. - Price: Free · Plus $8/mo (Grok models only) · Premium $30/mo · Super $100/mo · Ultra $200/mo - Best for: Default AI editor - Site: https://cursor.com - ToolTier: https://tooltier.ai/tools/cursor.html ### A · GitHub Copilot Lives in the VS Code or JetBrains you already use, with almost every frontier model on the menu. GPT-6.1 Terra, a cheaper model for agentic and terminal work, is GA on Pro and up (Oct 26), and assisted permissions, where a model auto-approves only clearly safe tool requests, are GA in the CLI, the Copilot app and VS Code. Copilot Fusion, which picks and combines models for you at Standard, High or Max effort, is GA on all plans (Oct 28). Copilot Memory, which remembers your preferences and repo conventions across sessions, is GA on paid plans. Copilot is now also an agent in JetBrains Air (Nov 3), with cloud tasks billed to your Copilot plan, and it is in public preview inside Xcode's built-in coding assistant from Xcode 27.3 beta (Nov 4). @GitHub in Slack and Teams is generally available (Nov 6): investigate bugs, create issues, implement changes, and open pull requests from the conversation. Nov 6: manage Copilot code review settings through the REST and GraphQL APIs from enterprise policy down to repositories; reviews and comments have explicit attribution fields; the review overview comment is more compact; agent sessions show AI credits consumed per review; Balanced effort reviews use three reviewer models with another model combining findings; failed or timed-out reviews retry once automatically. Available on Copilot Pro, Pro+, Max, Business, and Enterprise. The Nov 2 weekly release (posted Nov 6): set up Agent Merge from a pull request in the Copilot app so Copilot merges when ready, and it stays enabled while required checks or rules are pending; Copilot CLI /settings opens a unified, searchable dashboard for plugins, MCP servers, and more; VS Code 1.145 local automations accept cron expressions and workspace custom agents. Claude Fable 5.2 is GA in Copilot (Nov 9) on Pro+, Max, Business, and Enterprise, in VS Code, Visual Studio, JetBrains, Xcode, Eclipse, the CLI, the coding agent, and github.com. It needs data retention by default, and rollout is gradual. Gemini 4 Carbon is GA in Copilot (Nov 10) on Pro+, Max, Business, and Enterprise, billed at provider list pricing under usage-based billing, with a gradual rollout. Gemini 4 Hydrogen is generally available in GitHub Copilot (Nov 13) for Copilot Pro, Pro+, Max, Business, and Enterprise, billed at provider list pricing under usage-based billing, with a gradual rollout, in VS Code, Visual Studio, Copilot CLI, the coding agent, the Copilot app, github.com, Mobile, JetBrains, Xcode, Eclipse, and the Copilot SDK. GitHub Enterprise Server support in the GitHub Copilot app is generally available on Copilot app 1.2.0 and later. Cloud sessions are not available for GitHub Enterprise Server. Nov 13: GitHub will deprecate Claude Fable 5, Claude Haiku 4.5, Gemini 3.8 Flash, Gemini 4 Argon, Grok 4.6, and Kimi K3 across Copilot on Dec 14. Suggested replacements are Fable 5.2, Haiku 5.5, Gemini 4 Hydrogen, Gemini 4 Carbon, and Grok 4.7 (Kimi K3's is to be announced). Haiku 4.5 stays for individual subscribers on annual plans. Nov 16: Claude Opus 4.8, Opus 5, and GPT-5.6 Terra are deprecated across most Copilot experiences. Suggested replacements are Claude Opus 5.5 and GPT-6.1 Sol or GPT-6 Luna. Opus 4.8 stays for individual subscribers on annual plans. VS Code 1.146 deprecates the Local harness for Copilot agent sessions. Its replacement, the Copilot harness built on the Copilot SDK, has been the default for new sessions since VS Code 1.143 and does not move your files to the cloud. Switch under Session Target and review customizations before February 2027. Nov 17: GPT-6.2 Astra and GPT-6.2 Sol are generally available on Pro+, Max, Business, and Enterprise at provider list pricing (gradual rollout), and Microsoft's MAI Code 2 (Pro and up) and MAI Code 2 Flash (every plan, including Free) are in the model picker. Browser use (public preview, off by default) lets Copilot work in your signed-in Chrome or Edge through the Copilot extension, in the Copilot app, CLI, VS Code, and JetBrains. Copilot code review adds Adaptive effort (public preview), which picks Lite, Balanced, or Max per pull request. The Copilot app supports Azure DevOps repos in public preview, Copilot Fusion reaches github.com, Visual Studio, and the Mobile betas, and Copilot Evals (public preview) tests your skills, agents, and MCP tools. Nov 18: Gemini 4 Neon is GA on Pro+, Max, Business, and Enterprise at provider list pricing (gradual rollout). Eight more GitHub-verified connectors, including Supabase, Webflow, Wix, and Buildkite, are in public preview on all plans, and team customizations (GA, Business and Enterprise) let team maintainers set approved plugins as team defaults. - Price: Free · Pro $10/mo · Pro+ $39/mo · Max $100/mo - Best for: Stay in VS Code or JetBrains - Site: https://github.com/features/copilot - ToolTier: https://tooltier.ai/tools/github-copilot.html ### A · Google Antigravity Google's agent-first IDE. Strong free tier, best fit if you build on Gemini. Gemini 4 Argon is rolling out in the desktop app and CLI for Google AI Pro and Ultra subscribers. Heads-up: Claude Sonnet 4.6, Claude Opus 4.6 and GPT-OSS-120b leave Antigravity on Nov 18 (moved from Nov 2). They're the only non-Gemini models on the free tier, so free users will be down to Gemini 3.8 Flash; Claude Sonnet 5.5 and Opus 5.5 stay on paid Google AI Pro and Ultra. Gemini 4 Carbon is in the Antigravity app, CLI, and IDE extensions for Google AI Ultra subscribers (Nov 10), and /swarm (preview, app and CLI) runs a coordinator, parallel workers in separate git worktrees, and verifier agents on a shared message board. Google warns swarms use quota much faster than a normal chat. Gemini 4 Hydrogen is rolling out to paid Google AI Pro and Ultra subscribers (Nov 12), with a new xhigh thinking level. A new Orchestrator option hands planning to Carbon or Argon and edits and tests to Hydrogen inside one task; Google says it reached near-Carbon success on Terminal-Bench 4.1 with 24% less quota. Orchestrator (Carbon) and (Argon) are on Ultra, and Orchestrator (Argon) is on paid Pro. Nov 18: Gemini 4 Neon is rolling out on Google AI Pro, Ultra, and Gemini Enterprise, and becomes the default model if you have not picked one; Orchestrator (Neon) plans with Neon and implements with Hydrogen. Antigravity App 2.33.0 (Nov 17) connects to remote Linux machines over SSH, shows live GitHub pull request status, and opens /swarm to business and enterprise accounts where admins allow it. - Price: Free · higher limits via Google AI Pro/Ultra (plan price not listed on the Antigravity pricing page) - Best for: Building on Gemini - Site: https://antigravity.google - ToolTier: https://tooltier.ai/tools/google-antigravity.html ### B · Kiro AWS's spec-driven IDE. Plans before it codes, which is great for bigger features and slow for quick fixes. A local command sandbox can auto-approve shell commands for unattended runs, and Approve for me (Oct 29) lets Kiro approve routine actions in V3 sessions while your own allow, ask and deny rules still decide first. Heads-up (Nov 3): V3 is now the default CLI harness, and the Classic interface, the CLI desktop app, and inline shell autocomplete are retired (run kiro-cli --v2 to keep V2). Enterprise admins can pool credits at $20 per seat for 500 shared monthly credits (Nov 4), and PreCompact and PostCompact hooks plus session credits in /usage arrived Nov 5. Nov 10: IDE 1.4.154 brings Approve for me to chat, with a permission mode menu (Supervised, Accept file changes, Approve for me); Grok 4.7 is available with experimental support on Pro and above; and Enterprise Management (preview, new us-east-1 profiles) applies one AWS console policy across the IDE, CLI, Web, and Crew. Kiro Mobile for Android (Nov 12) lets you start, follow, and steer Kiro cloud sessions from your phone on Pro, Pro+, Pro Max, or Power; you still review and merge in your Git provider. Nov 16: Kiro Web adds a terminal so you can run builds and tests in your session's workspace. In V3 sessions a PreToolUse hook can rewrite a tool call's inputs, and a new PermissionRequest hook can allow or deny a call that would otherwise wait on you. A deny from any hook wins. Nov 17: Enterprise admins can require sandboxing for commands and local stdio MCP servers in Kiro IDE and CLI, and developers cannot turn a required sandbox off. Nov 18: Kiro IDE installs powers and skills from GitLab, can answer permission prompts with a Permission Request Hook script, and signs in once to your organization's HTTP MCP servers through your identity provider. Nov 19: Kiro Crew 0.13.0 turns on conductor mode (formerly Ultra Mode) in every standard build, and you can answer a waiting session from the sidebar or your own chat app. Enterprise organizations can also connect Kiro cloud sessions to private resources in an Amazon VPC (preview, us-east-1). - Price: Free (50 credits) · Pro $20/mo · Pro+ $40/mo · Pro Max $100/mo · Power $200/mo - Best for: Spec-driven larger features - Site: https://kiro.dev - ToolTier: https://tooltier.ai/tools/kiro.html ### B · Zed The fastest editor around. Bring your own agent or keys; AI is an add-on, not the point. Zed 1.27.0 (Nov 4) styles AI commit messages on your repo's 3 most recent commits, removes agent checkpoints and the Restore Checkpoint button (reject edits or use Git to undo), and requires macOS 12 Monterey or later. Zed 1.29.1 (Nov 18) adds a Git Panel branch mode that lists every file changed since a base branch, a bookmark picker, and Claude Fable 5.2 for Anthropic BYOK users; 1.29.2 adds an official Snap package for Linux. - Price: Personal free · Pro $10/mo (incl. $5 tokens) · Business $30/seat/mo - Best for: Editor speed, bring your own keys - Site: https://zed.dev - ToolTier: https://tooltier.ai/tools/zed.html ## Coding Agents Best overall: Claude Code. Best for bulk autonomous work: OpenAI Codex. ### S · Claude Code The best all-round coding agent. Reads big codebases well and plans before it edits. Long idle sessions now auto-compact before the prompt cache expires, and Code Review (automatic PR reviews) is GA on Team and Enterprise plans. With Opus 5.5 it leads Artificial Analysis's new Coding Agent Index v2.0 at 61.7. A new setting can block file writes outside your project folders, useful for unattended runs. Fast mode on Opus 4.8 is removed Nov 30, so switch to Opus 5.5. Version 2.1.319 (Nov 6) backgrounds MCP tasks, adds permissions.denyInsteadOfPrompting so unattended turns are not stuck on a permission prompt, and adds /claude-api latency-optimize. Version 2.1.321 (Nov 9) makes Claude Fable 5.2 the default Fable model, and saved Fable 5.1 picks move to it (/model claude-fable-5-1 switches back). Fable 5.2 is on Pro, Max, Ultra, Team, and Enterprise, and its fast mode works in Claude Code. Anthropic is giving eligible paid plans extra Fable usage during launch week. Version 2.1.323 (Nov 12) changes don't ask again so an allow rule that looks like it holds a secret, or would be saved to a settings.local.json that git tracks, lasts for the session only. That addresses the secrets-in-settings report from early November. It also adds Code Mode, an experimental opt-in where Claude writes JavaScript to call its tools. Version 2.1.325 (Nov 13) fixes a security issue in how zstd-compressed responses are decoded, fixes subagents on their own model being moved to the plan-mode model under opusplan or haiku, and fixes compaction on many third-party gateways and Foundry. Nov 13: Projects (public beta on Pro and Max) got a more proactive coordinator that answers in the project chat and reports on parallel threads, plus /btw and /fork, thread reminders, and read-only thread sharing. Running several threads uses plan limits faster. Desktop also gained custom themes (mods). Effective Nov 12, 2026, Anthropic's Supported Regions Policy makes Claude Code, Claude.ai, Cowork, the API, and Claude models via cloud platforms and resellers available only in listed countries: mainland China, Hong Kong, and Macau are not listed, the policy covers entities headquartered there or majority-owned or controlled from there, and Anthropic describes it as clarifying enforcement of existing rules. Nov 16: Claude Code on desktop supports iPhone Duo in the iOS simulator in public beta. Run your app on Duo next to the conversation, and Claude can fold and unfold the device to test each layout. Claude Code 2.1.326 also lets Code Mode run with agent teams enabled. Claude Code 2.1.327 (Nov 17) adds claude mcp add-json with stdin input so tokens stay off the command line, asks before /install-github-app changes a repository, and fixes stopping Remote Control in worktree mode deleting a running session's git-ignored files such as .env. Claude Code 2.1.328 (Nov 18) adds auto mode for Opus 4.6 and Sonnet 4.6 on Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, and the Claude apps gateway, lets mcp_tool hooks block an action when the hook call fails, and fixes zsh commands with words starting with = stopping with a not found error. - Price: Included with Claude Pro $20/mo ($17/mo annual) · Max from $100/mo - Best for: All-round agent for big codebases - Site: https://claude.com/product/claude-code - ToolTier: https://tooltier.ai/tools/claude-code.html ### S · OpenAI Codex Most autonomous for bulk work: CLI, IDE, cloud tasks and GitHub reviews on one ChatGPT plan. Codex CLI 0.167 adds an agent command center (codex agents --no-daemon) with unread-result markers, backend switching from the session picker that keeps drafts, and local image previews while composing. 0.163 lets you steer a running turn with a follow-up message, 0.164 adds reusable /presets slots, 0.165 adds a built-in Google Vertex AI provider, and 0.166 adds codex doctor --network-only for connection checks. GPT-6.1 Terra (Oct 26) is in Codex on Plus, Pro, Enterprise and Edu, and OpenAI says the same allowance covers more tasks with it than with GPT-6.1 Sol. Heads-up: from December, Plus, Pro and Business plans share one token-based allowance across ChatGPT and Codex, and OpenAI hasn't said how big it is. OpenAI will acquire Pierre (Nov 4), whose Trees and Diffs already power Codex file browsing and diffs, to deepen Git tooling after the deal closes. Nov 17: GPT-6.2 Astra (for the hardest projects) and GPT-6.2 Sol (everyday coding) are in Codex. OpenAI says GPT-6.2 Sol completes more tasks on the same paid plan than GPT-6.1 Sol. Pro $200 adds Ultrafast mode for Sol, and Pro $500 for both models. Codex CLI 0.171.0 (Nov 19) turns on the TUI workspace by default, with document, image, and subagent transcript previews, makes GPT-6.2 Sol the default catalog model, and adds codex exec --remote for noninteractive sessions on an existing app server. - Price: Free · Go $8/mo · Plus $20/mo · Pro $100, $200 or $500/mo - Best for: Bulk autonomous work - Site: https://openai.com/codex - ToolTier: https://tooltier.ai/tools/openai-codex.html ### A · Devin Cognition's agent, now merged with Windsurf. Desktop editor plus cloud agents you can assign like a teammate. Fusion mode pairs a frontier lead model with a cheaper sidekick: with Opus 5.5 and GPT-6 Luna it scored 68 on Artificial Analysis's v1.5 Coding Agent Index, about 2 points above Claude Code with Opus 5.5 at 31% lower cost per task. The tougher Index v2.0 (Oct 23) doesn't list Fusion yet. Nov 17: Devin Bots are persistent agents with their own memory and tools that own a goal, run several Devin sessions in parallel, and bring you only the decisions that need you. They are on Max ($200/mo) and Teams, billed to the Bot's creator, and Teams can set an on-demand dollar cap per Bot. Nov 19: Devin Security Threats is a managed index of newly disclosed vulnerabilities, such as NGINX2Root and Java4Shell. Pick repositories to scan, findings are ranked against your threat model, and Devin opens pull requests for the fixes. Teams can add their own threats, and Auto-triage scans for each new one automatically. - Price: Free · Pro $20/mo · Max $200/mo · Teams $80/mo + $40/dev seat - Best for: Assign work like a teammate - Site: https://devin.ai - ToolTier: https://tooltier.ai/tools/devin.html ### A · OpenCode Open-source terminal agent that runs any model and logs in with your existing Copilot or ChatGPT plan, and now your Claude Code login too. DeepSeek V4.1 Flash and GLM 5.3 Flash are free to use in it, and MiniMax M3.1 Flash is free for three days from Oct 19. Heads-up: on Oct 17 OpenCode disclosed a breach of its hosted Console that exposed saved provider API keys for 1.4% of Console users (all notified by email). The local agent wasn't affected. If you got the email, rotate your keys. OpenCode says refunds for fraudulent charges are underway, and OpenAI says it is refunding API credits drawn in the attack. OpenCode 2.2.6 (Nov 6): opt-in shared MCP connections with pool: true so projects with the same setup share one connection (fewer processes, faster start); opencode run -w or --worktree= starts a scripted session in a new git worktree; opencode run --archived keeps scripted and CI sessions out of the inbox and session lists; opencode run waits for background shells, subagents, and image jobs before exiting (a job that never exits, like a dev server, keeps the run open, so set a CI timeout). GUI plugins can add themes and code-block actions, and phones and tablets get a touch composer dock. OpenCode 2.2.7 (Nov 10) adds GitHub Copilot Auto in the model picker, so Copilot's router picks the model at the Auto discount, and remote MCP logins that rotate refresh tokens stay signed in. Breaking for SDK users: ImageResponse.image is removed in @opencode/ai (read response.images[0]). OpenCode 2.3.0 (Nov 13) runs subagents in the background by default, so you keep working while several report back, and the TUI folds each run of tool calls into one collapsible row. Nov 16: OpenCode Browse is an MIT-licensed MCP server and Chromium extension (v0.1.0). Agents open background tabs in your own Chrome, Edge, Brave, Arc, or other Chromium browser with your logins, and hand the tab back to you for logins, 2FA, or payments. Works with OpenCode, Claude Code, Cursor, Codex, Zed, and other MCP clients. - Price: Free and open source · you pay your model provider (no pricing page) - Best for: Open source, any model - Site: https://opencode.ai - ToolTier: https://tooltier.ai/tools/opencode.html ### A · Factory Droid Model-independent coding agent from Factory: a desktop app for macOS and Windows, a terminal UI, and an SDK, all on the same harness. Droid 1.0 (Oct 29) makes programmatic tool calling the default, so one model request can run many tool calls. In Factory's own Terminal-Bench 4 runs (Oct 23-28) it beat Claude Code, Codex, Cursor, OpenCode and Devin on the same models at lower cost. That is a vendor benchmark, not ours. No free plan is listed. BYOK is free up to an allowance, and a free open-weight model pool (Droid Core) kicks in after standard usage runs out. Nov 20: CLI and Desktop 1.16.0 lower the five-hour and weekly usage limits on most paid plans, with monthly limits unchanged, and plans below Enterprise can no longer turn off session contents sync. - Price: Pro $20/mo · Plus $100/mo · Max $200/mo · Teams $60/mo + $40/seat - Best for: Model-independent agent, any frontier model - Site: https://factory.com - ToolTier: https://tooltier.ai/tools/factory-droid.html ### A · Muse Code Meta's terminal coding agent. Muse Wonder is on every plan; Muse Wonder Full is only on Power and Maximum. - Price: Everyday $5/mo · High $15/mo · Power $50/mo · Maximum $200/mo - Best for: Meta terminal agent - Site: https://dev.meta.ai/products/muse-code - ToolTier: https://tooltier.ai/tools/muse-code.html ### B · Cline Open-source VS Code agent with full control and BYO keys. Costs can climb on big models. Cloud Agents (beta) now run tasks in parallel cloud sandboxes from the browser or Cline Desktop and hand back a branch and PR. - Price: Free · pay for inference at cost or bring your own key - Best for: Open-source VS Code agent, bring your own keys - Site: https://cline.bot - ToolTier: https://tooltier.ai/tools/cline.html ## MCP Servers Best overall: GitHub MCP Server. Best for current docs: Context7. Best for browser testing: Playwright MCP. ### S · GitHub MCP Server GitHub's official server for repos, issues, pull requests, Actions runs, and code security alerts. Use the hosted remote server at api.githubcopilot.com/mcp/ with OAuth or a personal access token, or run it locally. Turn on only the toolsets you need to keep the agent's context small, add /readonly to the URL for read-only tools, and use lockdown mode to hold back public-repo content from people without push access (a best-effort guard against prompt injection, not a permission boundary). It documents setup for Claude Code, Codex, Cursor, OpenCode, Zed, and Copilot. MIT licensed. v2.1.0 shipped Nov 3. v2.2.0 (Nov 16) replaces server instructions with filtered MCP skills, adds public agent automation tools, and lets secret scanning alert tools optionally hide secrets. - Price: Open source (MIT) · no separate fee listed · uses your GitHub account - Best for: Repos, issues, PRs, and Actions from your agent - Site: https://github.com/github/github-mcp-server - ToolTier: https://tooltier.ai/tools/github-mcp-server.html ### S · Context7 Pulls current, version-specific library docs and code examples into your agent's context, so it stops guessing at APIs from old training data. Runs as an MCP server at mcp.context7.com/mcp or as the ctx7 CLI plus a skill, and npx ctx7 setup configures Cursor, Claude Code, or OpenCode. Made by Upstash. Free is 1,000 API calls a month; after that Free users are blocked, with 20 bonus calls a day until the month resets. Pro users are never blocked and pay $5 per extra 1,000 calls. - Price: Free (1,000 API calls/mo) · Pro $10/seat/mo (2,000 calls/seat, then $5 per 1,000) - Best for: Current library docs in context - Site: https://context7.com - ToolTier: https://tooltier.ai/tools/context7.html ### S · Playwright MCP Microsoft's browser automation server. The agent drives Chrome, Firefox, WebKit, or Edge through structured accessibility snapshots instead of screenshots, so no vision model is needed. Adding it is one line, for example claude mcp add playwright npx @playwright/mcp@latest or codex mcp add. Its own README says coding agents may do better with the more token-efficient Playwright CLI plus skills, and keeps MCP for long, stateful browser loops. v0.0.84 (Oct 31) adds isolated sessions in one browser and URL parameter redaction. - Price: Free and open source (Apache-2.0) - Best for: Cross-browser automation and testing - Site: https://github.com/microsoft/playwright-mcp - ToolTier: https://tooltier.ai/tools/playwright-mcp.html ### A · Chrome DevTools MCP The Chrome DevTools team's server for debugging a live Chrome: performance traces with insights, network requests, screenshots, and console messages with source-mapped stack traces. It also ships a chrome-devtools CLI and skills for accessibility, LCP, and memory-leak debugging, plus a --slim mode with fewer tools. Chrome and Chrome for Testing only. Google collects usage statistics by default (opt out with --no-usage-statistics), and performance tools can send trace URLs to the CrUX API (turn that off with --no-performance-crux). v1.12.0 shipped Oct 22. - Price: Free and open source (Apache-2.0) - Best for: Debugging and profiling in Chrome - Site: https://github.com/ChromeDevTools/chrome-devtools-mcp - ToolTier: https://tooltier.ai/tools/chrome-devtools-mcp.html ### A · Supabase MCP Lets your agent list tables, run SQL, apply migrations, query logs, read security and performance advisors, generate TypeScript types, and deploy Edge Functions on your Supabase project. Hosted at mcp.supabase.com/mcp with OAuth, so no token is needed. Supabase warns about prompt injection from data in your tables: scope it to one project with project_ref, add read_only=true, limit feature groups, keep tool approval on, and never hand it to your end users. Branching tools need a paid plan. - Price: Open source (Apache-2.0) · no separate fee listed · uses your Supabase plan - Best for: Agent access to your Supabase project - Site: https://supabase.com/docs/guides/getting-started/mcp - ToolTier: https://tooltier.ai/tools/supabase-mcp.html ### A · Sentry MCP Sentry's remote server for coding agents: search errors, traces, and logs, triage issues, and read Sentry docs from Claude Code, Cursor, or VS Code. Connect with OAuth at mcp.sentry.dev/mcp and scope the URL to one org or project, which Sentry recommends. A Claude Code plugin adds a Sentry subagent. If you run the stdio version yourself, its natural-language search tools need your own LLM provider key. Sentry's free Developer plan (one user) includes MCP access. - Price: Developer free (1 user, MCP access) · Team $26/mo billed annually - Best for: Fixing production errors from your agent - Site: https://mcp.sentry.dev - ToolTier: https://tooltier.ai/tools/sentry-mcp.html ### B · Figma MCP Gives your agent design context from Figma (variables, components, layout) to generate code from a selected frame, and can write native content back to the canvas (beta, free for now, usage-based later). Use the remote server at mcp.figma.com/mcp. The catch is limits: Starter plans and View or Collab seats get up to 20 read tool calls a month, while Full or Dev seats on Professional get up to 200 a day. Only clients in Figma's MCP catalog can connect, including Claude Code, Codex, Cursor, and VS Code. Nov 17: admins can keep an allowlist of approved OAuth apps, including MCP clients like Cursor and Claude Code, and review app requests. - Price: Starter free (20 tool calls/mo) · Professional Dev seat $12/mo (200 calls/day) - Best for: Design context for code, on a paid seat - Site: https://help.figma.com/hc/en-us/articles/32132100833559-Guide-to-the-Figma-MCP-server - ToolTier: https://tooltier.ai/tools/figma-mcp.html ## AI Workflow Automation Best overall: n8n. Best visual, no server: Make. ### S · n8n The builder default for AI workflows. You pay per full workflow execution, not per step, and every cloud plan includes JS and Python code steps plus AI Agent, MCP, and human-approval nodes. Community Edition is free to self-host. Cloud Starter is €20/mo billed annually. Heads-up: n8n 3.0 (beta Oct 27, stable early December) has breaking changes, drops npm and npx self-hosting for Docker, and can't be rolled back, so run the Migration Report first. - Price: Community Edition free (self-host) · Starter €20/mo annual · Pro €50/mo annual - Best for: Self-host or per-execution AI workflows - Site: https://n8n.io - ToolTier: https://tooltier.ai/tools/n8n.html ### A · Make Best visual canvas when you do not want a server. Make's pricing page lists 3,500+ apps, and routers do not spend credits. Most other module actions cost 1 credit, so a long flow costs more than one n8n execution. Maia (AI agents) and an MCP server are on the platform. Free is 1,000 credits a month with a 15-minute minimum gap between runs. Core starts at $9/mo for 10,000 credits on Make's comparison page. - Price: Free (1,000 credits/mo) · Core from $9/mo (10,000 credits) - Best for: Visual branching without a server - Site: https://www.make.com - ToolTier: https://tooltier.ai/tools/make.html ### A · Zapier Fastest no-host start, and Zapier's comparison page lists 9,000+ apps. The free plan is 100 tasks a month and two-step Zaps only. Multi-step Zaps start on Professional at $19.99/mo billed annually for 750 tasks. A task is a successful step, so long workflows burn the allowance. Agents and Chatbots are separate add-ons, not part of the task plan. - Price: Free (100 tasks/mo, two-step) · Professional from $19.99/mo annual (750 tasks) - Best for: Largest app catalog, no hosting - Site: https://zapier.com - ToolTier: https://tooltier.ai/tools/zapier.html ### B · Activepieces Open-source flows, agents, tables, and MCP, on Activepieces cloud or your own server. A run is one credit no matter how many steps it has. AI steps cost more unless you bring your own key on Plus. Free is 1,000 credits a month with no card. The trade-off versus n8n is a smaller ready-made app catalog. - Price: Free (1,000 credits/mo) · Plus $20/mo · Team $200/mo - Best for: Free cloud tier plus self-host - Site: https://www.activepieces.com - ToolTier: https://tooltier.ai/tools/activepieces.html ## AI Code Review Best overall: Greptile. Best for team PR reviews: CodeRabbit. ### S · Greptile Graph-indexes the repo and reviews pull requests with that context. Starter is free for one active developer: unlimited repos and 50 credits a month. A base review is 1 credit, Plus is 3, and Apex is 10. Pro is $30 per active developer per month, with 50 credits included and extra credits at $1. - Price: Starter free (1 developer, 50 credits/mo) · Pro $30/seat/mo - Best for: Solo builders who want free review credits - Site: https://www.greptile.com - ToolTier: https://tooltier.ai/tools/greptile.html ### S · CodeRabbit Agentic reviews on the pull request, in the CLI, and in the IDE, and it learns from your feedback. The free plan is PR summaries plus reviews in VS Code and the CLI, with a 14-day Advanced trial. Open-source public repos get Team features free. Essentials adds PR reviews at $24 per developer per month billed annually ($30 month-to-month). Review instructions and custom pre-merge checks can now live as Markdown files in a .coderabbit/ folder next to the code they cover, and your existing YAML keeps working (Nov 13). Nov 13: the CodeRabbit API now covers more than 150 product operations (reviews, coding tasks, Triage, security scans, settings, usage), and the same operations are tools on a hosted MCP server at mcp.coderabbit.ai for Claude Code, Codex, and other clients. It is GitHub Cloud only, and the MCP server is in the US region. Nov 17: CodeRabbit Verify (beta, free during the beta) starts your app in an isolated sandbox, uses the pull request's change the way a user would, and reports bugs with reproduction steps, screenshots, and a session recording. Trigger it with @coderabbitai verify or automatically, and save journeys like sign-up or checkout to run on a schedule. GitHub Cloud, GitLab.com, and Bitbucket Cloud. Nov 19: Automatic Approvals has a minimum blocking severity, so with critical it requests changes only for Critical findings and leaves Major and lower as advisory comments (min_blocking_severity in .coderabbit.yaml). Also Nov 19: the Agent Skills your coding agents follow, such as .claude/skills/code-review/SKILL.md at the repository root, are read automatically as review guidelines, and CLI 0.9.6 can export saved findings as Markdown. - Price: Free (summaries; IDE and CLI reviews) · OSS public repos free · Essentials $24/dev/mo annual ($30 monthly) - Best for: Seat-priced PR, CLI, and IDE reviews - Site: https://www.coderabbit.ai - ToolTier: https://tooltier.ai/tools/coderabbit.html ### A · Cursor Bugbot Cursor's reviewer for GitHub pull requests. There is no separate Bugbot subscription: Individual plans use included usage first, then on-demand usage if you turn it on, and Teams bill from on-demand usage. Cursor's pricing page includes Bugbot on Premium ($30/mo) and above, not on Free or Plus, and says the average review costs $1.00–$1.50. - Price: No separate fee · Premium $30/mo and up · average review $1.00–$1.50 - Best for: Already paying for Cursor - Site: https://cursor.com/bugbot - ToolTier: https://tooltier.ai/tools/cursor-bugbot.html ### A · Graphite Agent AI pull-request reviews from Graphite Agent, with suggested fixes on the higher plans. Hobby is free for personal repos and includes limited AI reviews. Starter is $20 per seat per month and Team is $40 per seat per month, both billed annually. PR reviews stay limited until Team, which is unlimited, and Team has a 30-day trial. - Price: Hobby free (limited AI reviews) · Starter $20/seat/mo annual · Team $40/seat/mo annual - Best for: Stacked pull requests plus AI review - Site: https://graphite.com - ToolTier: https://tooltier.ai/tools/graphite-agent.html ### A · Claude Code Review Anthropic's automatic GitHub pull-request review for Team and Enterprise. Several agents read the diff, a verification step filters findings, and comments land inline. A review never approves or blocks the merge. There is no flat per-review price: reviews bill as usage credits, separate from included plan usage. Most reviews finish in about 6–10 minutes, at Quick, Standard, or Deep per repo. On any plan, /code-review runs locally in Claude Code. - Price: Team and Enterprise only · usage credits, no flat per-review price - Best for: Already on Claude Team or Enterprise - Site: https://code.claude.com/docs/en/code-review - ToolTier: https://tooltier.ai/tools/claude-code-review.html ### B · Qodo Agentic pull-request reviews with a rules system, plus Git and IDE integrations. There is no permanent free tier. Every workspace gets a 14-day unlimited trial, then reviews pause until you buy pooled credits at $0.012 each. Packs are 2,500, 5,000, and 20,000 credits, about 18, 36, and 144 reviews a month. A Codex marketplace plugin (Nov 2) brings Qodo's rules and review into Codex sessions. Nov 18: Auto Approval Workflows (beta) approve pull requests that meet your criteria, with guards that keep critical code with a person, and Agent Session Review (research preview) assesses a coding agent's whole session across its PRs. - Price: 14-day trial · then $0.012/credit (2,500 credits is $30) - Best for: Credit-based reviews after a trial - Site: https://www.qodo.ai - ToolTier: https://tooltier.ai/tools/qodo.html ## Design → Code Best overall: Figma Make. Best for React UI: v0. ### S · Figma Make Prompt to working prototype inside Figma, using your own designs and libraries. The designer's default. Can now scaffold a Figma-hosted Payload backend (CMS, database, auth) to take a prototype to a real app. - Price: Starter free (limited AI credits) · Professional Full seat $16/mo - Best for: Prototypes inside Figma - Site: https://www.figma.com/make/ - ToolTier: https://tooltier.ai/tools/figma-make.html ### A · v0 Best React/shadcn UI generator, with one-click deploys to Vercel. ChatGPT Business, Plus, and Pro plans can cover eligible OpenAI-model responses instead of v0 credits (Nov 10). - Price: Free (7 messages/day) · Plus from $30/user/mo · Business $100/user/mo - Best for: React and shadcn UI - Site: https://v0.app - ToolTier: https://tooltier.ai/tools/v0.html ### A · Builder.io Turns Figma into code that uses your real components and repo, not throwaway markup. Agent-Native beta is an open-source framework for agentic apps where the agent and UI share state. - Price: Free (60 credits/mo) · Pro $24/user/mo · Team $40/user/mo - Best for: Your real components and repo - Site: https://www.builder.io - ToolTier: https://tooltier.ai/tools/builder-io.html ### B · Anima Solid Figma-to-React/HTML plugin and playground. Good for one-off handoff. - Price: Free (5 generations) · paid plan prices not shown on pricing page (unverified) · Enterprise from $500/mo annual - Best for: One-off Figma handoff - Site: https://www.animaapp.com - ToolTier: https://tooltier.ai/tools/anima.html ### B · Onlook Open-source (Apache 2.0), local-first visual editor where designers style and build in the real React code with AI instead of a mockup, using your existing design system. Free to download or self-host. The hosted team version adds branching, templates, and SSO with sales-led pricing, so it suits teams with a code-first design workflow more than solo prompt-to-app builders. - Price: Free (open source, desktop app or self-host) · Teams custom pricing - Best for: Open-source visual editor on real code - Site: https://onlook.com - ToolTier: https://tooltier.ai/tools/onlook.html ### B · Locofy Figma to React/Next code with responsive layout tagging. Needs tidy design files. - Price: Pricing could not be verified on Oct 14, 2026 (pricing page did not load) - Best for: Figma to React when the file is tidy - Site: https://www.locofy.ai - ToolTier: https://tooltier.ai/tools/locofy.html ## AI APIs & Models Best overall: Anthropic Claude API. Best for the broadest ecosystem: OpenAI API. ### S · Anthropic Claude API Top models for coding and agents. Sonnet is the default workhorse, Opus for hard problems, Haiku for cheap high-volume calls. Opus 5.5 fast mode is out of research preview, no access request needed. Claude Fable 5.2 (claude-fable-5-2, Nov 9) is Anthropic's most capable generally available model for long agentic coding and reasoning, with a 1M-token context and 128K output, at $8 / $40 per 1M tokens (down from $10 / $50 for Fable 5.1). Optional fast mode is up to 2.5x faster at $16 / $80. It requires 30-day data retention, so it is not available under zero data retention without Anthropic's say-so. Self-hosted Claude Managed Agents (Nov 12) runs the whole Managed Agents service, including agents, sessions, and history, on your own infrastructure; request access through your Anthropic account team. Effective Nov 12, 2026, Anthropic's Supported Regions Policy makes Claude.ai, Claude Code, Cowork, the API, and Claude models via cloud platforms and resellers available only in listed countries: mainland China, Hong Kong, and Macau are not listed, the policy covers entities headquartered there or majority-owned or controlled from there, and Anthropic describes it as clarifying enforcement of existing rules. Nov 17: Linked billing (beta) lets your customers pay for the Claude usage in your app through their own Claude organization. Set billing_policy on each request to choose who pays; customers can set a spend cap or unlink in the Claude Console. It works for organizations that pay Anthropic directly. - Price: Pay per token · Haiku 5.5 $0.10 / $0.50 (prompts up to 100K) · Sonnet 5.5 $2 / $10 · Opus 5.5 $4 / $20 · Fable 5.2 $8 / $40 per 1M tokens - Best for: Coding and agent models - Site: https://claude.com/platform/api - ToolTier: https://tooltier.ai/tools/anthropic-claude-api.html ### S · OpenAI API The broadest ecosystem and tooling, with a cheap tier for everything from tiny to frontier. The Responses API now offers 12-hour prompt caching on GPT-5.6 and later, so shared instructions stay at the cheap cached rate across long gaps. The Decisions API (GA Oct 22) handles fast classify, route and score calls on GPT-6 Luna at $0.10 per 1M input tokens, with no output charge. GPT-6.1 Terra (Oct 26) is the new mid-price option for computer use and everyday coding. GPT-6.2 Astra ($8 / $40, cached input $0.40) and GPT-6.2 Sol ($2 / $10, same as GPT-6.1 Sol) arrived Nov 17 on the Responses API and Chat Completions; tool calling needs the Responses API, and a migration guide covers changes to reasoning preservation and the instructions field. A background completion window (public beta) cuts token rates 30% for two hours or 40% for eight hours. Nov 19: GPT-Live-1.1 (gpt-live-1.1) improves pronunciation, accent consistency, and transcription in multilingual voice sessions, and a standby option pauses inference while a WebRTC session is idle. - Price: Pay per token · GPT-6.2 Astra $8 / $40 · GPT-6.2 Sol $2 / $10 · GPT-6.1 Terra $1 / $5 · GPT-6 Luna $0.10 / $0.50 per 1M tokens - Best for: Broadest ecosystem - Site: https://platform.openai.com - ToolTier: https://tooltier.ai/tools/openai-api.html ### A · Google Gemini API Most generous free tier and great price-to-performance on Flash. Computer Use, for agents that operate a browser or desktop, is GA (Oct 30). On Vercel AI Gateway, google/gemini-omni-1.2-flash does text-to-video (Nov 5). Heads-up: from Dec 1, gemini-2.5-pro calls route to Gemini 3.8 Flash and gemini-2.5-flash calls to Gemini 3.5 Flash-Lite, billed at their rates, so update your model string first. Gemini 4 Carbon (gemini-4-carbon, GA Nov 10) is Google's strongest reasoning model for long agentic coding, with a 1M-token context and low, medium, or high thinking levels, on the paid tier only. It is $2 / $10 per 1M tokens through Nov 30, then $4 / $20. Gemini Decision 1 (gemini-decision-1, Nov 11) answers yes or no, multiple-choice, and rubric questions about text, images, audio, video, or PDFs through the new Decisions API with zero output tokens, so it is a cheap fit for routing, policy checks, and ranking. It is $0.10 per 1M input tokens on the paid tier and free on the free tier. Gemini 4 Hydrogen (gemini-4-hydrogen, GA Nov 12) is the fast everyday model for coding and agent work, with a 1M-token context and a new xhigh thinking level above low, medium, and the default high. It is on the free tier and costs $1.50 / $7.50 per 1M tokens on the paid tier, and Google has a migration guide from Gemini 3.8 Flash. Nov 18: you can pass Word, PowerPoint, Excel, and OpenDocument files directly, and slice documents, spreadsheets, video, and audio by page range, sheet, cell range, or time interval in prompts and function responses. Gemini 4 Neon (gemini-4-neon, GA Nov 18) sits between Hydrogen and Carbon for complex coding and agent work, with four thinking levels (low, medium, default high, and xhigh), a 1M-token context, and long outputs up to 1M tokens. It is on the paid tier only at $3 / $15 per 1M tokens ($0.15 cached input). Nov 19: Genie 4 (genie-4) is GA on the paid tier for real-time interactive world generation, at $1.50 per 1M input tokens and $17.50 per 1M video output tokens (about $0.10 a second). - Price: Free tier · Gemini 3.8 Flash $0.75 / $3.75 (promo to Dec 31) · Gemini 4 Hydrogen $1.50 / $7.50 · Gemini 4 Neon $3 / $15 · Gemini 4 Argon $2 / $10 (promo to Nov 30) · Gemini 4 Carbon $2 / $10 (promo to Nov 30, then $4 / $20) per 1M tokens - Best for: Free tier and Flash pricing - Site: https://ai.google.dev - ToolTier: https://tooltier.ai/tools/google-gemini-api.html ### A · Muse Wonder Meta's frontier coding and agent model on the Model API, with a 1M context window. Muse Wonder Full stays on Muse Code subscriptions. Meta also lists Muse Ember (muse-ember-1.0), its smallest model, for high-volume subagent work like tool calls, coding subtasks, and extraction: 1M context at $0.10 in / $0.50 out per 1M tokens up to 200K tokens of context, $0.30 / $1.50 above that. - Price: $4 in / $20 out per 1M tokens · cached input $0.20 - Best for: Frontier coding model, 1M context - Site: https://dev.meta.ai/models/muse-wonder - ToolTier: https://tooltier.ai/tools/muse-wonder.html ### A · OpenRouter One key, hundreds of models and automatic fallbacks. Ideal for testing and routing. Crouton Alpha, a free stealth model with a 1M-token context for coding and agent sub-tasks, is free on OpenRouter for now (Nov 3). - Price: Free (25+ free models, 50 req/day) · pay-as-you-go with 5.5% platform fee - Best for: One key, many models - Site: https://openrouter.ai - ToolTier: https://tooltier.ai/tools/openrouter.html ### B · xAI Grok API Fast, cheap flagship with a 500k context window. A good second provider. - Price: Pay per token · Grok 4.7 $2 / $6 per 1M tokens - Best for: Fast second provider - Site: https://x.ai/api - ToolTier: https://tooltier.ai/tools/xai-grok-api.html ## Comparisons ### Claude Code vs OpenAI Codex Pick Claude Code for all-round work in big codebases; pick OpenAI Codex for bulk autonomous work. - Claude Code: S tier in Coding Agents · Included with Claude Pro $20/mo ($17/mo annual) · Max from $100/mo · Free tier: None listed; included with Claude Pro ($20/mo) · Best for: All-round agent for big codebases - OpenAI Codex: S tier in Coding Agents · Free · Go $8/mo · Plus $20/mo · Pro $100, $200 or $500/mo · Free tier: Yes (Free plan) · Best for: Bulk autonomous work - Page: https://tooltier.ai/compare/claude-code-vs-openai-codex.html ### Lovable vs Bolt.new Pick Lovable for polished output if you don't want to write the code; pick Bolt.new for the fastest prompt-to-preview. - Lovable: S tier in App Builders · Free (5 credits/day) · Pro from $25/mo · Free tier: Yes (5 credits/day) · Best for: Polished apps for non-coders - Bolt.new: S tier in App Builders · Free · Lite $9/mo (Forge only) · Pro from $25/mo · Teams $30/member · Free tier: Yes · Best for: Fastest prompt-to-preview - Page: https://tooltier.ai/compare/lovable-vs-bolt-new.html ### Vercel vs Netlify Pick Vercel for Next.js and v0 apps; pick Netlify for static and full-stack sites on a generous free tier. - Vercel: S tier in Deploy & Hosting · Hobby free · Pro $20/mo (+$20/dev seat) · Free tier: Yes (Hobby) · Best for: Next.js and v0 apps - Netlify: S tier in Deploy & Hosting · Free · Personal $9/mo · Pro $20/mo · Free tier: Yes · Best for: Static and full-stack sites - Page: https://tooltier.ai/compare/vercel-vs-netlify.html ### Supabase vs Firebase Supabase wins for most vibe coders (S tier vs A). Pick Firebase for mobile and realtime apps. - Supabase: S tier in Backend, DB & Auth · Free (2 projects) · Pro from $25/mo · Free tier: Yes (2 projects) · Best for: Postgres, auth, storage, and edge functions - Firebase: A tier in Backend, DB & Auth · Spark free · Blaze pay-as-you-go · Free tier: Yes (Spark) · Best for: Mobile and realtime apps - Page: https://tooltier.ai/compare/supabase-vs-firebase.html ### Cursor vs GitHub Copilot Cursor wins for most builders (S tier vs A). Pick GitHub Copilot to stay in VS Code or JetBrains. - Cursor: S tier in AI Coding IDEs · Free · Plus $8/mo (Grok models only) · Premium $30/mo · Super $100/mo · Ultra $200/mo · Free tier: Yes · Best for: Default AI editor - GitHub Copilot: A tier in AI Coding IDEs · Free · Pro $10/mo · Pro+ $39/mo · Max $100/mo · Free tier: Yes · Best for: Stay in VS Code or JetBrains - Page: https://tooltier.ai/compare/cursor-vs-github-copilot.html ### Anthropic Claude API vs OpenAI API Pick the Claude API for coding and agents; pick the OpenAI API for the broadest ecosystem. - Anthropic Claude API: S tier in AI APIs & Models · Pay per token · Haiku 5.5 $0.10 / $0.50 (prompts up to 100K) · Sonnet 5.5 $2 / $10 · Opus 5.5 $4 / $20 · Fable 5.2 $8 / $40 per 1M tokens · Free tier: None listed; pay per token · Best for: Coding and agent models - OpenAI API: S tier in AI APIs & Models · Pay per token · GPT-6.2 Astra $8 / $40 · GPT-6.2 Sol $2 / $10 · GPT-6.1 Terra $1 / $5 · GPT-6 Luna $0.10 / $0.50 per 1M tokens · Free tier: None listed; pay per token · Best for: Broadest ecosystem - Page: https://tooltier.ai/compare/anthropic-claude-api-vs-openai-api.html ### Railway vs Render Railway wins for most builders (A tier vs B). Pick Render for a Heroku-style PaaS. - Railway: A tier in Deploy & Hosting · $5 trial credit · Hobby $5/mo · Pro $20/mo · Free tier: Trial only ($5 credit) · Best for: Backends, workers, and databases - Render: B tier in Deploy & Hosting · Free tier · usage-based instances · Free tier: Yes · Best for: Services, cron jobs, and Postgres - Page: https://tooltier.ai/compare/railway-vs-render.html ### Greptile vs CodeRabbit Pick Greptile for free reviews as a solo developer; pick CodeRabbit for seat-priced team PR reviews. - Greptile: S tier in AI Code Review · Starter free (1 developer, 50 credits/mo) · Pro $30/seat/mo · Free tier: Yes (Starter: 1 developer, 50 credits/mo) · Best for: Solo builders who want free review credits - CodeRabbit: S tier in AI Code Review · Free (summaries; IDE and CLI reviews) · OSS public repos free · Essentials $24/dev/mo annual ($30 monthly) · Free tier: Yes (summaries plus IDE and CLI reviews; OSS public repos free) · Best for: Seat-priced PR, CLI, and IDE reviews - Page: https://tooltier.ai/compare/greptile-vs-coderabbit.html ### Lovable vs Replit Lovable wins for most builders (S tier vs A). Pick Replit for a full browser IDE with an agent, database and deploys in one place. - Lovable: S tier in App Builders · Free (5 credits/day) · Pro from $25/mo · Free tier: Yes (5 credits/day) · Best for: Polished apps for non-coders - Replit: A tier in App Builders · Free · Core $20/mo · Pro $100/mo · Free tier: Yes · Best for: Browser IDE, agent, database, and deploys - Page: https://tooltier.ai/compare/lovable-vs-replit.html ### Bolt.new vs v0 Bolt.new wins for most builders (S tier vs A). Pick v0 for React and shadcn UI on the Vercel stack. - Bolt.new: S tier in App Builders · Free · Lite $9/mo (Forge only) · Pro from $25/mo · Teams $30/member · Free tier: Yes · Best for: Fastest prompt-to-preview - v0: A tier in App Builders · Free · paid from $30/user/mo · Free tier: Yes (7 messages/day) · Best for: React and shadcn UI on Vercel - Page: https://tooltier.ai/compare/bolt-new-vs-v0.html ### Lovable vs Base44 Lovable wins for most builders (S tier vs B). Pick Base44 for internal tools with built-in data and auth. - Lovable: S tier in App Builders · Free (5 credits/day) · Pro from $25/mo · Free tier: Yes (5 credits/day) · Best for: Polished apps for non-coders - Base44: B tier in App Builders · Free · paid from $16/mo (annual) · Free tier: Yes · Best for: Internal tools with data and auth - Page: https://tooltier.ai/compare/lovable-vs-base44.html ### Vercel vs Railway Vercel ranks higher (S tier vs A) for front ends and Next.js. Pick Railway for one-click backends, workers and databases. - Vercel: S tier in Deploy & Hosting · Hobby free · Pro $20/mo (+$20/dev seat) · Free tier: Yes (Hobby) · Best for: Next.js and v0 apps - Railway: A tier in Deploy & Hosting · $5 trial credit · Hobby $5/mo · Pro $20/mo · Free tier: Trial only ($5 credit) · Best for: Backends, workers, and databases - Page: https://tooltier.ai/compare/vercel-vs-railway.html ### Netlify vs Cloudflare Workers Netlify ranks higher (S tier vs A) for static and full-stack sites. Pick Cloudflare Workers for low-cost edge compute. - Netlify: S tier in Deploy & Hosting · Free · Personal $9/mo · Pro $20/mo · Free tier: Yes · Best for: Static and full-stack sites - Cloudflare Workers: A tier in Deploy & Hosting · Free · Paid from $5/mo · Free tier: Yes · Best for: Low-cost edge compute - Page: https://tooltier.ai/compare/netlify-vs-cloudflare-workers.html ### Supabase vs Convex Supabase wins for most vibe coders (S tier vs A). Pick Convex for a reactive TypeScript backend that AI agents write well. - Supabase: S tier in Backend, DB & Auth · Free (2 projects) · Pro from $25/mo · Free tier: Yes (2 projects) · Best for: Postgres, auth, storage, and edge functions - Convex: A tier in Backend, DB & Auth · Free · Pro $25/dev/mo · Free tier: Yes · Best for: Reactive TypeScript backends - Page: https://tooltier.ai/compare/supabase-vs-convex.html ### Cursor vs Google Antigravity Cursor wins for most builders (S tier vs A). Pick Google Antigravity if you build on Gemini and want a strong free tier. - Cursor: S tier in AI Coding IDEs · Free · Plus $8/mo (Grok models only) · Premium $30/mo · Super $100/mo · Ultra $200/mo · Free tier: Yes · Best for: Default AI editor - Google Antigravity: A tier in AI Coding IDEs · Free · higher limits via Google AI Pro/Ultra (plan price not listed on the Antigravity pricing page) · Free tier: Yes · Best for: Building on Gemini - Page: https://tooltier.ai/compare/cursor-vs-google-antigravity.html ### Claude Code vs Devin Claude Code wins for most builders (S tier vs A). Pick Devin (now merged with Windsurf) to assign work to cloud agents like a teammate. - Claude Code: S tier in Coding Agents · Included with Claude Pro $20/mo ($17/mo annual) · Max from $100/mo · Free tier: None listed; included with Claude Pro ($20/mo) · Best for: All-round agent for big codebases - Devin: A tier in Coding Agents · Free · Pro $20/mo · Max $200/mo · Teams $80/mo + $40/dev seat · Free tier: Yes · Best for: Assign work like a teammate - Page: https://tooltier.ai/compare/claude-code-vs-devin.html ### n8n vs Make Pick n8n for per-execution pricing, code steps, or self-hosting. Pick Make for a visual canvas with no server. - n8n: S tier in AI Workflow Automation · Community Edition free (self-host) · Starter €20/mo annual · Pro €50/mo annual · Free tier: Community Edition (self-host); Cloud trial, no card · Best for: Self-host or per-execution AI workflows - Make: A tier in AI Workflow Automation · Free (1,000 credits/mo) · Core from $9/mo (10,000 credits) · Free tier: Yes (1,000 credits/mo) · Best for: Visual branching without a server - Page: https://tooltier.ai/compare/n8n-vs-make.html ### n8n vs Zapier Pick n8n for multi-step AI workflows and self-hosting. Pick Zapier to connect a long-tail app with no hosting. - n8n: S tier in AI Workflow Automation · Community Edition free (self-host) · Starter €20/mo annual · Pro €50/mo annual · Free tier: Community Edition (self-host); Cloud trial, no card · Best for: Self-host or per-execution AI workflows - Zapier: A tier in AI Workflow Automation · Free (100 tasks/mo, two-step) · Professional from $19.99/mo annual (750 tasks) · Free tier: Yes (100 tasks/mo, two-step Zaps) · Best for: Largest app catalog, no hosting - Page: https://tooltier.ai/compare/n8n-vs-zapier.html ### Cursor vs Claude Code Different jobs, and both are S tier. Pick Cursor to steer each edit inside an AI editor. Pick Claude Code to hand off a whole task from the terminal and review the diff. - Cursor: S tier in AI Coding IDEs · Free · Plus $8/mo (Grok models only) · Premium $30/mo · Super $100/mo · Ultra $200/mo · Free tier: Yes · Best for: Default AI editor - Claude Code: S tier in Coding Agents · Included with Claude Pro $20/mo ($17/mo annual) · Max from $100/mo · Free tier: None listed; included with Claude Pro ($20/mo) · Best for: All-round agent for big codebases - Page: https://tooltier.ai/compare/cursor-vs-claude-code.html ### Cursor vs OpenAI Codex Different jobs, and both are S tier. Pick Cursor to steer each edit inside an AI editor. Pick OpenAI Codex for bulk autonomous work across the CLI, IDE, cloud tasks and GitHub reviews on one ChatGPT plan. - Cursor: S tier in AI Coding IDEs · Free · Plus $8/mo (Grok models only) · Premium $30/mo · Super $100/mo · Ultra $200/mo · Free tier: Yes · Best for: Default AI editor - OpenAI Codex: S tier in Coding Agents · Free · Go $8/mo · Plus $20/mo · Pro $100, $200 or $500/mo · Free tier: Yes (Free plan) · Best for: Bulk autonomous work - Page: https://tooltier.ai/compare/cursor-vs-openai-codex.html ### Claude Code vs Factory Droid Claude Code wins for most builders (S tier vs A). Pick Factory Droid for one model-independent agent that runs Claude, GPT and open-weight models. - Claude Code: S tier in Coding Agents · Included with Claude Pro $20/mo ($17/mo annual) · Max from $100/mo · Free tier: None listed; included with Claude Pro ($20/mo) · Best for: All-round agent for big codebases - Factory Droid: A tier in Coding Agents · Pro $20/mo · Plus $100/mo · Max $200/mo · Teams $60/mo + $40/seat · Free tier: None listed; Pro $20/mo (BYOK free up to an allowance) · Best for: Model-independent agent, any frontier model - Page: https://tooltier.ai/compare/claude-code-vs-factory-droid.html ### Claude Code vs OpenCode Claude Code wins for most builders (S tier vs A). Pick OpenCode for a free, open-source terminal agent that runs any model. - Claude Code: S tier in Coding Agents · Included with Claude Pro $20/mo ($17/mo annual) · Max from $100/mo · Free tier: None listed; included with Claude Pro ($20/mo) · Best for: All-round agent for big codebases - OpenCode: A tier in Coding Agents · Free and open source · you pay your model provider (no pricing page) · Free tier: Yes (free and open source; you pay your model provider) · Best for: Open source, any model - Page: https://tooltier.ai/compare/claude-code-vs-opencode.html ### Supabase vs Neon Supabase wins for most vibe coders (S tier vs A). Pick Neon when you only need serverless Postgres with instant branching for every preview. - Supabase: S tier in Backend, DB & Auth · Free (2 projects) · Pro from $25/mo · Free tier: Yes (2 projects) · Best for: Postgres, auth, storage, and edge functions - Neon: A tier in Backend, DB & Auth · Free · usage from $0.106/CU-hr · Free tier: Yes · Best for: Serverless Postgres with branching - Page: https://tooltier.ai/compare/supabase-vs-neon.html ### Vercel vs Cloudflare Workers Vercel ranks higher (S tier vs A) for Next.js and v0 apps. Pick Cloudflare Workers for low-cost edge compute with a huge free tier. - Vercel: S tier in Deploy & Hosting · Hobby free · Pro $20/mo (+$20/dev seat) · Free tier: Yes (Hobby) · Best for: Next.js and v0 apps - Cloudflare Workers: A tier in Deploy & Hosting · Free · Paid from $5/mo · Free tier: Yes · Best for: Low-cost edge compute - Page: https://tooltier.ai/compare/vercel-vs-cloudflare-workers.html ### Lovable vs v0 Lovable wins for most builders (S tier vs A). Pick v0 for React and shadcn UI on the Vercel stack. - Lovable: S tier in App Builders · Free (5 credits/day) · Pro from $25/mo · Free tier: Yes (5 credits/day) · Best for: Polished apps for non-coders - v0: A tier in App Builders · Free · paid from $30/user/mo · Free tier: Yes (7 messages/day) · Best for: React and shadcn UI on Vercel - Page: https://tooltier.ai/compare/lovable-vs-v0.html ### CodeRabbit vs Cursor Bugbot CodeRabbit ranks higher (S tier vs A) for seat-priced PR, CLI and IDE reviews. Pick Cursor Bugbot if you already pay for Cursor Premium or above. - CodeRabbit: S tier in AI Code Review · Free (summaries; IDE and CLI reviews) · OSS public repos free · Essentials $24/dev/mo annual ($30 monthly) · Free tier: Yes (summaries plus IDE and CLI reviews; OSS public repos free) · Best for: Seat-priced PR, CLI, and IDE reviews - Cursor Bugbot: A tier in AI Code Review · No separate fee · Premium $30/mo and up · average review $1.00–$1.50 · Free tier: No; needs Cursor Premium ($30/mo) or above · Best for: Already paying for Cursor - Page: https://tooltier.ai/compare/coderabbit-vs-cursor-bugbot.html ### Playwright MCP vs Chrome DevTools MCP Playwright MCP ranks higher (S tier vs A) for automating Chrome, Firefox or WebKit through accessibility snapshots. Pick Chrome DevTools MCP to debug and profile in Chrome: performance traces, network requests, and console errors. - Playwright MCP: S tier in MCP Servers · Free and open source (Apache-2.0) · Free tier: Yes (free and open source) · Best for: Cross-browser automation and testing - Chrome DevTools MCP: A tier in MCP Servers · Free and open source (Apache-2.0) · Free tier: Yes (free and open source) · Best for: Debugging and profiling in Chrome - Page: https://tooltier.ai/compare/playwright-mcp-vs-chrome-devtools-mcp.html ### Make vs Zapier Both are A tier, so it comes down to fit. Pick Make for a visual canvas with branching and no server. Pick Zapier for the largest app catalog when the workflow is short. - Make: A tier in AI Workflow Automation · Free (1,000 credits/mo) · Core from $9/mo (10,000 credits) · Free tier: Yes (1,000 credits/mo) · Best for: Visual branching without a server - Zapier: A tier in AI Workflow Automation · Free (100 tasks/mo, two-step) · Professional from $19.99/mo annual (750 tasks) · Free tier: Yes (100 tasks/mo, two-step Zaps) · Best for: Largest app catalog, no hosting - Page: https://tooltier.ai/compare/make-vs-zapier.html ### Cline vs OpenCode OpenCode ranks higher (A tier vs B). Pick OpenCode for an open-source terminal agent that runs any model and can use your ChatGPT, Copilot or Claude Code login. Pick Cline to stay inside VS Code with your own keys. - Cline: B tier in Coding Agents · Free · pay for inference at cost or bring your own key · Free tier: Yes (free; pay inference at cost or bring your own key) · Best for: Open-source VS Code agent, bring your own keys - OpenCode: A tier in Coding Agents · Free and open source · you pay your model provider (no pricing page) · Free tier: Yes (free and open source; you pay your model provider) · Best for: Open source, any model - Page: https://tooltier.ai/compare/cline-vs-opencode.html ### OpenAI Codex vs OpenCode OpenAI Codex ranks higher (S tier vs A) for bulk autonomous work on one ChatGPT plan. Pick OpenCode for a free, open-source terminal agent that runs any model. - OpenAI Codex: S tier in Coding Agents · Free · Go $8/mo · Plus $20/mo · Pro $100, $200 or $500/mo · Free tier: Yes (Free plan) · Best for: Bulk autonomous work - OpenCode: A tier in Coding Agents · Free and open source · you pay your model provider (no pricing page) · Free tier: Yes (free and open source; you pay your model provider) · Best for: Open source, any model - Page: https://tooltier.ai/compare/openai-codex-vs-opencode.html ### Claude Code vs Kiro Different jobs on different lists. Pick Claude Code (S tier) to hand a whole task to an agent and review the diff. Pick Kiro (B tier IDE) when you want a written spec before the code on bigger features. - Claude Code: S tier in Coding Agents · Included with Claude Pro $20/mo ($17/mo annual) · Max from $100/mo · Free tier: None listed; included with Claude Pro ($20/mo) · Best for: All-round agent for big codebases - Kiro: B tier in AI Coding IDEs · Free (50 credits) · Pro $20/mo · Pro+ $40/mo · Pro Max $100/mo · Power $200/mo · Free tier: Yes (50 credits) · Best for: Spec-driven larger features - Page: https://tooltier.ai/compare/claude-code-vs-kiro.html ### Claude Code vs Google Antigravity Different jobs on different lists. Pick Claude Code (S tier) to hand a task to a terminal agent. Pick Google Antigravity (A tier IDE) for an agent-first editor with a strong free tier, best on Gemini. - Claude Code: S tier in Coding Agents · Included with Claude Pro $20/mo ($17/mo annual) · Max from $100/mo · Free tier: None listed; included with Claude Pro ($20/mo) · Best for: All-round agent for big codebases - Google Antigravity: A tier in AI Coding IDEs · Free · higher limits via Google AI Pro/Ultra (plan price not listed on the Antigravity pricing page) · Free tier: Yes · Best for: Building on Gemini - Page: https://tooltier.ai/compare/claude-code-vs-google-antigravity.html ### Greptile vs Claude Code Review Greptile ranks higher (S tier vs A) and has a free Starter plan for one developer. Pick Claude Code Review if your team is already on Claude Team or Enterprise. - Greptile: S tier in AI Code Review · Starter free (1 developer, 50 credits/mo) · Pro $30/seat/mo · Free tier: Yes (Starter: 1 developer, 50 credits/mo) · Best for: Solo builders who want free review credits - Claude Code Review: A tier in AI Code Review · Team and Enterprise only · usage credits, no flat per-review price · Free tier: No; Team and Enterprise only, billed as usage credits · Best for: Already on Claude Team or Enterprise - Page: https://tooltier.ai/compare/greptile-vs-claude-code-review.html ### CodeRabbit vs Claude Code Review CodeRabbit ranks higher (S tier vs A) for seat-priced reviews on the PR, in the CLI and in the IDE. Pick Claude Code Review if your team is already on Claude Team or Enterprise. - CodeRabbit: S tier in AI Code Review · Free (summaries; IDE and CLI reviews) · OSS public repos free · Essentials $24/dev/mo annual ($30 monthly) · Free tier: Yes (summaries plus IDE and CLI reviews; OSS public repos free) · Best for: Seat-priced PR, CLI, and IDE reviews - Claude Code Review: A tier in AI Code Review · Team and Enterprise only · usage credits, no flat per-review price · Free tier: No; Team and Enterprise only, billed as usage credits · Best for: Already on Claude Team or Enterprise - Page: https://tooltier.ai/compare/coderabbit-vs-claude-code-review.html ### Replit vs Base44 Replit ranks higher (A tier vs B) for a full browser IDE with an agent, database and deploys. Pick Base44 for internal tools with built-in data and auth. - Replit: A tier in App Builders · Free · Core $20/mo · Pro $100/mo · Free tier: Yes · Best for: Browser IDE, agent, database, and deploys - Base44: B tier in App Builders · Free · paid from $16/mo (annual) · Free tier: Yes · Best for: Internal tools with data and auth - Page: https://tooltier.ai/compare/replit-vs-base44.html ### Cursor vs Zed Cursor ranks higher (S tier vs B) as the default AI editor. Pick Zed for raw editor speed when you bring your own agent or keys. - Cursor: S tier in AI Coding IDEs · Free · Plus $8/mo (Grok models only) · Premium $30/mo · Super $100/mo · Ultra $200/mo · Free tier: Yes · Best for: Default AI editor - Zed: B tier in AI Coding IDEs · Personal free · Pro $10/mo (incl. $5 tokens) · Business $30/seat/mo · Free tier: Yes (Personal) · Best for: Editor speed, bring your own keys - Page: https://tooltier.ai/compare/cursor-vs-zed.html ## Badges Free tier badges for every listed tool: https://tooltier.ai/badges.html. Image URL: https://tooltier.ai/badges/.svg (shows the tool's current tier).