Quick Reference — pick by what you're doing
| If you want to… | Start with | Why |
|---|---|---|
| Drive agentic work from the terminal | Claude Code, OpenAI Codex CLI, Aider | Terminal-native, scriptable, strong autonomy; Aider is BYO-key/open-source. |
| Stay in a full AI-first IDE | Cursor, Devin Desktop, Zed | Inline edits, multi-file agent, tab-completion in one editor. |
| Add AI to your existing editor | GitHub Copilot, Cline, JetBrains Junie | Extensions for VS Code / JetBrains / etc.; keep your setup. |
| Delegate whole tasks asynchronously | Devin, Copilot coding agent, Codex cloud, Jules | Assign an issue → it works in a sandbox → opens a PR. |
| Bring your own API key / any model | Aider, Cline, Zed, Cursor | Pay model cost directly; mix providers; run local models. |
| Maximize MCP / tool integrations | Cline, Claude Code | Cline's one-click MCP marketplace; Claude Code's deep MCP + sub-agents. |
| Spend $0 | Copilot Free, Gemini CLI (OSS), Aider, Cline, Zed Personal | Free tiers or BYO-key open-source (you still pay model API if BYO). |
| Spec-driven / enterprise AWS | Kiro | Spec→plan→build workflow (Amazon Q is being sunset toward Kiro). |
Fundamentals
How to think about the category
Four form factors (and the autonomy spectrum)
Almost every tool is one (or several) of these. Many products now span multiple surfaces sharing one engine.
- CLI Terminal agent — runs in your shell, edits files, runs commands, scriptable into CI. Claude Code, Codex CLI, Aider, Gemini CLI.
- IDE Standalone AI IDE — a full editor (often a VS Code fork) built around AI. Cursor, Devin Desktop, Kiro, Zed.
- EXT Editor extension — bolts AI onto your current editor. GitHub Copilot, Cline, JetBrains Junie/AI Assistant.
- CLOUD Autonomous cloud agent — you assign a task; it works async in a sandbox and returns a PR. Devin, Copilot coding agent, Codex cloud, Jules, Cursor background agents.
Autonomy spectrum: autocomplete (Tab/Copilot completions) → chat/edit (ask, apply a diff) → in-loop agent (multi-step, you approve) → autonomous (delegated, returns a PR). More autonomy = more leverage and more tokens, more review burden, and more ways to go wrong unsupervised.
MCP, BYO-key, and the cost model that actually bites
- MCP (Model Context Protocol) — the now-standard way agents connect to external tools/data (your DB, GitHub, Slack, docs). Broad support is table stakes in 2026; Cline's one-click MCP marketplace and Claude Code's deep MCP are standouts.
- Subscription vs BYO-key — a flat plan is a cap (predictable, but rate limits / rolling windows can block bursts). Bring-your-own-key is a meter (no floor, no ceiling — a single complex agentic run can outspend a week of chat).
Comparison matrix (as of mid-2026 — verify prices)
| Tool | Type | Entry price | Models | BYO key | MCP |
|---|---|---|---|---|---|
| Claude Code | CLI +IDE/web | Pro $17/mo (annual); Max from $100/mo; API PAYG | Claude Opus 4.8 / Sonnet 4.6 / Haiku 4.5 / Fable 5 (1M ctx) | Yes (3rd-party) | Yes |
| Cursor | IDE | Hobby $0; Pro $20; Pro+ $60; Ultra $200; Teams $40/seat | Multi-vendor + in-house Composer 2.5; Auto mode | Yes | Yes |
| GitHub Copilot | EXT +CLOUD | Free; Pro $10; Pro+ $39; Max $100; Business $19/seat | Picker: Claude, OpenAI GPT-5.x, Gemini, MS MAI | No (managed) | Yes |
| OpenAI Codex | CLI +CLOUD +IDE | In ChatGPT Go $8 / Plus $20 / Pro $100; API PAYG | GPT-5.5 (default), GPT-5.4 | No (OpenAI only) | Yes |
| Devin Desktop (ex-Windsurf) | IDE | Free; Pro $20; Teams $40/seat; Max $200 | In-house SWE-1.6 + Claude/GPT/Gemini/Grok | Unconfirmed | Yes |
| Gemini (CLI / Code Assist / Jules) | CLI EXT CLOUD | Code Assist Std ~$19, Ent ~$45/seat; Jules in AI Pro ~$20 | Gemini 3.1 Pro / 3.5 Flash | Yes (CLI) | Yes |
| Aider | CLI (OSS) | Free — you pay model API | Any LLM (incl. local / OpenAI-compatible) | Yes | Limited |
| Cline | EXT (OSS) | Free — BYO key (optional hosted PAYG) | Any (200+ via OpenRouter, Ollama, LM Studio) | Yes | Yes ★ |
| Kiro (AWS) | IDE | Free; Pro $20; Pro+ $40; Pro Max $100; Power $200 | Claude + open-weight + Auto router | No (managed) | Yes |
| Devin (Cognition) | CLOUD | Free; Pro $20; Max $200; Teams $80 + $40/seat | In-house SWE-1.6 + configurable frontier | Config | Yes |
| JetBrains Junie + AI Assistant | EXT | AI Pro $10/mo (personal); AI Ultimate $30 | Claude/GPT/Gemini/Grok + Mellum; local | Yes | Yes |
| Zed | IDE (OSS) | Personal $0 (BYO unlimited); Pro $10; Business $30/seat | Hosted Claude/GPT/Gemini; BYO no-markup | Yes | Yes |
★ Cline ships a one-click MCP marketplace and on-the-fly tool creation — the strongest MCP onboarding. "Type" pills: CLI terminal · IDE standalone editor · EXT editor extension · CLOUD autonomous cloud agent.
Tool profiles
Claude Code
What: A terminal coding agent that also runs as a VS Code extension, JetBrains plugin (beta), desktop app, and web (claude.ai/code) — all sharing one engine, CLAUDE.md, MCP config, and settings. Strong at multi-step autonomous work, sub-agents, and automation (GitHub Actions, Slack→PR, scheduled jobs).
Price (mid-2026): Free tier excluded; Pro $17/mo (billed annually, $20 monthly); Max from $100/mo (5× usage) up to $200/mo (20×); Team/Enterprise per-seat; or API pay-as-you-go. Usage is pooled across Claude chat + Code on a 5-hour rolling window plus weekly caps.
Models: Opus 4.8, Sonnet 4.6, Haiku 4.5, Fable 5; 1M-token context on the larger models; opusplan mode (Opus plans, Sonnet executes). BYO via third-party providers supported.
curl -fsSL https://claude.ai/install.sh | bash
# or: npm install -g @anthropic-ai/claude-code (needs Node 18+)Cursor
What: A VS Code-fork IDE built around AI: unlimited Tab completions, an Agent/Composer for multi-file changes, background (cloud) agents, and a BugBot code reviewer.
Price (mid-2026): Hobby $0; Pro $20/mo; Pro+ $60; Ultra $200; Teams $40/user. In June 2025 it moved from request-counts to a dollar-credit / token-cost model with a separate, much cheaper pool for Auto + the in-house Composer 2.5 model — the repricing drew backlash and a CEO apology.
Models: OpenAI, Anthropic, Google, xAI, and more, plus proprietary Composer 2.5; Auto mode picks by cost/reliability. BYO key supported (Teams adds a small BYOK platform fee).
GitHub Copilot
What: The broadest-reach assistant — extensions for VS Code, Visual Studio, JetBrains, Eclipse, Xcode; web, mobile, CLI; an in-IDE agent mode and an async coding agent (assign an Issue → it works in a GitHub Actions sandbox → opens a PR, with a ~59-min session cap).
Price (mid-2026): Free (2,000 completions/mo); Pro $10; Pro+ $39; new Max $100; Business $19/seat; Enterprise $39/seat. On June 1, 2026 it switched from "premium requests" to token-based AI Credits (1 credit = $0.01); code completions + Next Edit Suggestions stay unlimited/free.
Models: the widest catalog — Claude (to Opus 4.8/Fable 5), OpenAI GPT-5.x, Google Gemini 3.x, Microsoft MAI — selectable, with reasoning levels.
OpenAI Codex
What: A relaunched suite — an open-source Rust Codex CLI, a cloud agent that runs parallel sandboxed tasks → PRs, an IDE extension, a desktop app, plus GitHub @codex and Slack. Sandboxed by default; agent-phase internet off by default.
Price (mid-2026): included in ChatGPT Free/Go $8/Plus $20/Pro $100 (and Business/Enterprise), with rolling 5-hour usage windows; API pay-as-you-go also available.
Models: GPT-5.5 is the recommended default, with GPT-5.4 variants (the older codex-1/GPT-5-codex names are retired).
npm install -g @openai/codexDevin Desktop (formerly Windsurf)
What: The AI IDE formerly called Windsurf/Codeium. After a turbulent 2025 (an OpenAI acquisition fell through; Google DeepMind hired its leadership; Cognition acquired the remaining product/team), it was rebranded "Devin Desktop" on June 2, 2026. Its Cascade agent became "Devin Local."
Price (mid-2026): Free; Pro $20; Teams $40/seat; Max $200; Enterprise custom — now on auto-refreshing daily/weekly quotas (credits retired).
Models: in-house SWE-1.5/1.6 (0-cost) and an Adaptive router, plus Claude/GPT-5.x/Gemini 3.x/Grok/others. MCP + ACP support.
Google Gemini: CLI · Code Assist · Jules
What: Three distinct things. Gemini CLI (open-source, strong MCP); Gemini Code Assist (IDE extension); and Jules (async cloud agent → GitHub PRs).
Price (mid-2026): Code Assist Standard ~$19/seat, Enterprise ~$45/seat. Jules has Free (15 tasks/day) / Pro (100/day) / Ultra (300/day) tiers, bundled into Google AI Pro (~$20/mo) / Ultra.
Models: Gemini 3.1 Pro (1M context) flagship, 3.5 Flash. Strength: huge context, generous quotas, deep Google Cloud ties.
Aider
What: A beloved open-source (Apache-2.0) terminal pair programmer. Architect/editor mode, auto-commits with generated messages, 100+ languages, works with virtually any model including local ones.
Price: free — your only cost is the model API you point it at (BYO key). Maximum control and transparency.
uv tool install aider-chat # or: pipx install aider-chatCline (& the Roo Code note)
What: An open-source agent extension for VS Code (and JetBrains) with Plan/Act modes and the strongest MCP story — a one-click MCP Marketplace and on-the-fly tool creation. BYO key across Anthropic/OpenAI/Gemini/Bedrock/Vertex/OpenRouter (200+)/Ollama/LM Studio; an optional hosted PAYG provider and an Enterprise tier exist.
Kiro & Amazon Q Developer
What: Kiro is AWS's spec-driven agentic IDE (a Code-OSS fork, GA Nov 2025): you write a spec, it plans, then builds — with hooks, steering, and subagents. Runs Claude (Sonnet/Haiku/Opus) + open-weight models + an Auto router; MCP supported.
Price (mid-2026): Free (50 credits); Pro $20 (1,000); Pro+ $40 (2,000); Pro Max $100 (5,000); Power $200 (10,000); overage $0.04/credit.
Devin
What: The original "fully autonomous software engineer" — a cloud agent you delegate scoped tasks to (web, CLI, Slack, VS Code/JetBrains, GitHub/Linear/Jira), which works in its own environment and opens PRs. MCP marketplace with 30+ servers.
Price (mid-2026): Free; Pro $20; Max $200; Teams $80/mo min + $40/seat; Enterprise custom. The old PAYG "ACU" self-serve model was retired (Apr 2026) in favor of quota tiers; ACUs (≈15 min of work each) survive only for Enterprise.
JetBrains Junie + AI Assistant · Zed
JetBrains Junie (GA June 2026) is an autonomous agent across the IDE + tool window + CLI, sharing a credit pool with AI Assistant. Price: AI Pro $10/mo personal (10 credits, ~$1 each), AI Ultimate $30/mo (35 credits); models incl. Claude/GPT/Gemini/Grok + in-house Mellum + local via Ollama; BYO key; MCP. Junie burns credits fast — Ultimate is realistic for heavy use.
Zed is a fast Rust editor (open-source core) with an Agent Panel, parallel agents, an open-source edit-prediction model, MCP, and external-agent support via ACP. Price: Personal $0 (unlimited with your own keys), Pro $10, Business $30/seat; BYO key with no markup on all tiers; Mac/Linux/Windows. Strength: speed + generous BYOK; watch-out: smaller ecosystem than VS Code.
The 2026 pricing shift — read this before you subscribe
Across 2025–2026, nearly every major tool abandoned flat/fixed-request pricing for usage / token / credit / quota models, clustering around mid-2026:
- Copilot: premium requests → token-based AI Credits (Jun 1, 2026; 1 credit = $0.01).
- Cursor: request counts → dollar-credit/token usage (Jun 2025; backlash + CEO apology + refunds).
- Devin Desktop & Devin: credits/ACU PAYG → auto-refreshing quota tiers (2026).
- Claude Code: added weekly limits on Pro/Max (Aug 2025); 5-hour limits doubled (May 2026).
- OpenAI Codex: per-message → API-token-aligned usage (Apr 2026).
Reference: API prices per million tokens (in / out) — for BYO-key math
| Model (mid-2026) | Input /MTok | Output /MTok |
|---|---|---|
| Claude Opus 4.8 | $5 | $25 |
| Claude Sonnet 4.6 | $3 | $15 |
| Claude Haiku 4.5 | $1 | $5 |
| Claude Fable 5 | $10 | $50 |
| OpenAI GPT-5.5 | $5 | $30 |
| OpenAI GPT-5.4 | $2.50 | $15 |
| Google Gemini 3.1 Pro (≤200K) | $2 | $12 |
| Google Gemini 3.5 Flash | $1.50 | $9 |
All three providers offer roughly 90%-off cache reads and 50%-off batch — material for BYO-key cost. Note: newer Claude tokenizers can consume ~30–35% more tokens for the same text, which offsets some per-token savings. Figures as of mid-2026; verify on each provider's pricing page.
Benchmarks reality check (SWE-bench)
- Credible self-reported highs (mid-2026): Claude Opus 4.8 ≈ 88.6% and OpenAI GPT-5.5 ≈ 88.7% on SWE-bench Verified. Gemini 3.1 Pro ≈ low-80s%.
- Treat ~95% "leaderboard" claims with suspicion — some aggregator figures circulating for the newest models aren't corroborated by the vendors' own published numbers.
- The field is moving on to harder, contamination-resistant suites (SWE-bench Pro — leaders in the ~60s% — Multilingual, Terminal-Bench).
How to choose
Common mistakes & anti-patterns
CLAUDE.md/rules/AGENTS file dramatically improves output — most users never write one.