52 facts per product, each taken from the vendor's own public pages and linked to its source. 26 rows differ and are highlighted; the better documented value in a row is bold. “Not documented” means the vendor's pages do not state it — it is never counted as a “No”.
Facts verified · Prices in USD · Machine-readable JSON
Aider is free under the Apache 2.0 licence and lists no paid plans; you pay your model provider for usage, with your own API key. Claude's Free plan does not include Claude Code; it starts on Pro at $17 per month billed annually or $20 monthly, and pay-as-you-go use goes through an Anthropic Console API account.
Aider connects to almost any model through LiteLLM, including OpenAI, Anthropic, Gemini, DeepSeek and xAI, and to local models through Ollama, LM Studio or any OpenAI-compatible server. Claude Code runs Anthropic's Claude models only and does not support routing to other models.
Aider is Apache 2.0 open source and always runs on your own machine or container; the vendor states it never collects your code, prompts or keys, and with local models inference stays on your infrastructure too. Claude Code's client is proprietary, and its models run on Anthropic or on your Amazon Bedrock, Google Cloud or Microsoft Foundry account.
Claude Code has a VS Code extension and a JetBrains plugin. Aider's pages point to third-party VS Code plugins and to running aider in an IDE's terminal, or to its watch mode, which acts on AI comments you type in any editor.
Claude Code runs cloud sessions that keep going after you close your laptop, and the Claude app for iOS and Android starts, monitors and steers them. Aider runs in your terminal, and its pages document neither cloud agents nor a mobile app.
Claude Code's Team plan is $20 per seat per month billed annually or $25 monthly, for 2 to 150 seats, with SSO and an analytics dashboard for admins. Aider lists no team plan, admin controls or SSO.
Claude Code documents SOC 2 Type II, ISO 27001:2022 and HIPAA coverage on qualified Enterprise accounts. Aider's pages document no certifications; the vendor states it never collects your code, and your model provider's terms apply to what you send it.
| Aider | Claude Code | |
|---|---|---|
| Free plan | Yes The tool is free and open source (Apache 2.0). Most models need an API key from an LLM provider, and you pay that provider for usage. | No Claude's Free plan does not include Claude Code; Claude Code starts on Pro. The Console route is pay-as-you-go API usage. |
| Free plan limits | No aider-imposed limits; model usage is paid to your LLM provider (free options: OpenRouter free models with daily limits, local models) Aider never enforces token limits; it only reports limit errors from the API provider. The LLMs page names OpenRouter free models (limited daily usage) and Google's Gemini 2.5 Pro Exp as free options, and local models via Ollama. | No free plan Claude's Free plan does not include Claude Code. |
| Free trial (days) | Not documented Not documented on vendor pages | Not documented Not documented on vendor pages. The plan comparison lists trials only for sales-assisted Enterprise, with no length stated. |
| Trial requires credit card | Not documented Not documented on vendor pages | Not documented Not documented on vendor pages |
| Cheapest paid plan, billed annually (per user / month) | Not documented Not documented on vendor pages | $17.00 Pro plan, billed annually ($200 up front). |
| Cheapest paid plan, billed monthly (per user / month) | Not documented Not documented on vendor pages | $20.00 Pro plan, billed monthly. |
| Highest listed-price plan, billed annually (per user / month) | Not documented Not documented on vendor pages | $100.00 Team Premium seat. Max 20x ($200/month) costs more but is billed monthly only; Enterprise is $20/seat plus usage at API rates. |
| Minimum paid seats | Not documented Not documented on vendor pages | 2 Team plan is for 2 to 150 seats. Pro and Max are single-user plans. |
| Custom-priced enterprise plan | Not documented Not documented on vendor pages | Yes Enterprise lists US$20/seat/month billed annually plus usage at API rates; the sales-assisted route gives a tailored quote. |
| Aider | Claude Code | |
|---|---|---|
| Web app | Yes Experimental browser UI that you launch locally with aider --browser; it edits files in your local git repo. Not a hosted web service. | Yes Claude Code on the web (claude.ai/code) runs cloud sessions; Pro, Max, Team, and Enterprise premium or Chat + Claude Code seats. |
| Runs on Windows | Yes One-line PowerShell installer listed under the install page's WINDOWS heading. Also installs with pip, uv or pipx on Python 3.8-3.13. | Yes CLI on Windows 10 1809+ or Windows Server 2019+ (native or WSL); Desktop app also on Windows. |
| Runs on macOS | Yes One-line curl/wget installer for Mac and Linux. Also installs with pip, uv or pipx on Python 3.8-3.13. | Yes macOS 13.0 or later. |
| Runs on Linux | Yes One-line curl/wget installer for Mac and Linux. Docker images (paulgauthier/aider, paulgauthier/aider-full) are also published. | Yes CLI on Ubuntu 20.04+, Debian 10+, Alpine Linux 3.19+. The Desktop app on Linux is in beta. |
| iOS app | Not documented Not documented on vendor pages | Yes The Claude app is a client for cloud sessions and Remote Control of local sessions; code does not run on the phone. |
| Android app | Not documented Not documented on vendor pages | Yes The Claude app is a client for cloud sessions and Remote Control of local sessions; code does not run on the phone. |
| Browser extension | Not documented Not documented on vendor pages | Yes Claude in Chrome extension (Chrome, Edge, other Chromium browsers) lets Claude Code drive the browser for testing; requires a claude.ai login, not an API key. |
| Aider | Claude Code | |
|---|---|---|
| Own standalone code editor | Not documented Not documented on vendor pages | Yes Claude Desktop's Code tab: an agent app with a file-editor pane, diff viewer and terminal. Not a full IDE and not a fork of another editor. |
| Extension for VS Code | Not documented Not documented on vendor pages. The docs point to third-party aider plugins for VS Code and to running aider in VS Code's terminal. | Yes Requires VS Code 1.94.0 or later. |
| Plugin for JetBrains IDEs | Not documented Not documented on vendor pages | Yes IntelliJ IDEA, PyCharm, Android Studio, WebStorm, PhpStorm, GoLand and others; the plugin runs the CLI in the IDE terminal. |
| Command-line (terminal) agent | Yes Aider is a terminal program; the browser UI and IDE file-watching are add-ons to it. | Yes The CLI is the most complete surface; scripting and the Agent SDK are CLI-only. |
| Other editors supported | Any IDE or text editor via --watch-files AI comments; NeoVim via a community plugin (aider.nvim) With --watch-files, aider reads one-line comments ending in AI! or AI? that you type in any editor and acts on them. The NeoVim plugin is by a community member (joshuavial), not the vendor. | Cursor, Devin Desktop, Kiro and other VS Code forks (via the VS Code extension); any editor's terminal via the CLI Cursor has its own install link on the same page. |
| Aider | Claude Code | |
|---|---|---|
| Inline code completion (autocomplete) | Not documented Not documented on vendor pages | No Stated for the Desktop app; no Claude Code surface documents as-you-type completion. It works through prompts and agent edits. |
| Agent that edits across multiple files | Yes Edits every file added to the chat and asks to add other files it needs. Architect mode splits the work: one model proposes the change and an editor model writes the file edits. | Yes |
| Agent runs terminal commands | Yes The model suggests shell commands (install dependencies, run tests, run the program) and aider runs them after you confirm; on by default, controlled by --suggest-shell-commands. /run, /test and --auto-test also run commands and feed output back. | Yes Asks permission before running commands unless a permission mode allows it. |
| Cloud / background agents | Not documented Not documented on vendor pages | Yes Cloud sessions on Pro, Max and Team, and for Enterprise users with premium or Chat + Claude Code seats; not available through third-party providers. |
| Pull request code review | Yes The documented workflow is manual, in the chat: load a branch diff with /run git diff a..b (or --read a diff file), then ask aider about it. Not an automated GitHub PR reviewer. | Yes Managed GitHub PR review is a research preview on Team and Enterprise, billed separately through usage credits (about $15-25 per review). Other plans can review a diff locally with /code-review. |
| Codebase indexing / semantic code search | Yes Repo map: the key classes, functions and signatures of the whole git repo, ranked by a file-dependency graph and trimmed to a token budget (--map-tokens, default 1k), sent with each request. It is a symbol map, not an embeddings search. | No Uses agentic search (file-pattern and regex search) at run time instead of a code index. |
| MCP (Model Context Protocol) servers | Not documented Not documented on vendor pages | Yes |
| Project rules / custom instruction files | Yes A conventions markdown file (e.g. CONVENTIONS.md), loaded read-only with /read or --read. The read: setting in .aider.conf.yml loads it every session. | Yes CLAUDE.md files and .claude/rules/; also reads AGENTS.md. |
| Checkpoints to roll back agent edits | Yes Aider git-commits each of its edits; /undo discards the last aider commit. This depends on git integration, which is on by default. | Yes Rewind with /rewind or Esc twice. Files changed by Bash commands are not tracked. |
| Aider | Claude Code | |
|---|---|---|
| User can choose the AI model | Yes Choose with --model at launch or /model during a chat. Separate editor and weak models are configurable too. | Yes Switch with /model or claude --model. |
| Model families offered | Almost any LLM via LiteLLM; documented providers: OpenAI, Anthropic, Gemini, Groq, LM Studio, xAI, Azure, Cohere, DeepSeek, Ollama, OpenRouter, GitHub Copilot, Vertex AI, Amazon Bedrock, OpenAI-compatible APIs The LLMs page recommends Gemini 2.5 Pro, DeepSeek R1 and V3, Claude 3.7 Sonnet, and OpenAI o3, o4-mini and GPT-4.1. | Anthropic Claude only: Fable, Opus, Sonnet, Haiku Opus requires a paid plan; Fable draws on usage credits on Pro and 50% of weekly limits on Max. Non-Claude models are not supported. |
| Bring your own API key | Yes Your own provider key is how most models are used; set it on the command line, in environment variables, in a .env file or in .aider.conf.yml. A GitHub Copilot token also works, billed through your Copilot subscription. | Yes Anthropic Console API key, or your own Amazon Bedrock, Google Cloud Agent Platform or Microsoft Foundry account; usage billed by that provider. |
| Local / self-hosted models | Yes Ollama, LM Studio, or any local server with an OpenAI-compatible API. | No Claude models only, served by the Anthropic API, Amazon Bedrock, Google Cloud Agent Platform or Microsoft Foundry. |
| How paid-plan usage is limited | Not documented Not documented on vendor pages | Usage pool shared with Claude chat: limits reset every 5 hours, plus weekly caps; optional usage credits at API rates Max = 5x or 20x Pro usage; Team Premium = 5x Standard. Enterprise and Console usage is billed per token at API rates. |
| Open-source client | Yes Apache 2.0, source on GitHub (Aider-AI/aider). | No The public GitHub repo holds issues, changelog, plugins and examples; the client is proprietary. |
| Aider | Claude Code | |
|---|---|---|
| Zero data retention option | Yes Default for everyone: aider runs on your machine and the vendor never collects code, prompts, chats or keys. Its analytics are opt-in and exclude them. Code and prompts go to the LLM provider you configure, whose retention terms apply. | Yes Enterprise only, for qualified accounts; not default and not in the standard Enterprise plan. Anthropic enables it per organization after an eligibility check. |
| Code excluded from model training | Not documented Not documented on vendor pages | Yes Team, Enterprise, API and cloud-platform use. Free, Pro and Max accounts are used for training when the user's model-improvement setting is on (opt-out). |
| Self-hosted or on-premises deployment | Yes Aider always runs on your own machine or container (pip, uv, pipx or two Docker images). With local models (Ollama, LM Studio, OpenAI-compatible servers), inference also stays in your own infrastructure. | Yes Self-hosted environments run cloud sessions on your own infrastructure (public beta, Team and Enterprise); model inference still goes to api.anthropic.com. The CLI itself runs locally. |
| Team admin dashboard and usage analytics | Not documented Not documented on vendor pages | Yes Team and Enterprise at claude.ai/analytics/claude-code (Admins and Owners), and Console for API customers; seat management on Team and Enterprise. |
| Aider | Claude Code | |
|---|---|---|
| Listed integrations | Not documented Not documented on vendor pages | 313 Plugins in the Claude Marketplace directory filtered to 'Works with: Claude Code' (bundles of tools, skills and MCP integrations); 337 across Claude and Claude Code. |
| Public API | Yes Command line: --message or --message-file runs one instruction and exits. Python: Coder.create() and coder.run(). The vendor says the Python API is not officially supported and may change without backward compatibility. | Yes Agent SDK (CLI, Python and TypeScript packages). |
| Single sign-on (SSO) | Not documented Not documented on vendor pages | Yes Team and Enterprise plans; not on Pro or Max. |
| Two-factor authentication | Not documented Not documented on vendor pages | Not documented Not documented on vendor pages |
| SOC 2 report | Not documented Not documented on vendor pages | Yes SOC 2 Type I and Type II; report available from the Anthropic Trust Center. |
| ISO 27001 certification | Not documented Not documented on vendor pages | Yes ISO 27001:2022; also ISO/IEC 42001:2023. |
| HIPAA compliance offered | Not documented Not documented on vendor pages | Yes Enterprise only. Claude Code is under the BAA only when zero data retention is enabled on a qualified account. |
| Aider | Claude Code | |
|---|---|---|
| Support channels | GitHub issues, Discord, in-chat /help /help answers questions about using aider inside the chat, and /report opens a GitHub issue. Privacy questions go to privacy@aider.chat. | In-app support messenger (Fin AI bot, then Product Support team) and email No phone or live-chat support. Sales-assisted Enterprise adds customer success at certain spend thresholds. |
| 24/7 support | Not documented Not documented on vendor pages | Not documented Not documented on vendor pages |
| Vendor (legal entity) | Aider AI LLC Named in the FAQ and in the privacy policy. The LICENSE file names no copyright holder (the Apache template placeholder is left as is). | Anthropic, PBC Contracting entity is Anthropic Ireland, Limited for customers in the EEA, Switzerland and the UK. |
| Founded | Not documented Not documented on vendor pages | 2021 |
| Headquarters | Not documented Not documented on vendor pages | San Francisco, California, United States Registered address per the privacy policy, which also states the company is headquartered in the United States. |
| Aider plan | Billed annually | Billed monthly |
|---|---|---|
| Open source (Apache 2.0) Free; LLM usage billed by your model provider The only way to get Aider: the open-source tool under the Apache 2.0 licence, which grants a no-charge, royalty-free licence. The vendor lists no paid plans (aider.chat/pricing returns 404). Most models need an API key from an LLM provider, and you pay that provider for usage. Free options: OpenRouter free models (daily usage limits) and local models. | Free | Free |
| Claude Code plan | Billed annually | Billed monthly |
|---|---|---|
| Pro Per month Individual plan; Claude Code included. Annual billing is $200 up front. Usage limits shared with Claude chat. | $17.00 | $20.00 |
| Max 5x Per month Individual plan; 5x the usage of Pro per 5-hour session. Billed monthly only. | Not offered | $100.00 |
| Max 20x Per month Individual plan; 20x the usage of Pro per 5-hour session. Billed monthly only. | Not offered | $200.00 |
| Team (Standard seat) Teams of 2 to 150; Claude Code included; more usage than Pro. SSO, central billing, usage analytics. | $20.00 | $25.00 |
| Team (Premium seat) 5x more usage than Standard seats; seat types can be mixed within one Team plan. | $100.00 | $125.00 |
| Enterprise Per user / month + usage at API rates Seat price plus all usage billed at API rates; billed annually only. Self-serve or sales-assisted (tailored quote). Adds SCIM, audit logs, custom data retention, role-based access. | $20.00 | Not offered |
| Claude API (Console) Pay as you go (per million tokens) Claude Code billed at standard API token prices through a Claude Console account; no per-seat fee. Listed API prices per million input/output tokens: Haiku 4.5 $1/$5, Sonnet 5 $2/$10, Opus 5.5 $4/$20, Fable 5.1 $10/$50. | Pay as you go | Pay as you go |
Per user per month unless the plan states otherwise, as listed on each vendor's pricing page.