52 facts per product, each taken from the vendor's own public pages and linked to its source. 14 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
Claude Pro includes Claude Code at $17 per month billed annually or $20 monthly. Augment Code lists no yearly price; its cheapest plan, Standard, is $20 per month. Neither has a free plan that includes the product.
Claude Code's Team plan is $20 per seat per month billed annually or $25 monthly, for 2 to 150 seats, with each seat's usage limits resetting every five hours plus weekly caps. Augment Code bills usage in dollars across the team: its plans include $20 or $100 of usage a month, and more is pay as you go.
Augment Code's Standard plan is $20 per month flat for the whole team, up to 50 seats, with $20 of usage included; more usage is charged at the model provider's list price plus a 40% service fee on LLM usage. Claude Code's Team plan charges per seat, from $20 per month billed annually.
Augment Code's Context Engine indexes the workspace in Augment's cloud, and files can be excluded with .gitignore or .augmentignore. Claude Code keeps no code index: it searches files with pattern and regex search at run time.
Augment Code offers Anthropic Claude, OpenAI GPT, Google Gemini, xAI Grok, GLM and Kimi, plus its Prism routers that pick a model automatically. Claude Code runs Anthropic's Claude models only and does not support routing to other models.
Augment Code lists on-prem deployment, VPC deployment and single-tenant instances. Claude Code's self-hosted environments, in public beta on Team and Enterprise, run cloud sessions on your infrastructure while model inference still goes to Anthropic.
Both document SOC 2 Type II and a HIPAA BAA. Claude Code also documents ISO 27001:2022, and SSO starts on its Team plan. Augment Code's pages do not document ISO 27001, and SSO is on its Enterprise plan only.
| Claude Code | Augment Code | |
|---|---|---|
| Free plan | 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. | No The pricing page lists three plans (Standard, Business, Enterprise) and none is free. |
| Free plan limits | No free plan Claude's Free plan does not include Claude Code. | No free plan The pricing page lists three plans (Standard, Business, Enterprise) and none is free. |
| Free trial (days) | Not documented Not documented on vendor pages. The plan comparison lists trials only for sales-assisted Enterprise, with no length stated. | Not documented Not documented on vendor pages |
| 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) | $17.00 Pro plan, billed annually ($200 up front). | Not documented Not documented on vendor pages |
| Cheapest paid plan, billed monthly (per user / month) | $20.00 Pro plan, billed monthly. | $20.00 Standard plan. $20/month is a flat price for the whole team (up to 50 seats), not a per-user price, and includes $20 of usage. |
| Highest listed-price plan, billed annually (per user / month) | $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. | Not documented Not documented on vendor pages |
| Minimum paid seats | 2 Team plan is for 2 to 150 seats. Pro and Max are single-user plans. | Not documented Not documented on vendor pages |
| Custom-priced enterprise plan | Yes Enterprise lists US$20/seat/month billed annually plus usage at API rates; the sales-assisted route gives a tailored quote. | Yes Enterprise plan: contact sales. Volume-based annual discounts. |
| Claude Code | Augment Code | |
|---|---|---|
| Web app | Yes Claude Code on the web (claude.ai/code) runs cloud sessions; Pro, Max, Team, and Enterprise premium or Chat + Claude Code seats. | Yes Cosmos (cloud agents) is used from the web app, a phone or Slack. |
| Runs on Windows | Yes CLI on Windows 10 1809+ or Windows Server 2019+ (native or WSL); Desktop app also on Windows. | Yes Auggie CLI runs on Windows through WSL. The VS Code and JetBrains extensions document Windows/Linux keyboard shortcuts. |
| Runs on macOS | Yes macOS 13.0 or later. | Yes Auggie CLI (Node.js 20+), plus VS Code and JetBrains extensions. |
| Runs on Linux | Yes CLI on Ubuntu 20.04+, Debian 10+, Alpine Linux 3.19+. The Desktop app on Linux is in beta. | Yes Auggie CLI (Node.js 20+), plus VS Code and JetBrains extensions. |
| iOS app | Yes The Claude app is a client for cloud sessions and Remote Control of local sessions; code does not run on the phone. | Not documented Not documented on vendor pages |
| Android app | Yes The Claude app is a client for cloud sessions and Remote Control of local sessions; code does not run on the phone. | Not documented Not documented on vendor pages |
| Browser extension | 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. | Not documented Not documented on vendor pages |
| Claude Code | Augment Code | |
|---|---|---|
| Own standalone code editor | 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. | Not documented Not documented on vendor pages |
| Extension for VS Code | Yes Requires VS Code 1.94.0 or later. | Yes Agent and chat. Inline completions and Next Edit were retired on March 31, 2026, except on Enterprise plans. |
| Plugin for JetBrains IDEs | Yes IntelliJ IDEA, PyCharm, Android Studio, WebStorm, PhpStorm, GoLand and others; the plugin runs the CLI in the IDE terminal. | Yes All JetBrains IDEs. The September 2026 plugin changelog requires JetBrains IDEs 2025.2 or newer; the install doc still says 2024.3 or above. |
| Command-line (terminal) agent | Yes The CLI is the most complete surface; scripting and the Agent SDK are CLI-only. | Yes Auggie CLI (npm @augmentcode/auggie, Node.js 20+). Interactive and non-interactive (--print) modes. Non-interactive mode may be disabled if an Enterprise agreement does not include it. |
| Other editors supported | 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. | Zed, Neovim, Emacs (via Auggie CLI in ACP mode); Vim and Neovim (Augment plugin) The Vim/Neovim plugin offers chat only and is in maintenance mode; its inline completions have been retired. |
| Claude Code | Augment Code | |
|---|---|---|
| Inline code completion (autocomplete) | No Stated for the Desktop app; no Claude Code surface documents as-you-type completion. It works through prompts and agent edits. | Yes Enterprise plans only. Retired for all other plans (the former Indie, Standard, Max and Legacy plans) on March 31, 2026. |
| Agent that edits across multiple files | Yes | Yes Available in the IDE extensions, Auggie CLI and Cosmos. |
| Agent runs terminal commands | Yes Asks permission before running commands unless a permission mode allows it. | Yes By default the Agent pauses for approval before running a command. Agent Auto runs commands automatically. |
| Cloud / background agents | 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. | Yes Cosmos cloud agents run in sandboxed VMs and can be triggered by events. Listed on all plans. Compute costs $0.19/hour and is drawn from the usage balance. |
| Pull request code review | 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. | Yes Included on all plans, with token usage drawn from the plan balance. Enterprise Code Review adds analytics, user allowlists, MCP context, multi-org support and unlimited seats/repos. |
| Codebase indexing / semantic code search | No Uses agentic search (file-pattern and regex search) at run time instead of a code index. | Yes The Context Engine indexes the workspace in Augment's cloud. Files can be excluded with .gitignore or .augmentignore. |
| MCP (Model Context Protocol) servers | Yes | Yes Supports local and remote (HTTP/SSE) MCP servers and one-click Easy MCP. Cosmos has an MCP registry. "MCP & Native Tools" is listed on all plans. |
| Project rules / custom instruction files | Yes CLAUDE.md files and .claude/rules/; also reads AGENTS.md. | Yes User and workspace rules in .augment/rules, user guidelines, a .augment-guidelines file, and hierarchical AGENTS.md / CLAUDE.md files. |
| Checkpoints to roll back agent edits | Yes Rewind with /rewind or Esc twice. Files changed by Bash commands are not tracked. | Yes IDE Agent. |
| Claude Code | Augment Code | |
|---|---|---|
| User can choose the AI model | Yes Switch with /model or claude --model. | Yes Model picker in the IDE, Cosmos (per Expert or session) and Auggie CLI (/model or --model). Prism routers can pick the model automatically. |
| Model families offered | 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. | Anthropic Claude, OpenAI GPT, Google Gemini, xAI Grok, Zhipu AI GLM, Moonshot AI Kimi, and Augment's Prism routers Current list includes Claude Fable 5.1, Opus 5, Sonnet 5, Haiku 4.5, GPT-6 Astra, GPT-5.6 Sol/Terra/Luna, Gemini 3.1 Pro, Grok 4.6, GLM 5.3 Flash and Kimi K3. The Prism routers combine Claude and Gemini, or GPT, models. |
| Bring your own API key | Yes Anthropic Console API key, or your own Amazon Bedrock, Google Cloud Agent Platform or Microsoft Foundry account; usage billed by that provider. | Yes Enterprise tenants only, and only for customers with their own Enterprise Agreement with Anthropic, OpenAI, AWS or GCP. |
| Local / self-hosted models | No Claude models only, served by the Anthropic API, Amazon Bedrock, Google Cloud Agent Platform or Microsoft Foundry. | Not documented Not documented on vendor pages |
| How paid-plan usage is limited | 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. | Monthly usage allowance in dollars ($20 Standard, $100 Business), shared across the team, with pay-as-you-go top-ups Usage is charged as LLM tokens at the provider's list price, plus a 40% service fee on LLM usage, plus Cosmos compute at $0.19/hour. Top-ups are valid for 12 months. Enterprise has custom usage limits and admin-set budgets. |
| Open-source client | No The public GitHub repo holds issues, changelog, plugins and examples; the client is proprietary. | No Auggie CLI is under a custom proprietary licence. The Vim/Neovim plugin wrapper is MIT-licensed, but its bundled server is proprietary. |
| Claude Code | Augment Code | |
|---|---|---|
| Zero data retention option | Yes Enterprise only, for qualified accounts; not default and not in the standard Enterprise plan. Anthropic enables it per organization after an eligibility check. | Yes Listed among the Cosmos enterprise security features. The page does not say which plan it needs or whether it is the default. Enterprise admins can allow-list or block models by their data-retention policy. |
| Code excluded from model training | 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). | Yes Paid plans, under the Professional and Enterprise Terms. The Community Terms instead let Augment use Customer Code to train models. |
| Self-hosted or on-premises deployment | 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. | Yes The Cosmos page also lists VPC deployment and single-tenant instances. Agents can run on self-hosted daemons or self-hosted Kubernetes (early access, Linux only), but still make LLM calls to Augment's services. |
| Team admin dashboard and usage analytics | Yes Team and Enterprise at claude.ai/analytics/claude-code (Admins and Owners), and Console for API customers; seat management on Team and Enterprise. | Yes Usage analytics dashboards and budgets are Enterprise-only (the pricing table marks Usage Analytics as Enterprise-only). On the Business plan, Team admins can invite and remove members and manage seats and billing. |
| Claude Code | Augment Code | |
|---|---|---|
| Listed integrations | 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. | Not documented Not documented on vendor pages |
| Public API | Yes Agent SDK (CLI, Python and TypeScript packages). | Yes Auggie SDK for TypeScript and Python, plus an Analytics REST API for usage metrics. Service accounts for automation are Enterprise-only. |
| Single sign-on (SSO) | Yes Team and Enterprise plans; not on Pro or Max. | Yes Enterprise plan only. |
| Two-factor authentication | Not documented Not documented on vendor pages | Not documented Not documented on vendor pages |
| SOC 2 report | Yes SOC 2 Type I and Type II; report available from the Anthropic Trust Center. | Yes SOC 2 Type II, listed on all plans. Reports are available through the Trust Center. |
| ISO 27001 certification | Yes ISO 27001:2022; also ISO/IEC 42001:2023. | Not documented Not documented on vendor pages |
| HIPAA compliance offered | Yes Enterprise only. Claude Code is under the BAA only when zero data retention is enabled on a qualified account. | Yes The security page lists HIPAA Compliant and BAA Available. |
| Claude Code | Augment Code | |
|---|---|---|
| Support channels | 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. | Community support and support-portal tickets (Standard, Business); dedicated support (Enterprise) Trials get community support only. Billing questions go to accounting@augmentcode.com. |
| 24/7 support | Not documented Not documented on vendor pages | Yes Critical (SEV-0) incidents only: 24x7 action with a 2-hour response target. Other requests get target response times within business hours. The SLA does not cover trials. |
| Vendor (legal entity) | Anthropic, PBC Contracting entity is Anthropic Ireland, Limited for customers in the EEA, Switzerland and the UK. | Augment Computing, Inc. The 2024 funding press release calls the company Augment Inc. |
| Founded | 2021 | 2022 Came out of stealth in 2024. |
| Headquarters | San Francisco, California, United States Registered address per the privacy policy, which also states the company is headquartered in the United States. | United States No city is stated. The April 2024 funding press release is datelined Palo Alto, Calif. |
| 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 |
| Augment Code plan | Billed annually | Billed monthly |
|---|---|---|
| Standard Per month, flat for the whole team (no per-seat charge) Flat $20/month for the whole team, up to 50 seats. Includes $20/month of usage across LLM, Context Engine and compute. Top-ups are pay as you go. Includes Cosmos, CLI access, and MCP & native tools. Only a monthly price is listed; no annual billing option is shown. | Not offered | $20.00 |
| Business Per month, flat for the whole team (no per-seat charge) Flat $100/month for the whole team, up to 50 seats. Includes $100/month of usage across LLM, Context Engine and compute. Top-ups are pay as you go. Only a monthly price is listed; no annual billing option is shown. | Not offered | $100.00 |
| Enterprise Custom (contact sales) Custom user pricing, bespoke usage limits, volume-based annual discounts, unlimited users, SSO/OIDC/SCIM, CMEK and ISO 42001 compliance, dedicated support. | Custom | Custom |
Per user per month unless the plan states otherwise, as listed on each vendor's pricing page.