Suggested searches

GPT Image Introduction GPT Image Free Guides GPT Image Developer Docs Midjourney Introduction Midjourney Free Guides Midjourney Developer Docs Google Nano Banana Introduction Google Nano Banana Free Guides Google Nano Banana Developer Docs Adobe Firefly Image Introduction Adobe Firefly Image Free Guides Adobe Firefly Image Developer Docs FLUX Introduction FLUX Free Guides FLUX Developer Docs Ideogram Introduction Ideogram Free Guides Ideogram Developer Docs Recraft Introduction Recraft Free Guides Recraft Developer Docs Stable Diffusion Introduction ByteDance Seedream Introduction Grok Imagine Image Introduction Google Veo Introduction Google Veo Free Guides Google Veo Developer Docs Runway Introduction Kling AI Introduction ByteDance Seedance Introduction ByteDance Seedance Free Guides ByteDance Seedance Developer Docs Luma AI Introduction Adobe Firefly Video Introduction Adobe Firefly Video Free Guides Adobe Firefly Video Developer Docs Hailuo AI Introduction PixVerse Introduction PixVerse Free Guides PixVerse Developer Docs Pika Introduction Pika Free Guides Pika Developer Docs Alibaba Wan Introduction LTX Video Introduction Grok Imagine Video Introduction Google Gemini Introduction Google Gemini Free Guides Google Gemini Developer Docs OpenAI GPT Introduction Claude Fable Introduction Claude Fable Free Guides Claude Fable Developer Docs DeepSeek Introduction Qwen Introduction Llama Introduction Codex Introduction Codex Free Guides Codex Developer Docs Cursor Introduction Cursor Free Guides Cursor Developer Docs OpenClaw Introduction OpenClaw Free Guides OpenClaw Developer Docs Perplexity Introduction ElevenLabs Introduction Suno Introduction Manus Introduction Claude vs ChatGPT: Compare Them Without Borrowed Numbers Claude vs Gemini: Comparing Two Assistants Honestly Is Adobe Firefly Free? The Free Membership, the Credits and the First Year Adobe Firefly Pricing: Plans, Generative Credits and the Cost of One Image Adobe Firefly Video Cost: Credits per Second and per Clip Is Adobe Firefly Video Free? Where the Free Plan Stops FLUX.2 Prompt Guide: The Structure Black Forest Labs Documents FLUX.2 vs Nano Banana Pro: What Each Vendor Actually Publishes Ideogram 4.0 Prompt Guide: The Documented Structure and How Text Renders Ideogram Pricing: Plans, Credits and the Free Limits Midjourney Prompt Guide: Structure, Elements and Edit Instructions Midjourney Pricing: Four Plans, GPU Hours and What a Job Costs Nano Banana Pro Pricing: What Google Publishes and What It Does Not Nano Banana Pro vs Midjourney: Which One Fits Your Workflow Pika Credits: What One Pika 2.5 Video Costs Is Pika Free? What the $0 Plan Actually Includes What PixVerse Credits Cost, and Which Ledger You Are Paying Is PixVerse Free? Two Free Tiers, and What Each One Costs You Recraft V4.1: The Eight Variants and Which to Pick Recraft Pricing and the Free Plan: What the Vendor Publishes Seedance Official Website: Which Entrances Are First-Party Seedance 2.5 vs 2.0: The Parameters ByteDance Publishes Veo 3.1 vs Sora 2: What Each Vendor Still Confirms Veo 3.1 vs Kling 3.0: What Each Vendor Publishes Is Claude AI Free? What the $0 Plan Actually Gives You Claude Pricing Plans: Pro vs Max 5x vs Max 20x How to Use Adobe Firefly (Adobe Firefly Image 5) Adobe Firefly API: Credentials, Endpoints and the Image5 Schema How to Use Adobe Firefly Video Adobe Firefly Video API: /v3/videos/generate Explained Designing UI Mockups and App Screens with GPT Image 2.5 Sticker Packs and Transparent Emoji with GPT Image 2.5 Nano Banana Pro Prompt Guide: The Official Frameworks Is Nano Banana Pro Free? What Google Actually Confirms How to Use Pika 2.5 Pika API: the official developer site, billing and endpoints How to Use PixVerse PixVerse API: Platform, Endpoints and Credits How to Use ByteDance Seedance 2.5 Seedance API: The Real Endpoint, Model ID and Fields Veo 3.1 Prompt Guide: The Seven Elements Google Names Veo 3.1 Price and Free Access: The Official Numbers How to Use Claude AI Claude API: Getting Started How to Use FLUX AI: A FLUX.2 Getting-Started Guide FLUX.2 API: Getting Started with Black Forest Labs GPT Image 2.5 vs DALL·E 3 Making Infographics and Diagrams with GPT Image 2.5 How to Use Ideogram Ideogram API: Access, Endpoints and Text Rendering How to Use Midjourney V8.2 Midjourney API: What Exists and What Does Not How to Use Nano Banana Pro Nano Banana Pro API: Getting Started How to Use Recraft Recraft API: Access, Endpoints and Style Consistency How to Use Veo 3.1 Veo 3.1 API Pricing and Vertex AI Access GPT Image 2.5 Prompt Sharing GPT Image 2.5 vs Nano Banana 2 GPT Image 2.5 vs Seedream 5.0 Pro GPT Image 2.5 vs FLUX 2 GPT Image 2.5 vs Ideogram Is GPT Image 2.5 Free GPT Image 2.5 Sketch GPT Image 2.5 Templates GPT Image 2.5 Comment Editing GPT Image 2.5 Character Consistency GPT Image 2.5 Combine Images GPT Image 2.5 Text Rendering What Is GPT Image 2.5 GPT Image 2.5 API Overview Codex vs. ChatGPT: Which Should You Use? Codex app, CLI, IDE, or cloud: how to choose the right surface Your First Low-Risk Coding Task with Codex: A Safe Walkthrough What Is Cursor? Its AI Coding Workflow Explained Cursor vs. VS Code: Which Editor Fits Your Workflow? Cursor Features Explained: Agent, Tab, Context, and More What Is Gemini? Apps, Models, AI Studio, and API Explained Gemini Apps vs. Gemini API: How to Choose the Right Tool for the Job What Can Gemini Do? A Practical Capability Guide OpenClaw Foundation Explained: Governance and Independence OpenClaw Skill Workshop Guide: Review Reusable Workflows OpenClaw Skill Cards: Read ClawHub Security Scans OpenClaw 2.0 Guide: New Features and Upgrade Checks OpenClaw LTS Guide: Choosing extended-stable or stable Install OpenClaw: Desktop, Script, npm, and Source Options OpenClaw Node.js Setup: Versions, Installation, and PATH How to Write Better Codex Prompts: A Practical Framework How to Review Codex Code Changes Before You Commit Cursor Beginner Tutorial: From Install to First Reviewed Edit Cursor Rules Tutorial: Project Rules, User Rules, and AGENTS.md Install Cursor on Windows and Configure a Chinese Interface Cursor MCP Tutorial: Configure, Verify, and Secure MCP Servers Gemini Prompt Guide: Better Instructions and Templates Gemini API Quickstart: Key, Python SDK and First Call Gemini Web App Guide: Login, Files, Chats and Privacy Gemini API Key Security: Storage, Restrictions and Rotation What Is Codex? Capabilities, Limits, and Ways to Use It Codex Beginner Tutorial: Complete Your First Safe Task Install Codex CLI: Sign In and Run Your First Safe Task Codex AGENTS.md Guide: Layered Rules and Validation Codex CLI Commands: Sessions, Review, and Automation How to Use Gemini: Web, Android & iPhone Setup Gemini Features Guide: Chat, Files, Images & Live How to Chat with Gemini: Prompts, Follow-Ups & Live Gemini AI Image Generator Guide: Prompts & Editing Gemini vs GPT-4: Features, Limits & Which to Use Gemini AI Assistant Guide: Mobile, Apps & Privacy Gemini Prompt Engineering Guide: Patterns & Examples Gemini Chat API Guide: Multi-Turn Prompts in Python Gemini System Instructions: API Guide & Examples Gemini Context Caching Guide: Cost, Latency & API
AI Tool Blog Manus 1.6 reference hub

Understand Manus 1.6 before you delegate work to it.

Manus is a general-purpose AI agent, sold under the vendor’s own line “Less structure, more intelligence.” The current generation is Manus 1.6, and the flagship agent inside it is Manus 1.6 Max, published under an index date of 15 December 2025; the previous generation, Manus 1.5, is dated 16 October 2025. Manus does not disclose which language models any of them run on.

Version details, feature descriptions and positioning quotes on this page come from Manus’ own release post for Manus 1.6 Max, its About page, its engineering blog and its help pages. Prices, credit allowances and legal terms come from the Manus pricing page, the Manus Team page, the Terms of Use and the Privacy Policy — the pricing page builds its amounts client-side, so those figures were read from the rendered page.

Official examples

What Manus 1.6 Max looks like

Manus publishes no model output to show, so the gallery carries what it does publish: the 1.6 Max key art, two screenshots of the workspace running a real task, and the benchmark chart this page’s own claims come from. All four figures come from the release post.

Two hands reaching toward each other with the Manus wordmark above and the number 1.6 between them
The Manus 1.6 Max key art, published with the release.
A Manus workspace showing a written prompt beside six generated character illustrations in different colours
The Manus workspace generating six character illustrations from a written style brief.
A Manus workspace with a task log on the left and a phone preview of a Stillness Timer app on the right
The workspace building a meditation timer app and previewing it on a phone.
A bar chart comparing Manus 1.6 and Manus 1.6 Max scores across five task categories
The internal benchmark chart Manus published for 1.6 and 1.6 Max.

Images © Manus, from the Manus 1.6 Max release post

What it is

How Manus describes what it is

Manus calls itself a general AI agent, and its About page puts it as “We build general AI agents as the Action Engine for life.” The product is sold as a hosted service with one current generation rather than as a menu of models you choose between, and the vendor is unusually willing to name the parts of the loop.

01

A positioning line, not a specification

“Less structure, more intelligence” is Manus’ own description of the product, and the About page adds “Hands on AI.” The company’s blog calls the product “orthogonal to the underlying models”, which is consistent with the fact that no Manus page names one — so the pitch is about the loop around the model rather than about the model itself.

02

An action space, run in a sandbox

Manus describes its loop as the model that “selects an action from a predefined action space”, with each action executed “in the environment (e.g., Manus’s virtual machine sandbox)”. That sandbox is a product surface in its own right: Manus Sandbox is documented as “a fully isolated cloud virtual machine … for each task”, rather than the agent acting directly in your own session.

03

You keep ownership; Manus takes a licence

The Terms of Use do not claim ownership: “The Company does not claim ownership of any Input or Output (collectively, "Your Content"). Subject to Section 5.3, as between the Company and you, you are the owner of all right, title and interest in Your Content.” Section 5.3 then takes a licence, not ownership — including a perpetual and irrevocable right to use that content to improve the services and create Usage Data — and Section 6.1 repeats that the company does not own your input or output. The two halves are separate: you are the owner, and you have granted Manus a broad licence over what you own.

04

Three plans, one credit meter

The three individual plans are labelled by how much usage they cover rather than by a published tier name: “Standard monthly usage” at $20/mo, “Customizable monthly usage” at $40/mo and “Extended usage for productivity” at $200/mo, or $17, $34 and $167 per month billed yearly. Manus labels the annual toggle “Annually · Save 17%”, while the published per-credit arithmetic works out at 15.0%, 15.0% and 16.5%.

05

Independent again since September 2026

The Terms of Use name Butterfly Effect Pte. Ltd. as the contracting party and the site footer reads “© 2026 Manus AI · Singapore.” That arrangement changed: Manus joined Meta in December 2025 and then, in the vendor’s own words, “Manus has formally resumed independent operations” under an index date of 1 September 2026. Manus publishes no named country-level restriction, though the same post refers to “a temporary interruption to access” and a restoration portal.

Capabilities

What Manus documents

Manus documents its product through release posts, feature pages and an API reference rather than a single specification sheet, so this section carries only the features the vendor names and describes. Where a named feature has no published detail — what a skill may contain, or how a schedule is expressed — this page says so instead of filling it in.

01

Manus Sandbox

Documented as “a fully isolated cloud virtual machine … for each task”. It is the environment the agent’s actions are executed in, and the vendor treats it as the boundary that keeps a task’s work away from your own machine.

02

Manus Browser Operator

A browser extension, distributed through the “My Browser” Connector, which the vendor says “enables Manus to operate … within your local browser environment”. It is the documented route for work that depends on a browser you are already signed into.

03

Scheduled Tasks 2.0

Named by Manus as a feature of the product. The pages cited here do not publish a schedule syntax, a task limit or a minimum interval, so this page states none of those.

04

Manus Skills

Another feature Manus lists by name. No catalogue of what a skill can contain appears on the pages cited here, so there is no documented inventory to summarise.

05

API v2

Programmatic access, documented at open.manus.ai against the base URL https://api.manus.ai, where Manus states that “API v1 has been deprecated”. This page states no token-level rate: Manus meters usage in credits, and the pages cited publish credit allowances rather than per-token pricing.

06

Team and Enterprise

Seats are sold from the Manus Team page at “US$20 Per seat / month” or “US$200 Per seat / year”, carrying “4,000 credits / seat / month” that the vendor says are pooled. For paid tiers Manus states that it “explicitly prohibits model providers from training on our Team/Enterprise Plan customers’ data”.

Specifications

Documented specifications

Every row below is stated on a Manus-owned page. The pricing rows were read from the rendered pricing page, which assembles its amounts client-side, so the published digits only appear once the page has loaded.

Developer
Manus (Butterfly Effect Pte. Ltd.)
Current version
Manus 1.6
Flagship agent
Manus 1.6 Max
Published
15 December 2025
Previous release
Manus 1.5, 16 October 2025
Sandbox
A fully isolated cloud virtual machine per task
Interfaces
Web, iOS, Android, macOS, Windows, browser extension
API
v2, base https://api.manus.ai
Plans, monthly
$20 · $40 · $200
Plans, annual
$17 · $34 · $167 per month, billed yearly
Credits included
4,000 · 8,000 · 40,000 per month
Effective per credit
$0.0050 monthly; $0.00425 · $0.00425 · $0.00417 annual
Team
US$20 per seat / month · US$200 per seat / year
Underlying models
Not published
How to use it

Documented access channels

Manus is a hosted product reached through the vendor’s own clients, a documented API and a Team seat offering. Everything linked below is a Manus-owned page.

Manus web app

The primary surface, and the starting point for a task run in the Manus Sandbox. Mobile clients for iOS and Android and desktop builds for macOS and Windows are offered alongside it, plus the “My Browser” extension.

Open

Plans and credits

The three individual plans in monthly and annual billing, their credit allowances and the per-credit arithmetic — the page whose amounts are rendered client-side.

Open

API v2 documentation

Manus’ developer reference for programmatic access against the base URL https://api.manus.ai. Manus states there that API v1 has been deprecated.

Open

Team and Enterprise

The seat pricing, the pooled per-seat credit allowance and the training restriction Manus applies to Team and Enterprise plan data.

Open

The 1.6 Max release post

Manus’ own announcement for the version this page treats as current, and the source of most of its version and feature claims.

Open
Common questions

Manus 1.6 FAQ

Which version of Manus is current?

Manus 1.6, with Manus 1.6 Max as the flagship agent inside it. The vendor’s release post describes it as “our new flagship agent” and carries an index date of 15 December 2025; the previous release, Manus 1.5, is dated 16 October 2025.

Which language models does Manus run on?

Manus does not publish that, so this page does not state it. No Manus page names the language models behind Manus 1.6 or Manus 1.6 Max, and the company’s blog describes the product as “orthogonal to the underlying models”. Any list of models attributed to Manus is not drawn from the vendor’s own pages.

How much does Manus cost?

The three individual plans are $20, $40 and $200 a month, or $17, $34 and $167 per month billed yearly. They carry 4,000, 8,000 and 40,000 credits a month, the entry plan adding “300 refresh credits everyday” and the top plan a “Free Cloud Computer”. That is $0.0050 per credit on monthly billing and $0.00425, $0.00425 and $0.00417 on annual billing. Team seats are “US$20 Per seat / month” or “US$200 Per seat / year” with “4,000 credits / seat / month”. Add-on credit packs are bought in Team settings → Billing, and Manus publishes no public price list for them.

Who owns what I generate with Manus?

You own it, and Manus takes a licence over it — both halves are in the terms. The Terms of Use, last updated 28 November 2025, state: “The Company does not claim ownership of any Input or Output (collectively, "Your Content"). Subject to Section 5.3, as between the Company and you, you are the owner of all right, title and interest in Your Content.” Section 5.3 is the licence, not a transfer of ownership, and includes “a perpetual and irrevocable license to use Your Content in an aggregated manner to improve the Services … and create Usage Data”; Section 6.1 repeats that the company does not own your input or output.

Does this page show examples of Manus output?

No. Manus publishes no static figure of its own output on its homepage — the rendered page contains no product image and no video, and its brand page offers only logos. Static output figures do appear inside the vendor’s blog posts, but there is no official static figure on the product page for a gallery to reproduce, so this page carries none.

Who operates Manus, and where is it based?

The party named in the Terms of Use is Butterfly Effect Pte. Ltd., and the site footer reads “© 2026 Manus AI · Singapore.” The arrangement has changed: Manus joined Meta in December 2025, and on 1 September 2026 the company stated that “Manus has formally resumed independent operations”. Its help pages say that free credits and add-on credits never expire.