Agent AI / automation / content

Manus

  • Free daily 300 credits

    Manus 1.6 Lite only.

  • Pro monthly from $20

    4,000 or 8,000 credits. Variants 1.6 Lite, 1.6 and 1.6 Max.

  • Team per user from $20

    The same three variants as Pro. 17% less on annual billing.

Since 09/01/2026 Manus operates on its own again. China's NDRC blocked the Meta acquisition on 04/27/2026.

  • Verified2026-09-03
  • Models covered3
  • Sources8
  • Deployment channels4

Purchase decision (when to choose / when to avoid)

Choose if...

  • You want autonomous execution of complex tasks (research, reports, automations), not just chat.
  • You have marketing-analytical processes that can be wrapped into agentic workflows with MCP connectors.
  • You need 'end-to-end' results, not just suggestions and prompts.

Avoid if...

  • You need predictable unit costs (credit-based can be variable).
  • You have strict data requirements (residency, owner outside the EU/US) - demand clear enterprise terms.

Cost in practice (scenarios)

Marketing team (agent for research + content)

Pro from $20/mo (4,000 credits) or $40/mo (8,000); Team from $20 per seat with a shared credit pool.

  • campaigns, briefs, reports
  • 20 parallel tasks on Pro
Company automations

Credits depend on tokens, VM time and external APIs - less predictable than tokens; need limits and monitoring.

  • multi-step tasks
  • add-on credits do not expire while the subscription is active
These are estimates/scenarios (not an invoice). Actual cost depends on context length, number of users, limits and retention policies.

Deployment / data / enterprise

Deployment channels

  • Manus (web and desktop app) - agentic platform
  • Slack, Zapier (8,000+ apps), Browser Operator
  • MCP connectors (Gmail, Drive, Notion, HubSpot, Stripe, GitHub, Shopify, Zoom) and custom MCP servers
  • Manus API (REST, api.manus.ai; webhooks, skills, connectors)

Data policy

Training on data
Team/Enterprise: Manus prohibits model providers from training on customer data; individual plans per terms.
Retention
Customer data deleted on departure; data created since 12/29/2025 was deleted on 08/23-24/2026 after the Meta separation.
Data residency
Data stored in the US and Singapore; residency is not published.
For companies: key are logs, agent action audit and data policies.

Enterprise readiness

Admin
Team: shared credit pool and user management; Enterprise custom.
SSO/SCIM
SSO free from 30 seats, below that a flat $150 + tax.
Audit
Audit logs in Team/Enterprise plans.
DPA
Depends on agreement.
Certifications
SOC 2 Type 1 and Type 2, ISO 27001:2022, ISO 27701:2019.
Best when you want agent autonomy - but watch governance and credit costs.

Best use cases

  • complex, multi-step tasks executed autonomously (research, reports, data analysis, slides)
  • content automation: product descriptions, briefs, translations, campaigns; recurring jobs (Scheduled Tasks)
  • work across hundreds of items at once (Wide Research) and integrations via MCP connectors and the API.

Strengths

  • Autonomous agency: planning + execution + result delivery end-to-end; Plan Mode with plan approval.
  • MCP connectors (Gmail, Google Drive, Notion, HubSpot, Stripe, GitHub, Shopify, Zoom), Slack, Zapier, Browser Operator; Manus API (REST).
  • Public pricing (Free, Pro, Team) and certifications: SOC 2 Type 1 and 2, ISO 27001:2022, ISO 27701:2019; no training on Team/Enterprise data.

Weaknesses / risks

  • Cost hard to predict (credits depend on tokens, VM time and external APIs; no upfront pricing).
  • Chinese-capital owner (Tencent), Singapore HQ, data in the US and Singapore; after the Meta separation in 08/2026, user data created since 12/29/2025 was deleted.
  • Shorter enterprise history than OpenAI/Google; data residency is not published.

Current models (examples)

  • Manus 1.6 Max (flagship), Manus 1.6 and Manus 1.6 Lite (12/15/2025); Free gets Lite only, Pro and Team get all three.
  • Wide Research: parallel sub-agents for tasks spanning hundreds of items; Plan Mode (07/22/2026) with plan approval before execution.
  • Manus API (REST, api.manus.ai) and MCP connectors: Gmail, Google Calendar, Drive, Notion, HubSpot, Stripe, GitHub, Slack, Zapier, Shopify, Zoom, ElevenLabs.

Alternatives (if this model doesn't fit)

OP
OpenAI
custom agents and tools in API - more control
CL
Claude
stable tool use + safety
GR
Grok
cheap long contexts for agents (depending on model)