n8n
n8n (AI features: AI Agent, Assistant, MCP)
Provider: n8n GmbH · Based in: n8n GmbH, Novalisstr. 10, 10115 Berlin, Germany · Provider website
- Plans
- 4
- Sources
- 12
- As of
- 18 Oct
As of 18 Oct 2026. Based on our research on this date and the process described in the methodology. No guarantee of accuracy, not legal advice. The provider’s current documents take precedence. Found an error? Report a correction.
Incomplete. 3 points could not be verified in any provider source (see open points). This does not mean the matter is unproblematic; it means we have not checked it.
At a glance
- Hosting
- mixed: Starter, Pro, Enterprisenot publicly documented: Business
- Training on inputs
- no: all 4 plans
- DPA
- yes: all 4 plans
- Provider
- n8n GmbH
- Based in
- n8n GmbH, Novalisstr. 10, 10115 Berlin, Germany; Local Court (Amtsgericht) Charlottenburg, HRB 212509 B (q7)
Values from 4 plans, each listed with the plans it applies to. Details and evidence are in the plan table.
Compare n8n
Compare with another toolCompared plan by plan with other tools in the category Business software:
Details per plan
Short values per plan. Click a feature to open the evidence and notes for all plans; sources with retrieval dates are under “Evidence”.
| Feature | Starter (Cloud)Compare n8n Starter (Cloud) with another tool | Pro (Cloud)Compare n8n Pro (Cloud) with another tool | Business (self-hosted only)Compare n8n Business (self-hosted only) with another tool | Enterprise (cloud or self-hosted)Compare n8n Enterprise (cloud or self-hosted) with another tool |
|---|---|---|---|---|
| differs by plan | 20 EUR/mo… (further prices in the details) | 50 EUR/mo… (further prices in the details) | 667 EUR/mo… (further prices in the details) | custom |
| Details: Price | 20 EUR per month with annual payment; 2,500 workflow executions; 5 concurrent executions (pricing page: according to the page, annual payment saves 17%, with monthly payment 24 EUR per month; according to the Self-Serve Terms, all prices shown are exclusive of taxes) | 50 EUR per month with annual payment; 10,000 workflow executions; up to 50 concurrent executions (pricing page: according to the page, annual payment saves 17%, with monthly payment 60 EUR per month; according to the Self-Serve Terms, all prices shown are exclusive of taxes) | 667 EUR per month with annual payment; 40,000 workflow executions (pricing page: according to the page, annual payment saves 17%, with monthly payment 800 EUR per month; the Self-Serve Terms (cloud) and the Master Enterprise Terms each state prices exclusive of taxes; the pricing page does not state which terms apply to the self-hosted Business plan) | Custom, number of executions freely selectable (pricing page); according to the Master Enterprise Terms 'Fees are exclusive of taxes' |
| yes | yes | yes | yes | |
| Details: AI features included | yes (Agents, MCP and AI nodes; 1,600 Assistant credits/month; AI models without own API keys) | yes (up to 9,600 Assistant credits/month) | yes | yes |
| yes | yes | yes | yes | |
| Details: DPA | yes (DPA can be signed via link, template available for download) Provider’s DPA | yes (DPA can be signed via link, template available for download) Provider’s DPA | yes (DPA can be signed via link, template available for download) Provider’s DPA | yes (DPA can be signed via link, template available for download) Provider’s DPA |
| no | no | no | no | |
| Details: Training on inputs | Privacy policy: n8n does not use data from the website and services, including from third-party services/integrations, to train its own or third-party ML models. n8n AI Terms (as of 2026-07-06): n8n does not use customer content and outputs for training and does not store them longer than necessary for the AI feature; with 'bring your own LLM', the customer determines the model provider and its terms. The documentation does not differentiate by plan. However, the AI Terms allow n8n to use usage data and customer prompts internally in aggregated and de-identified form to improve AI services. Docs (Privacy): data sent to the Assistant is not used to train the AI services' models. | Privacy policy: n8n does not use data from the website and services, including from third-party services/integrations, to train its own or third-party ML models. n8n AI Terms (as of 2026-07-06): n8n does not use customer content and outputs for training and does not store them longer than necessary for the AI feature; with 'bring your own LLM', the customer determines the model provider and its terms. The documentation does not differentiate by plan. However, the AI Terms allow n8n to use usage data and customer prompts internally in aggregated and de-identified form to improve AI services. Docs (Privacy): data sent to the Assistant is not used to train the AI services' models. | Privacy policy: n8n does not use data from the website and services, including from third-party services/integrations, to train its own or third-party ML models. n8n AI Terms (as of 2026-07-06): n8n does not use customer content and outputs for training and does not store them longer than necessary for the AI feature; with 'bring your own LLM', the customer determines the model provider and its terms. The documentation does not differentiate by plan. However, the AI Terms allow n8n to use usage data and customer prompts internally in aggregated and de-identified form to improve AI services. Docs (Privacy): data sent to the Assistant is not used to train the AI services' models. | Privacy policy: n8n does not use data from the website and services, including from third-party services/integrations, to train its own or third-party ML models. n8n AI Terms (as of 2026-07-06): n8n does not use customer content and outputs for training and does not store them longer than necessary for the AI feature; with 'bring your own LLM', the customer determines the model provider and its terms. The documentation does not differentiate by plan. However, the AI Terms allow n8n to use usage data and customer prompts internally in aggregated and de-identified form to improve AI services. Docs (Privacy): data sent to the Assistant is not used to train the AI services' models. |
| n8n AI Terms: no retention of customer… | n8n AI Terms: no retention of customer… | n8n AI Terms: no retention of customer… | n8n AI Terms: no retention of customer… | |
| Details: Data retention | n8n AI Terms: no retention of customer content beyond the time necessary for AI processing and output. Security page: execution data is deleted automatically in accordance with the account's retention settings; audit logs at least 12 months. Cloud documentation: execution data max. 2,500 saved executions, 7 days (whichever limit is reached first applies; oldest deleted first). Self-Serve Terms: customer content is usually deleted 6 months after the deactivation of the account, unless a statutory retention obligation applies; usage data may be retained in aggregated or de-identified form. | n8n AI Terms: no retention of customer content beyond the time necessary for AI processing and output. Security page: execution data is deleted automatically in accordance with the account's retention settings; audit logs at least 12 months. Cloud documentation: execution data max. 25,000 saved executions, 30 days (whichever limit is reached first applies; oldest deleted first). Self-Serve Terms: customer content is usually deleted 6 months after the deactivation of the account, unless a statutory retention obligation applies; usage data may be retained in aggregated or de-identified form. | n8n AI Terms: no retention of customer content beyond the time necessary for AI processing and output. Self-hosted: retention and deletion of execution data are the customer's responsibility; the docs recommend automatic pruning via EXECUTIONS_DATA_MAX_AGE. Cloud limits do not apply, as Business is not offered in n8n Cloud. | n8n AI Terms: no retention of customer content beyond the time necessary for AI processing and output. Security page: execution data is deleted automatically in accordance with the account's retention settings; audit logs at least 12 months. Cloud documentation: execution data max. 50,000 saved executions, unlimited retention period (whichever limit is reached first applies). |
| differs by plan | mixed | mixed | not publicly documented | mixed |
| Details: Hosting | Security page: n8n Cloud runs on Microsoft Azure; hardware and data are currently located in the EU. For AI providers, the sub-processor list in some cases names processing in the USA and Singapore (in particular 'n8n Gateway' features). | Security page: n8n Cloud runs on Microsoft Azure; hardware and data are currently located in the EU. For AI providers, the sub-processor list in some cases names processing in the USA and Singapore (in particular 'n8n Gateway' features). | Pricing page: 'Self-hosted only'; according to the pricing FAQ there is no Business variant hosted by n8n yet ('Not yet', waiting list). Operation and location are the customer's responsibility; according to the docs, for workflow data of self-hosted instances n8n is 'neither a Controller nor a Processor'. Data flowing to n8n: licence and usage counts (including the number of production executions; with a paid licence also when telemetry is switched off), telemetry (active by default, can be switched off; no workflow data or credentials) and, when the Assistant is used, workflow context (nodes, schemas, configuration, code; no credentials or output data) to AI services, only after the workspace has opted in. | Security page: n8n Cloud runs on Microsoft Azure; hardware and data are currently located in the EU. For AI providers, the sub-processor list in some cases names processing in the USA and Singapore (in particular 'n8n Gateway' features). Enterprise: hosted by n8n or self-hosted (pricing page). |
| list available | list available | list available | list available | |
| Details: Sub-processors |
|
|
|
|
| differs by plan | 9 sources | 9 sources | 10 sources | 9 sources |
| Details: Sources with retrieval date |
|
|
|
|
Compare n8n Starter (Cloud) with another tool
Price and scope
- differs by plan
- 20 EUR/mo… (further prices in the details)
20 EUR per month with annual payment; 2,500 workflow executions; 5 concurrent executions (pricing page: according to the page, annual payment saves 17%, with monthly payment 24 EUR per month; according to the Self-Serve Terms, all prices shown are exclusive of taxes)
- yes
yes (Agents, MCP and AI nodes; 1,600 Assistant credits/month; AI models without own API keys)
Contract and data use
- yes
yes (DPA can be signed via link, template available for download)
Provider’s DPA- no
Privacy policy: n8n does not use data from the website and services, including from third-party services/integrations, to train its own or third-party ML models. n8n AI Terms (as of 2026-07-06): n8n does not use customer content and outputs for training and does not store them longer than necessary for the AI feature; with 'bring your own LLM', the customer determines the model provider and its terms. The documentation does not differentiate by plan. However, the AI Terms allow n8n to use usage data and customer prompts internally in aggregated and de-identified form to improve AI services. Docs (Privacy): data sent to the Assistant is not used to train the AI services' models.
- n8n AI Terms: no retention of customer…
- n8n AI Terms: no retention of customer content beyond the time necessary for AI processing and output. Security page: execution data is deleted automatically in accordance with the account's retention settings; audit logs at least 12 months. Cloud documentation: execution data max. 2,500 saved executions, 7 days (whichever limit is reached first applies; oldest deleted first). Self-Serve Terms: customer content is usually deleted 6 months after the deactivation of the account, unless a statutory retention obligation applies; usage data may be retained in aggregated or de-identified form.
Hosting and sharing
- differs by plan
- mixed
Security page: n8n Cloud runs on Microsoft Azure; hardware and data are currently located in the EU. For AI providers, the sub-processor list in some cases names processing in the USA and Singapore (in particular 'n8n Gateway' features).
- list available
- Microsoft Azure (cloud hosting): processing EU (e.g. Germany, Sweden)
- AI providers: OpenAI (USA), Anthropic (Anthropic Ireland Limited; processing USA), Google Enterprise Agent Platform (EU, USA), LangChain, Inc. (USA)
- Inference/sandbox: Modal Labs (USA), Baseten Labs (EU), Daytona Platforms (USA, sandbox for AI Assistant)
- n8n Gateway: Firecrawl, Brave Software, Browserbase, PDF.co (USA), LlamaIndex (EU), Moonshot AI (Singapore), Alibaba Qwen (EU), Nanonoble Pte. Ltd. (Singapore; processing USA according to the list)
- Group: n8n US Inc. (USA), n8n UK Ltd. (United Kingdom)
- Community forum: Hetzner Online (Germany)
Evidence
- differs by plan
- 9 sources
- PricingPricing page, retrieved 18 Oct 2026
- SecurityTrust Center, retrieved 18 Oct 2026
- Privacy Policy (as of 2026-09-28)Privacy notice, retrieved 18 Oct 2026
- Sub-processors (as of 2026-09-22)Sub-processor list, retrieved 18 Oct 2026
- Data Processing AgreementDPA, retrieved 18 Oct 2026
- n8n AI Terms (as of 2026-07-06)Terms and conditions, retrieved 18 Oct 2026
- n8n Docs: Manage your data (cloud execution data)Documentation, retrieved 18 Oct 2026
- n8n Self-Serve Terms (as of 2026-08-28)Terms and conditions, retrieved 18 Oct 2026
- n8n Docs: Privacy (self-hosted, telemetry, AI features)Documentation, retrieved 18 Oct 2026
not documentedmeans: not publicly documented, not verifiable in any provider source. It does not mean “no”.
Third-country transfers
Privacy policy (as of 2026-09-28): recipients may be located outside the EU/EEA, in particular in the USA; transfers take place on the basis of adequacy decisions such as the EU-US Data Privacy Framework, standard contractual clauses and technical and organisational measures. Docs (Privacy): the DPA includes the standard contractual clauses. Transfer basis per sub-processor: stated neither in the list nor in the privacy policy or Trust Center.
- Privacy Policy (as of 2026-09-28) (Privacy notice), retrieved 18 Oct 2026
- Sub-processors (as of 2026-09-22) (Sub-processor list), retrieved 18 Oct 2026
- n8n Trust Center (SafeBase) (Trust Center), retrieved 18 Oct 2026
- n8n Docs: Privacy (self-hosted, telemetry, AI features) (Documentation), retrieved 18 Oct 2026
Certifications (as stated by the provider)
Security page: n8n aligns its security programme with SOC 2 (annual independent audit); the SOC 2 report is available to Enterprise customers, a SOC 3 report is public. The Trust Center (SafeBase) lists GDPR, SOC 2 Type 2 and SOC 3 under compliance; only the SOC 3 report is public, the SOC 2 report, pentest report, CAIQ (cloud/self-hosted) and policies only on access request. An ISO 27001 certification is named neither on the security page nor in the Trust Center.
- Security (Trust Center), retrieved 18 Oct 2026
- n8n Trust Center (SafeBase) (Trust Center), retrieved 18 Oct 2026
AI Act
Functions: AI nodes and AI Agents in the workflow editor, MCP, n8n Assistant (credits), AI models without own API keys, 'Bring your own LLM' and Gateway services (web search, scraping, document extraction) (pricing page, AI Terms, sub-processor list).
Provider’s statement: not publicly documented(no mention of the EU AI Act in the AI Terms, Self-Serve Terms, Master Enterprise Terms, Acceptable Use Policy, privacy policy, security page, DPA page or Trust Center; as of 2026-10-18). AI Terms: AI outputs may contain errors; the customer reviews them before productive use; no use for high-risk purposes where errors could result in death, serious physical injury or significant legal liability; use 'in compliance with applicable laws, including AI-specific regulations'.
Classification (for review, not legal advice): For review: customer typically a deployer (Art. 3 No. 4 AI Act). Which obligations apply depends on the workflows and agents built (check Annex III). With 'bring your own LLM', the customer chooses the model and provider itself. Not legal advice.
- Pricing (Pricing page), retrieved 18 Oct 2026
- n8n AI Terms (as of 2026-07-06) (Terms and conditions), retrieved 18 Oct 2026
- n8n Self-Serve Terms (as of 2026-08-28) (Terms and conditions), retrieved 18 Oct 2026
- n8n Master Enterprise Terms (version 08.2026) (Terms and conditions), retrieved 18 Oct 2026
- n8n Trust Center (SafeBase) (Trust Center), retrieved 18 Oct 2026
Current notes 2026
Sub-processor list dated 2026-09-22, privacy policy 2026-09-28, AI Terms 2026-07-06. According to the pricing page, in addition to the cloud, n8n offers a self-hosted Community Edition (GitHub). For 'n8n Gateway', the list also names AI providers based in Singapore.
Open points of the review
- Transfer basis per sub-processor not stated; the sample DPA is only offered as a download and was not evaluated.
- SOC 2 report, pentest report and CAIQ in the Trust Center only on access request ('Get access'), not inspected.
- For self-hosting, it is not documented via which sub-processors n8n-hosted AI features (Assistant, AI credits) run; the list refers to the cloud service.
Frequently asked questions
Where does n8n store data?
mixed (plans: Starter (Cloud), Pro (Cloud), Enterprise (cloud or self-hosted)); not publicly documented (plans: Business (self-hosted only)). Based on our research, as of 18 Oct 2026.
Is there a DPA for n8n?
yes in: Starter (Cloud), Pro (Cloud), Business (self-hosted only), Enterprise (cloud or self-hosted). According to the provider, as of 18 Oct 2026.
Does n8n use inputs for AI training?
no in: Starter (Cloud), Pro (Cloud), Business (self-hosted only), Enterprise (cloud or self-hosted). According to the provider, as of 18 Oct 2026.
Where is the provider based?
n8n GmbH, Novalisstr. 10, 10115 Berlin, Germany; Local Court (Amtsgericht) Charlottenburg, HRB 212509 B. According to the provider, as of 18 Oct 2026.
All sources
- 01PricingPricing page · retrieved 18 Oct 2026
- 02SecurityTrust Center · retrieved 18 Oct 2026
- 03Privacy Policy (as of 2026-09-28)Privacy notice · retrieved 18 Oct 2026
- 04Sub-processors (as of 2026-09-22)Sub-processor list · retrieved 18 Oct 2026
- 05Data Processing AgreementDPA · retrieved 18 Oct 2026
- 06n8n AI Terms (as of 2026-07-06)Terms and conditions · retrieved 18 Oct 2026
- 07ImprintLegal notice · retrieved 18 Oct 2026
- 08n8n Docs: Manage your data (cloud execution data)Documentation · retrieved 18 Oct 2026
- 09n8n Self-Serve Terms (as of 2026-08-28)Terms and conditions · retrieved 18 Oct 2026
- 10n8n Master Enterprise Terms (version 08.2026)Terms and conditions · retrieved 18 Oct 2026
- 11n8n Trust Center (SafeBase)Trust Center · retrieved 18 Oct 2026
- 12n8n Docs: Privacy (self-hosted, telemetry, AI features)Documentation · retrieved 18 Oct 2026
More tools in Business software with an EU hosting option (in at least one plan)
- DATEV AI features · Based in: Paumgartnerstraße 6-14, 90429 Nürnberg, Germany
- HubSpot Breeze AI · Based in: Cambridge, MA, USA
- Intercom Fin · Based in: Intercom R&D Unlimited Company, 124 St Stephen's Green, Dublin 2, DC02 C628, Ireland
- Lexware Office · Based in: Munzinger Straße 9, 79111 Freiburg, Germany. Contracting party and processor according to the DPA and privacy notice: Haufe Service Center GmbH
All tools in Business software · Tools with an EU hosting option
Further reading
All tools in the category: Business software. Figures across all tools: Data report.