Cohere vs. n8n: data protection per plan
Cohere (3 plans) and n8n (4 plans) side by side: DPA, training on inputs, hosting and data retention per plan, based on the providers’ public documents. Without rating.
Last updated: (latest review date of the tools shown)
At a glance
Each value is listed with the plans it applies to. Pick a tier to see only plans of that tier; if plans are chosen in the plan comparison below, the table shows exactly those.
All plans: each value is listed with the plans it applies to.
| Feature | Cohere | n8n |
|---|---|---|
| Provider based in | Cohere Inc., 171 John Street, Suite 200, Toronto, ON M5T 1X3, Canada | n8n GmbH, Novalisstr. 10, 10115 Berlin, Germany |
| Plans recorded | 3 | 4 |
| Hosting | US only: API Trial, API Productionnot documented: Enterprise: North, Compass, Model Vault, private deployment | mixed: Starter, Pro, Enterprisenot documented: Business |
| Training on inputs | yes: API Trialno: Enterprise: North, Compass, Model Vault, private deploymentopt-out available: API Production | no: all 4 plans |
| DPA | no: API Trialyes: Enterprise: North, Compass, Model Vault, private deployment, API Production | yes: all 4 plans |
| As of | 18 Oct 2026 | 18 Oct 2026 |
Plans compared
Comparing: Cohere Enterprise: North, Compass, Model Vault, private deployment vs. n8n Enterprise
| Feature | CohereEnterprise: North, Compass, Model Vault, private deployment | n8nEnterprise (cloud or self-hosted) |
|---|---|---|
| yes | yes | |
| Details: DPA available | yes for SaaS/Model Vault customers on request (privacy@cohere.com, sent after NDA; the DPA contains the EU standard contractual clauses of 2021-06-04). According to the Enterprise Data Commitments, no DPA is required for private and third-party cloud deployments. | yes (DPA can be signed via link, template available for download) Provider’s DPA |
| no | no | |
| Details: Training on inputs | Enterprise Data Commitments: for private and third-party cloud deployments, Cohere does not receive prompts and generations. Privacy policy: data in the customer's or cloud provider's environment is not accessible to Cohere and is not used for training. Model Vault as a platform managed by Cohere: use for training not separately addressed in the documentation or the Enterprise Data Commitments; for Encrypted Vault, prompts and responses are, according to the documentation, not visible in plaintext even to Cohere. | 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. |
| differs by plan | not publicly documented | mixed |
| Details: Data residency | Region depends on the deployment at the customer or the cloud provider. Model Vault (Cohere-managed, single-tenant): documentation 'Compliance' for Encrypted Vault: 'Region selection supports data-residency requirements; contact Cohere to confirm the regions available for your vault.' There is no public list of regions. | 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 | |
| Details: List published |
|
|
| differs by plan | Private and third-party deployments… | n8n AI Terms: no retention of customer… |
| Details: Data retention | Private and third-party deployments: according to the Enterprise Data Commitments, Cohere has no access to prompts and generations. Model Vault: according to the documentation, with Zero Data Retention (ZDR) enabled, Cohere processes inputs and outputs only for inference and does not store any prompts or responses (Standard Vault and Encrypted Vault); retention periods without ZDR: not publicly documented. | 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 | North and Compass: custom | custom |
| Details: Price | North and Compass: custom (pricing page). Model Vault (Standard Vault) per instance, in USD, per hour / per month / per year (documentation 'Standard Vault Pricing'): Embed 5 Fast and Embed 5 Pro Small USD 3 / USD 2,000 / USD 20,000, Medium USD 5 / USD 3,250 / USD 32,500; Rerank 4 Fast, Rerank 4 Pro and Rerank 3.5 Medium USD 5 / USD 3,250 / USD 32,500; Rerank 4 Pro Large USD 10 / USD 6,500 / USD 65,000; Parse 5 Medium USD 4 / USD 2,500 / USD 25,000, Large USD 8 / USD 5,000 / USD 50,000, XL USD 7 / USD 4,300 / USD 43,000; Cohere Transcribe Medium USD 3.75 / USD 2,500 / USD 25,000, Large USD 7.50 / USD 4,750 / USD 47,500. Generative models on Standard Vault (mostly via waitlist) per instance and hour, L / XL: Command A USD 40 / USD 48, Command A Reasoning USD 48 / USD 57.50, Command A+ USD 17.50 / USD 32.50, North Mini Code USD 7.50 / USD 10.50. Encrypted Vault priced separately. According to the Terms of Use, prices, except where otherwise indicated, do not include applicable sales taxes ('do not include any applicable sales taxes'). | Custom, number of executions freely selectable (pricing page); according to the Master Enterprise Terms 'Fees are exclusive of taxes' |
| yes | yes | |
| Details: AI features included | yes (workplace platform North, search system Compass, dedicated model instances 'Model Vault' incl. Transcribe, deployment in a VPC or on-premises as well as via the cloud platforms of OCI, Azure, AWS, Google Cloud) | yes |
| 6 sources | 9 sources | |
| Details: Sources with retrieval date |
|
|
Contract / DPA
- Cohere Enterprise: North, Compass, Model Vault, private deploymentyes
- n8n Enterpriseyes
- Cohere Enterprise: North, Compass, Model Vault, private deployment
yes for SaaS/Model Vault customers on request (privacy@cohere.com, sent after NDA; the DPA contains the EU standard contractual clauses of 2021-06-04). According to the Enterprise Data Commitments, no DPA is required for private and third-party cloud deployments.
Training
- Cohere Enterprise: North, Compass, Model Vault, private deploymentno
- n8n Enterpriseno
- Cohere Enterprise: North, Compass, Model Vault, private deployment
Enterprise Data Commitments: for private and third-party cloud deployments, Cohere does not receive prompts and generations. Privacy policy: data in the customer's or cloud provider's environment is not accessible to Cohere and is not used for training. Model Vault as a platform managed by Cohere: use for training not separately addressed in the documentation or the Enterprise Data Commitments; for Encrypted Vault, prompts and responses are, according to the documentation, not visible in plaintext even to Cohere.
n8n EnterprisePrivacy 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.
Hosting
- differs by plan
- Cohere Enterprise: North, Compass, Model Vault, private deploymentnot publicly documented
- n8n Enterprisemixed
- Cohere Enterprise: North, Compass, Model Vault, private deployment
Region depends on the deployment at the customer or the cloud provider. Model Vault (Cohere-managed, single-tenant): documentation 'Compliance' for Encrypted Vault: 'Region selection supports data-residency requirements; contact Cohere to confirm the regions available for your vault.' There is no public list of regions.
n8n EnterpriseSecurity 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).
Sub-processors
- Cohere Enterprise: North, Compass, Model Vault, private deploymentlist available
- n8n Enterpriselist available
- Cohere Enterprise: North, Compass, Model Vault, private deployment
- Google Cloud (infrastructure): USA
- Fullstory (software delivery): USA
- LaunchDarkly (feature flags): USA
- New Relic (platform monitoring): USA
- Retool (software delivery): USA
- Sentry IO (software delivery): USA
- Segment (event and error processing): USA
- Sendgrid (e-mail communication): USA
- Vercel (web application hosting): USA
- Salesforce (customer support management): USA
- Wiz (cloud security and compliance): USA
- Forethought (customer support management): USA
n8n Enterprise- 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)
Retention
- differs by plan
- Cohere Enterprise: North, Compass, Model Vault, private deploymentPrivate and third-party deployments…
- n8n Enterprisen8n AI Terms: no retention of customer…
- Cohere Enterprise: North, Compass, Model Vault, private deploymentPrivate and third-party deployments: according to the Enterprise Data Commitments, Cohere has no access to prompts and generations. Model Vault: according to the documentation, with Zero Data Retention (ZDR) enabled, Cohere processes inputs and outputs only for inference and does not store any prompts or responses (Standard Vault and Encrypted Vault); retention periods without ZDR: not publicly documented.n8n Enterprisen8n 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).
Price
- differs by plan
- Cohere Enterprise: North, Compass, Model Vault, private deploymentNorth and Compass: custom
- n8n Enterprisecustom
- Cohere Enterprise: North, Compass, Model Vault, private deployment
North and Compass: custom (pricing page). Model Vault (Standard Vault) per instance, in USD, per hour / per month / per year (documentation 'Standard Vault Pricing'): Embed 5 Fast and Embed 5 Pro Small USD 3 / USD 2,000 / USD 20,000, Medium USD 5 / USD 3,250 / USD 32,500; Rerank 4 Fast, Rerank 4 Pro and Rerank 3.5 Medium USD 5 / USD 3,250 / USD 32,500; Rerank 4 Pro Large USD 10 / USD 6,500 / USD 65,000; Parse 5 Medium USD 4 / USD 2,500 / USD 25,000, Large USD 8 / USD 5,000 / USD 50,000, XL USD 7 / USD 4,300 / USD 43,000; Cohere Transcribe Medium USD 3.75 / USD 2,500 / USD 25,000, Large USD 7.50 / USD 4,750 / USD 47,500. Generative models on Standard Vault (mostly via waitlist) per instance and hour, L / XL: Command A USD 40 / USD 48, Command A Reasoning USD 48 / USD 57.50, Command A+ USD 17.50 / USD 32.50, North Mini Code USD 7.50 / USD 10.50. Encrypted Vault priced separately. According to the Terms of Use, prices, except where otherwise indicated, do not include applicable sales taxes ('do not include any applicable sales taxes').
n8n EnterpriseCustom, number of executions freely selectable (pricing page); according to the Master Enterprise Terms 'Fees are exclusive of taxes'
- Cohere Enterprise: North, Compass, Model Vault, private deploymentyes
- n8n Enterpriseyes
- Cohere Enterprise: North, Compass, Model Vault, private deployment
yes (workplace platform North, search system Compass, dedicated model instances 'Model Vault' incl. Transcribe, deployment in a VPC or on-premises as well as via the cloud platforms of OCI, Azure, AWS, Google Cloud)
n8n Enterpriseyes
Evidence
- Cohere Enterprise: North, Compass, Model Vault, private deployment6 sources
- n8n Enterprise9 sources
- Cohere Enterprise: North, Compass, Model Vault, private deployment
- PricingPricing page, retrieved 18 Oct 2026
- Enterprise Data Commitments (as of 2025-12-05)Documentation, retrieved 18 Oct 2026
- Cohere Trust CenterTrust Center, retrieved 18 Oct 2026
- Privacy Policy (as of 2026-05-01)Privacy notice, retrieved 18 Oct 2026
- Terms of Use (as of 2022-09-07)Terms and conditions, retrieved 18 Oct 2026
- Model Vault Overview, Standard Vault Pricing, Encrypted Vault ComplianceDocumentation, retrieved 18 Oct 2026
n8n Enterprise- 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 Master Enterprise Terms (version 08.2026)Terms and conditions, retrieved 18 Oct 2026
- n8n Docs: Privacy (self-hosted, telemetry, AI features)Documentation, retrieved 18 Oct 2026
| Feature | Cohere | n8n |
|---|---|---|
| differs by tool |
| yesall 4 plans |
| Details: DPA available |
|
|
| differs by tool |
| noall 4 plans |
| Details: Training on inputs |
|
|
| differs by tool |
|
|
| Details: Data residency |
|
|
| list availableall 3 plans | list availableall 4 plans | |
| Details: List published |
|
|
| differs by tool |
| n8n AI Terms: no retention of customer…all 4 plans |
| Details: Data retention |
|
|
| differs by tool |
|
|
| Details: Price |
|
|
| yesall 3 plans | yesall 4 plans | |
| Details: AI features included |
|
|
| 7 sources | 10 sources | |
| Details: Sources with retrieval date |
|
|
Contract / DPA
- differs by tool
- Cohere
- noAPI Trial (free of charge)
- yesEnterprise: North, Compass, Model Vault, private deployment, API Production (Pay-as-you-go, SaaS)
- n8nyesall 4 plans
- Cohere
- API Trial (free of charge)
no (trial keys are subject to the terms of use and privacy policy; the Enterprise Data Commitments and the DPA offer apply to paying SaaS customers. Privacy policy: trial environments are not intended for personal data; for that, switch to an enterprise plan with a contract)
- Enterprise: North, Compass, Model Vault, private deployment
yes for SaaS/Model Vault customers on request (privacy@cohere.com, sent after NDA; the DPA contains the EU standard contractual clauses of 2021-06-04). According to the Enterprise Data Commitments, no DPA is required for private and third-party cloud deployments.
- API Production (Pay-as-you-go, SaaS)
yes (on request: SaaS customers receive the DPA via privacy@cohere.com; according to the Trust Center, sent after a signed NDA)
n8n- Starter (Cloud)
yes (DPA can be signed via link, template available for download)
Provider’s DPA - Pro (Cloud)
yes (DPA can be signed via link, template available for download)
Provider’s DPA - Business (self-hosted only)
yes (DPA can be signed via link, template available for download)
Provider’s DPA - Enterprise (cloud or self-hosted)
yes (DPA can be signed via link, template available for download)
Provider’s DPA
- API Trial (free of charge)
Training
- differs by tool
- Cohere
- yesAPI Trial (free of charge)
- noEnterprise: North, Compass, Model Vault, private deployment
- opt-out availableAPI Production (Pay-as-you-go, SaaS)
- n8nnoall 4 plans
- Cohere
- API Trial (free of charge)
Privacy policy (as of 2026-05-01, section 2.3): for Trial Users and Researchers, Cohere collects inputs and outputs and may use them for research and development, including 'using inputs/outputs to improve the performance and safety of Cohere Products'; data is de-identified beforehand; users should not enter personal data. An opt-out for trial keys is not described (the dashboard switch 'Data Controls' is described in the Enterprise Data Commitments for paying customers). According to the Enterprise Data Commitments, the Terms of Use and the privacy policy apply to trial keys; the Terms of Use (as of 2022-09-07, section 4.1) allow Cohere to use 'Customer Data', among other things, to 'IMPROVE AND ENHANCE THE COHERE SOLUTION' and other offerings, including by sharing API data and fine-tuning data with third parties.
- Enterprise: North, Compass, Model Vault, private deployment
Enterprise Data Commitments: for private and third-party cloud deployments, Cohere does not receive prompts and generations. Privacy policy: data in the customer's or cloud provider's environment is not accessible to Cohere and is not used for training. Model Vault as a platform managed by Cohere: use for training not separately addressed in the documentation or the Enterprise Data Commitments; for Encrypted Vault, prompts and responses are, according to the documentation, not visible in plaintext even to Cohere.
- API Production (Pay-as-you-go, SaaS)
Enterprise Data Commitments (as of 2025-12-05): opt-out from the use of prompts and generations for training in the dashboard settings ('Data Controls', switch set to 'Off'); the change applies to data generated thereafter. For abuse monitoring, prompts and logs may be reviewed; PII is filtered before any possible use for training. Model Training Privacy Notice (as of 2026-05-01): 'Where a user has given Cohere permission to use inputs and outputs for model training', the data is de-identified beforehand. Default value of the switch for new accounts: not publicly documented.
n8n- Starter (Cloud)
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.
- Pro (Cloud)
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.
- Business (self-hosted only)
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.
- Enterprise (cloud or self-hosted)
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.
- API Trial (free of charge)
Hosting
- differs by tool
- Cohere
- US onlyAPI Trial (free of charge), API Production (Pay-as-you-go, SaaS)
- not publicly documentedEnterprise: North, Compass, Model Vault, private deployment
- n8n
- mixedStarter (Cloud), Pro (Cloud), Enterprise (cloud or self-hosted)
- not publicly documentedBusiness (self-hosted only)
- Cohere
- API Trial (free of charge)
Trust Center FAQ: hosting on Google Cloud servers in US-Central; according to the FAQ, Cohere does not use servers outside the USA.
- Enterprise: North, Compass, Model Vault, private deployment
Region depends on the deployment at the customer or the cloud provider. Model Vault (Cohere-managed, single-tenant): documentation 'Compliance' for Encrypted Vault: 'Region selection supports data-residency requirements; contact Cohere to confirm the regions available for your vault.' There is no public list of regions.
- API Production (Pay-as-you-go, SaaS)
Trust Center FAQ: hosting on Google Cloud servers in US-Central. According to the FAQ, in certain cases the offering can be configured so that no customer data is stored at Cohere ('ephemeral').
n8n- Starter (Cloud)
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).
- Pro (Cloud)
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).
- Business (self-hosted only)
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.
- Enterprise (cloud or self-hosted)
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).
- API Trial (free of charge)
Sub-processors
- Coherelist availableall 3 plans
- n8nlist availableall 4 plans
- Cohere
- API Trial (free of charge)
- Google Cloud (infrastructure): USA
- Fullstory (software delivery): USA
- LaunchDarkly (feature flags): USA
- New Relic (platform monitoring): USA
- Retool (software delivery): USA
- Sentry IO (software delivery): USA
- Segment (event and error processing): USA
- Sendgrid (e-mail communication): USA
- Vercel (web application hosting): USA
- Salesforce (customer support management): USA
- Wiz (cloud security and compliance): USA
- Forethought (customer support management): USA
- Enterprise: North, Compass, Model Vault, private deployment
- Google Cloud (infrastructure): USA
- Fullstory (software delivery): USA
- LaunchDarkly (feature flags): USA
- New Relic (platform monitoring): USA
- Retool (software delivery): USA
- Sentry IO (software delivery): USA
- Segment (event and error processing): USA
- Sendgrid (e-mail communication): USA
- Vercel (web application hosting): USA
- Salesforce (customer support management): USA
- Wiz (cloud security and compliance): USA
- Forethought (customer support management): USA
- API Production (Pay-as-you-go, SaaS)
- Google Cloud (infrastructure): USA
- Fullstory (software delivery): USA
- LaunchDarkly (feature flags): USA
- New Relic (platform monitoring): USA
- Retool (software delivery): USA
- Sentry IO (software delivery): USA
- Segment (event and error processing): USA
- Sendgrid (e-mail communication): USA
- Vercel (web application hosting): USA
- Salesforce (customer support management): USA
- Wiz (cloud security and compliance): USA
- Forethought (customer support management): USA
n8n- Starter (Cloud)
- 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)
- Pro (Cloud)
- 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)
- Business (self-hosted only)
- 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)
- Enterprise (cloud or self-hosted)
- 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)
- API Trial (free of charge)
Retention
- differs by tool
- Cohere
- Privacy policy: the platform is not…API Trial (free of charge)
- Private and third-party deployments…Enterprise: North, Compass, Model Vault, private deployment
- Logged prompts and generations are…API Production (Pay-as-you-go, SaaS)
- n8nn8n AI Terms: no retention of customer…all 4 plans
- Cohere
- API Trial (free of charge)Privacy policy: the platform is not intended for the processing of personal data by Trial Users; personal data entered by mistake can be erased by e-mail to privacy@cohere.com. Fixed periods for trial data: not publicly documented.
- Enterprise: North, Compass, Model Vault, private deploymentPrivate and third-party deployments: according to the Enterprise Data Commitments, Cohere has no access to prompts and generations. Model Vault: according to the documentation, with Zero Data Retention (ZDR) enabled, Cohere processes inputs and outputs only for inference and does not store any prompts or responses (Standard Vault and Encrypted Vault); retention periods without ZDR: not publicly documented.
- API Production (Pay-as-you-go, SaaS)Logged prompts and generations are automatically deleted after 30 days, except where there is a legal or contractual obligation or a suspected breach of the usage policy (Enterprise Data Commitments; privacy policy: 'generally 30 days' for Enterprise Users). Data released for training purposes may be retained separately. Zero Data Retention (no logging of prompts and generations) only for enterprise customers with additional usage commitments; Cohere still receives usage data.
n8n- Starter (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. 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.
- Pro (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. 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.
- Business (self-hosted only)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.
- Enterprise (cloud or self-hosted)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).
Price
- differs by tool
- Cohere
- freeAPI Trial (free of charge)
- North and Compass: customEnterprise: North, Compass, Model Vault, private deployment
- several tiersAPI Production (Pay-as-you-go, SaaS)
- n8n
- 20 EUR/mo… (further prices in the details)Starter (Cloud)
- 50 EUR/mo… (further prices in the details)Pro (Cloud)
- 667 EUR/mo… (further prices in the details)Business (self-hosted only)
- customEnterprise (cloud or self-hosted)
- Cohere
- API Trial (free of charge)
Free (pricing page: calls with a trial key are free, rate-limited)
- Enterprise: North, Compass, Model Vault, private deployment
North and Compass: custom (pricing page). Model Vault (Standard Vault) per instance, in USD, per hour / per month / per year (documentation 'Standard Vault Pricing'): Embed 5 Fast and Embed 5 Pro Small USD 3 / USD 2,000 / USD 20,000, Medium USD 5 / USD 3,250 / USD 32,500; Rerank 4 Fast, Rerank 4 Pro and Rerank 3.5 Medium USD 5 / USD 3,250 / USD 32,500; Rerank 4 Pro Large USD 10 / USD 6,500 / USD 65,000; Parse 5 Medium USD 4 / USD 2,500 / USD 25,000, Large USD 8 / USD 5,000 / USD 50,000, XL USD 7 / USD 4,300 / USD 43,000; Cohere Transcribe Medium USD 3.75 / USD 2,500 / USD 25,000, Large USD 7.50 / USD 4,750 / USD 47,500. Generative models on Standard Vault (mostly via waitlist) per instance and hour, L / XL: Command A USD 40 / USD 48, Command A Reasoning USD 48 / USD 57.50, Command A+ USD 17.50 / USD 32.50, North Mini Code USD 7.50 / USD 10.50. Encrypted Vault priced separately. According to the Terms of Use, prices, except where otherwise indicated, do not include applicable sales taxes ('do not include any applicable sales taxes').
- API Production (Pay-as-you-go, SaaS)
In USD (pricing page): Command R input USD 0.15, output USD 0.60 per 1M tokens; Command R7B USD 0.0375 / USD 0.15; Embed 5 Pro USD 0.12, Embed 5 Fast USD 0.08 per 1M tokens; Rerank 4 Pro USD 2.50, Rerank 4 Fast USD 2.00 per 1,000 searches (1 search = 1 request with up to 100 documents); Parse 5 USD 1.50 per 1,000 pages. Legacy models for existing customers include Command R+ 08-2024 USD 2.50 / USD 10.00; Aya Expanse USD 0.50 / USD 1.50. Billing monthly or when USD 250 is outstanding. Command A+ and North Mini Code free as open-source models (Apache 2.0). According to the Terms of Use, prices, except where otherwise indicated, do not include applicable sales taxes ('do not include any applicable sales taxes').
n8n- Starter (Cloud)
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)
- Pro (Cloud)
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)
- Business (self-hosted only)
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)
- Enterprise (cloud or self-hosted)
Custom, number of executions freely selectable (pricing page); according to the Master Enterprise Terms 'Fees are exclusive of taxes'
- API Trial (free of charge)
- Cohereyesall 3 plans
- n8nyesall 4 plans
- Cohere
- API Trial (free of charge)
yes (trial API key with rate limit, not for production or commercial use)
- Enterprise: North, Compass, Model Vault, private deployment
yes (workplace platform North, search system Compass, dedicated model instances 'Model Vault' incl. Transcribe, deployment in a VPC or on-premises as well as via the cloud platforms of OCI, Azure, AWS, Google Cloud)
- API Production (Pay-as-you-go, SaaS)
yes (Command R, Command R7B, Embed 5 Pro/Fast, Rerank 4 Pro/Fast, Parse 5; older models for existing customers; Aya Expanse via the API)
n8n- Starter (Cloud)
yes (Agents, MCP and AI nodes; 1,600 Assistant credits/month; AI models without own API keys)
- Pro (Cloud)
yes (up to 9,600 Assistant credits/month)
- Business (self-hosted only)
yes
- Enterprise (cloud or self-hosted)
yes
- API Trial (free of charge)
Evidence
- Cohere7 sources
- n8n10 sources
- Cohere
- PricingPricing page, retrieved 18 Oct 2026
- Enterprise Data Commitments (as of 2025-12-05)Documentation, retrieved 18 Oct 2026
- Cohere Trust CenterTrust Center, retrieved 18 Oct 2026
- Privacy Policy (as of 2026-05-01)Privacy notice, retrieved 18 Oct 2026
- Model Training Privacy Notice (as of 2026-05-01)Privacy notice, retrieved 14 Oct 2026
- Terms of Use (as of 2022-09-07)Terms and conditions, retrieved 18 Oct 2026
- Model Vault Overview, Standard Vault Pricing, Encrypted Vault ComplianceDocumentation, retrieved 18 Oct 2026
n8n- 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 Master Enterprise Terms (version 08.2026)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”.
No guarantee of accuracy, not legal advice. Each entry is valid as of the date shown. Open points are listed on the detail pages.
More comparisons
Cohere compared with
Individual pages: Cohere, n8n. All tools in the category: Business software.