Agent-readable comparison

LibreChat vs Perplexity Enterprise

Name: LibreChat vs Perplexity Enterprise: agent-readable comparison
Creator: onAI

Published by onAI. onAI also sells one of the products compared here. Findings about other products link to public sources so you can check them; statements about onAI are marked as stated by onAI.

This comparison has 43 criteria with sourced findings for both products, including 43 that a second agent cross-checked for both. 51 criteria have a sourced finding for at least one product. "Sourced" findings passed publication validation: they are scoped, fresh and cite public resolved sources. "Agent cross-checked" findings also received a separate agent source pass, not necessarily a hands-on test. "Stated by onAI" marks the publisher's own statements about its product (evidence type vendor-statement), which cite no third-party source. Humans approve the rubric, templates and generator; they do not review every finding. No winner is declared. A missing sourced finding is not evidence that a capability is absent.

LibreChat source checks: 2026-10-21 to 2026-10-26. Website: https://www.librechat.ai
Perplexity Enterprise source checks: 2026-10-21 to 2026-10-26. Website: https://www.perplexity.ai/enterprise
Generated 2026-10-27; next source check due 2026-12-20.

Same facts as Markdown and JSON. Methodology.

Models

MOD-01 Model catalogue and providers

Judgment rule: List each available model by provider and plan, including reasoning, fast and multimodal variants. Record whether the user picks the model, the product routes automatically, or both. A provider counts only if at least one of its current models is selectable on the scoped plan.

LibreChat

Agent cross-checked Support: partial

The model catalog is configured by the customer across first-party provider integrations and custom endpoints.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

providers: Documented routes include OpenAI, Anthropic, Google, Azure OpenAI, AWS Bedrock and custom compatible services; selection requires enabled credentials and model access.
current_models: v0.8.8 release notes mention GPT-6/GPT-6.1 Sol, Claude Opus/Sonnet 5.5 and Gemini 3.8 Flash support. Actual selectable IDs still depend on the installed configuration and provider account.
auto_routing: Does the product route between models automatically, and is the chosen model shown? No automatic routing policy showing a chosen model was established, and no configured endpoint was exercised.
multimodal_input: Provider-native files support images/PDFs and some providers accept additional Office/audio/video types. Exact acceptance depends on the selected model and transport; no matrix was tested.

providers Which model providers are available? [partial]: Documented routes include OpenAI, Anthropic, Google, Azure OpenAI, AWS Bedrock and custom compatible services; selection requires enabled credentials and model access. Sources: librechat:librechat:custom, librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex.
current_models Which current models are selectable on this plan? [partial]: v0.8.8 release notes mention GPT-6/GPT-6.1 Sol, Claude Opus/Sonnet 5.5 and Gemini 3.8 Flash support. Actual selectable IDs still depend on the installed configuration and provider account. Sources: librechat:librechat:releases.
user_choice Can users pick the model per chat? [supported]: Users choose an endpoint/model unless admins enforce model specs or a fixed Agent. Sources: librechat:librechat:modelspec, librechat:librechat:agents.
auto_routing Does the product route between models automatically, and is the chosen model shown? [unknown]: auto_routing: Does the product route between models automatically, and is the chosen model shown? No automatic routing policy showing a chosen model was established, and no configured endpoint was exercised.
multimodal_input Which models accept images, audio or files? [partial]: Provider-native files support images/PDFs and some providers accept additional Office/audio/video types. Exact acceptance depends on the selected model and transport; no matrix was tested. Sources: librechat:librechat:ocr.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:custom, librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex, librechat:librechat:releases, librechat:librechat:modelspec, librechat:librechat:agents, librechat:librechat:ocr.

Perplexity Enterprise

Agent cross-checked Support: partial

Enterprise offers multiple provider models, manual Search selection and automatic routing in Best, Deep Research and Computer.

Availability: generally-available · Delivery: native
Scope: surfaces=Enterprise Ask, Projects and Search web client, Enterprise Computer cloud tasks and scheduled automation, Portable Computer local inference on supported NVIDIA Windows/Linux hardware; version=not specified; plan=Enterprise Pro/Max; sales-assisted roles or connector RBAC only where stated; add_ons=none stated; deployment_mode=not specified; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

The partial atomic answers state their documentation or verification limits.
Capabilities apply only to the surface named in each atomic answer. Computer, Office/Teams and Portable do not establish feature parity in Ask/Search.
Hosted functions use Perplexity cloud services; Portable local execution is device-local on supported NVIDIA hardware. Portable is not a self-hosted Enterprise backend.

providers Which model providers are available? [supported]: Enterprise table names OpenAI, Google, Anthropic, MoonshotAI, Z.ai, xAI and NVIDIA; Perplexity provides orchestration and separate local PPLX 27B. Sources: perplexity:perplexity:p-models, perplexity:perplexity:p-local.
current_models Which current models are selectable on this plan? [supported]: October 17 Enterprise Pro/Max Search table lists GPT 6.1 Sol, GPT 6 Astra, Gemini 4 Argon, Gemini 3.8 Flash, Claude Sonnet 5.5, Claude Opus 5.5, Claude Fable 5.1, Kimi K3, GLM 5.3, Grok 4.7 and Nemotron 3.5 Super VL. Settings, retention, region and rollout can narrow the list. Sources: perplexity:perplexity:p-models.
user_choice Can users pick the model per chat? [supported]: Paid Search users can choose an eligible model per query. Computer can select a model for later session runs; this does not mean every tool step uses it. Sources: perplexity:perplexity:p-models, perplexity:perplexity:p-computer.
auto_routing Does the product route between models automatically, and is the chosen model shown? [partial]: Best chooses per Search query; Deep Research selects automatically and Computer routes per step while excluding organisation-disabled models. Audit answer events identify the model; full routed-model disclosure in every UI remains unverified. Sources: perplexity:perplexity:p-models, perplexity:perplexity:p-computer, perplexity:perplexity:p-audit.
multimodal_input Which models accept images, audio or files? [partial]: Ask/Computer accept files and images and file uploads can transcribe audio/video; no per-current-model input matrix was retrieved. Sources: perplexity:perplexity:p-files, perplexity:perplexity:p-filelimits.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-models, perplexity:perplexity:p-local, perplexity:perplexity:p-computer, perplexity:perplexity:p-audit, perplexity:perplexity:p-files, perplexity:perplexity:p-filelimits.

MOD-02 Model freshness

Judgment rule: Measure the days from a provider's general release to availability in the product for the last three major releases from OpenAI, Anthropic and Google (and Mistral where offered). Use dated changelogs or observation. Record deprecation notice for retired models.

LibreChat

Agent cross-checked Support: partial

Dated releases document model updates, but measured availability lags and retirement notice periods remain unknown.

Limitations

release_lag_days: What was the lag for each of the last three major releases, per provider? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established.
deprecation_notice: How much notice is given before a model is removed? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established.
version_pinning: Admins can name explicit model IDs in endpoints/model specs; continuing remote availability remains under provider control.

release_lag_days What was the lag for each of the last three major releases, per provider? [unknown]: release_lag_days: What was the lag for each of the last three major releases, per provider? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established.
changelog Is there a dated public model changelog? [supported]: Public releases and the LibreChat changelog date model updates; v0.8.8 was published 2026-10-01. Sources: librechat:librechat:releases.
deprecation_notice How much notice is given before a model is removed? [unknown]: deprecation_notice: How much notice is given before a model is removed? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established.
version_pinning Can an admin keep an older model version? [partial]: Admins can name explicit model IDs in endpoints/model specs; continuing remote availability remains under provider control. Sources: librechat:librechat:modelspec, librechat:librechat:custom.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:releases, librechat:librechat:modelspec, librechat:librechat:custom.

Perplexity Enterprise

Agent cross-checked Support: partial

A dated changelog exists; provider release lag and guaranteed older-version availability remain gaps.

Availability: generally-available · Delivery: native
Scope: surfaces=Enterprise Ask, Projects and Search web client; version=not specified; plan=Enterprise Pro/Max; sales-assisted roles or connector RBAC only where stated; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

Remaining atomic gaps: release_lag_days, version_pinning.

release_lag_days What was the lag for each of the last three major releases, per provider? [unknown]: Unknown for release_lag_days. No paired provider/product dates for the last three releases, guaranteed removal notice, or administrator version-pinning policy was retrieved.
changelog Is there a dated public model changelog? [supported]: Dated public releases include October 5 GPT 6.1 Sol/Claude Opus 5.5 and September 21 GPT 6 Astra. No matched last-three-release provider lag dataset was calculated. Sources: perplexity:perplexity:p-changelog.
deprecation_notice How much notice is given before a model is removed? [partial]: Model inventory expressly makes no commitment to keep an individual model available. A guaranteed notice period is unknown. Sources: perplexity:perplexity:p-models.
version_pinning Can an admin keep an older model version? [unknown]: Unknown for version_pinning. No paired provider/product dates for the last three releases, guaranteed removal notice, or administrator version-pinning policy was retrieved.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-changelog, perplexity:perplexity:p-models.

MOD-03 Bring-your-own keys and provider contracts

Judgment rule: Record customer-held API keys, customer cloud accounts (Azure OpenAI, Bedrock, Vertex), and aggregator routes (OpenRouter, LiteLLM) as separate routes. Record what still works without a vendor-provided model, whether prices change with BYO, and documented restrictions. API-key support does not imply support for the customer's own Azure contract.

LibreChat

Agent cross-checked Support: partial

Customer-held provider keys, customer Azure/AWS/Vertex configurations and custom endpoints are documented.

Limitations

byo_restrictions: File modalities, tools and other capabilities depend on provider/model support and optional services. A universal BYO feature-parity guarantee was not established.

own_api_keys Can the customer use its own provider API keys? [supported]: Provider keys can be operator-supplied or user_provided, with user key controls in Settings. Sources: librechat:librechat:firstchat, librechat:librechat:custom.
own_cloud_contract Can it use its own Azure OpenAI, Bedrock or Vertex deployment? [supported]: Customer Azure OpenAI deployments, AWS Bedrock region/credentials and Anthropic Vertex project/region routes are documented separately. Sources: librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex.
custom_endpoint Can an admin add any OpenAI-compatible endpoint? [supported]: Operators can configure a custom compatible API URL and model list. Sources: librechat:librechat:custom.
byo_pricing Does BYO change the licence price? [supported]: MIT repository use has no per-seat licence fee; customers separately procure provider service usage. Sources: librechat:librechat:license, librechat:librechat:firstchat.
byo_restrictions Which features stop working with BYO? [partial]: File modalities, tools and other capabilities depend on provider/model support and optional services. A universal BYO feature-parity guarantee was not established. Sources: librechat:librechat:ocr, librechat:librechat:code.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:firstchat, librechat:librechat:custom, librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex, librechat:librechat:license, librechat:librechat:ocr, librechat:librechat:code.

Perplexity Enterprise

No public information found Support: not-published

We found no public information on this. A missing finding is not evidence that the product lacks the capability.

MOD-04 Local and self-hosted models

Judgment rule: Record support for models running in the customer's environment (vLLM, Ollama, TGI or similar) and which features work with them: chat, RAG, tools, embeddings. Distinguish a documented, supported route from a generic endpoint that happens to work.

LibreChat

Agent cross-checked Support: partial

Local compatible inference and Ollama embeddings are documented; optional services must also be local for a fully private stack.

Limitations

feature_parity: Chat and retrieval can use local endpoints. Tool calling and vision depend on the model; external OCR/search/code services are separate. No complete offline fixture was run.
vendor_hosted_open_models: Does the vendor host open-weight models in EU/CH? A vendor-hosted EU/Swiss open-weight model service was not established for the MIT self-hosted project.

self_hosted_chat Can chat use a customer-hosted model? [supported]: Custom endpoints can point at customer-hosted compatible model servers, including Ollama-compatible setups. Sources: librechat:librechat:custom.
self_hosted_embeddings Can retrieval use customer-hosted embeddings? [supported]: The RAG configuration documents Ollama embeddings and local Hugging Face through the appropriate full image. Sources: librechat:librechat:ragcfg.
feature_parity Which features fail with self-hosted models? [partial]: Chat and retrieval can use local endpoints. Tool calling and vision depend on the model; external OCR/search/code services are separate. No complete offline fixture was run. Sources: librechat:librechat:ragcfg, librechat:librechat:ocr, librechat:librechat:code.
vendor_hosted_open_models Does the vendor host open-weight models in EU/CH? [unknown]: vendor_hosted_open_models: Does the vendor host open-weight models in EU/CH? A vendor-hosted EU/Swiss open-weight model service was not established for the MIT self-hosted project.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:custom, librechat:librechat:ragcfg, librechat:librechat:ocr, librechat:librechat:code.

Perplexity Enterprise

Agent cross-checked Support: partial

Portable Computer runs selected local models; local retrieval endpoints and vendor EU/CH hosting remain unknown.

Availability: generally-available · Delivery: native
Scope: surfaces=Portable Computer local inference on supported NVIDIA Windows/Linux hardware; version=not specified; plan=Enterprise Pro/Max; administrator must allow local inference; add_ons=none stated; deployment_mode=on-premise; region=Customer device; approved cloud steps leave it; os=Windows, Linux.

Limitations

Remaining atomic gaps: self_hosted_embeddings, vendor_hosted_open_models.

self_hosted_chat Can chat use a customer-hosted model? [supported]: Portable local mode runs PPLX 27B or Qwen 27B on supported NVIDIA Windows/Linux hardware. The requirement table explicitly includes Enterprise Pro/Max; this is local agent/inference, not an arbitrary hosted-model endpoint for cloud Ask. Sources: perplexity:perplexity:p-local.
self_hosted_embeddings Can retrieval use customer-hosted embeddings? [unknown]: Unknown for self_hosted_embeddings. Portable Computer documents local models and a local index, but no configurable embedding endpoint, vendor EU/CH open-model hosting location or full Enterprise deployment parity matrix.
feature_parity Which features fail with self-hosted models? [partial]: Portable local mode excludes Brain and saved memory, and loads one smaller model at a time. Cloud research, frontier reasoning and some browser/connector steps need approval. Embedding configuration and full parity remain unknown. Sources: perplexity:perplexity:p-local.
vendor_hosted_open_models Does the vendor host open-weight models in EU/CH? [unknown]: Unknown for vendor_hosted_open_models. Portable Computer documents local models and a local index, but no configurable embedding endpoint, vendor EU/CH open-model hosting location or full Enterprise deployment parity matrix.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-local.

MOD-05 Model control and usage limits

Judgment rule: Record admin allow-lists per group, default models, restrictions on which models may see which data, and per-user rate or fair-use limits. Test one restriction with two users in different groups. Record limits as enforced stops, warnings or undocumented fair use.

LibreChat

Agent cross-checked Support: partial

Model specs and scoped configuration can limit choices; optional user credit reservations provide a blocking mechanism.

Limitations

model_allowlist_by_group: Enforced model specs and role/group configuration overrides can restrict available endpoints/models. The separate management UI is preview; a two-group fixture was not run.
data_bound_models: Can admins restrict which models receive connector or knowledge content? A hard binding between each enterprise content source and a permitted model provider was not established in the Agent and access-control guides.
user_limits: Balance tracking, initial credits/refills and message moderation limits are operator-configurable, rather than a universal vendor allowance.

model_allowlist_by_group Can admins limit models per group? [partial]: Enforced model specs and role/group configuration overrides can restrict available endpoints/models. The separate management UI is preview; a two-group fixture was not run. Sources: librechat:librechat:modelspec, librechat:librechat:admin, librechat:librechat:access.
data_bound_models Can admins restrict which models receive connector or knowledge content? [unknown]: data_bound_models: Can admins restrict which models receive connector or knowledge content? A hard binding between each enterprise content source and a permitted model provider was not established in the Agent and access-control guides.
default_model Can admins set the default model? [supported]: Model-spec presets can define default endpoint/model configurations. Sources: librechat:librechat:modelspec.
user_limits What per-user message or token limits apply, and are they published? [partial]: Balance tracking, initial credits/refills and message moderation limits are operator-configurable, rather than a universal vendor allowance. Sources: librechat:librechat:balance, librechat:librechat:mod.
limit_behaviour What happens when a limit is reached? [supported]: Pinned checkBalance reserves credits and throws a TOKEN_BALANCE error when insufficient. This establishes a blocking code path, not an observed end-to-end quota test. Sources: librechat:librechat:balance-pin.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:modelspec, librechat:librechat:admin, librechat:librechat:access, librechat:librechat:balance, librechat:librechat:mod, librechat:librechat:balance-pin.

Perplexity Enterprise

Agent cross-checked Support: partial

Organisation model restrictions and Computer credit caps exist; group-specific model policy is unverified.

Availability: generally-available · Delivery: native
Scope: surfaces=Enterprise Ask, Projects and Search web client, Enterprise Computer cloud tasks and scheduled automation; version=not specified; plan=Enterprise Pro/Max; sales-assisted roles or connector RBAC only where stated; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

Remaining atomic gaps: data_bound_models, default_model.
Capabilities apply only to the surface named in each atomic answer. Computer, Office/Teams and Portable do not establish feature parity in Ask/Search.

model_allowlist_by_group Can admins limit models per group? [partial]: Admins restrict providers/models for the organisation and Computer excludes disabled models. Roles guide places model settings under organisation Data and privacy; group-specific allowlists remain unverified. Sources: perplexity:perplexity:p-models, perplexity:perplexity:p-roles, perplexity:perplexity:p-computer.
data_bound_models Can admins restrict which models receive connector or knowledge content? [unknown]: Unknown for data_bound_models. Published organisation model controls do not establish group-specific model rules, content-bound model rules, an administrator default or exact Ask quotas.
default_model Can admins set the default model? [unknown]: Unknown for default_model. Published organisation model controls do not establish group-specific model rules, content-bound model rules, an administrator default or exact Ask quotas.
user_limits What per-user message or token limits apply, and are they published? [partial]: Computer includes 500 credits/Pro seat/month or 15,000/Max, plus capped pool access. Weekly session limits are 100 Pro/1,000 Max. Exact model-specific Ask/token quotas remain unknown. Sources: perplexity:perplexity:p-credits, perplexity:perplexity:p-filelimits.
limit_behaviour What happens when a limit is reached? [partial]: Computer pool exhaustion or applicable cap blocks use until funded/raised; scheduled runs skip when credits unavailable and repeated skips pause tasks. Permission/cache refresh can delay cap changes; Ask limits behavior unverified. Sources: perplexity:perplexity:p-credits, perplexity:perplexity:p-tasks.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-models, perplexity:perplexity:p-roles, perplexity:perplexity:p-computer, perplexity:perplexity:p-credits, perplexity:perplexity:p-filelimits, perplexity:perplexity:p-tasks.

Company knowledge

KNOW-01 Files in chat

Judgment rule: Record supported formats, size and count limits, scanned-PDF OCR, tables and spreadsheets, images inside documents, and whether a file is read in full or retrieved in chunks. Upload the shared fixture set (long German PDF, scanned contract, Excel with formulas, PowerPoint) and record failures.

LibreChat

Agent cross-checked Support: partial

Files can be indexed, injected as extracted text or sent directly to compatible model providers.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=New spreadsheet finding at development source a378657583567310c841d652b0f6b00c83e2bd6b; earlier accepted facts retain their cited release pins; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

File counts, sizes and provider acceptance depend on deployment settings.
Spreadsheet parsing yields named sheets and CSV values; layout/formula fidelity and the shared fixture remain untested.

formats Which formats are accepted? [supported]: Documents include PDF/text/Office formats through configured extraction; provider-native acceptance varies, including Bedrock Office formats and Google audio/video. Sources: librechat:librechat:ocr, librechat:librechat:filecfg.
limits What size and count limits apply per file and chat? [partial]: File counts, sizes and MIME patterns are operator/endpoint settings; provider limits may be stricter. The shared fixture was not uploaded. Sources: librechat:librechat:filecfg, librechat:librechat:ocr.
ocr Are scanned PDFs read? [supported]: Optional Mistral OCR, Azure/Vertex Mistral OCR and provider-native file processing are documented. Sources: librechat:librechat:ocr.
spreadsheets Are Excel tables read with structure intact? [partial]: The inspected built-in XLSX/XLS/ODS parser emits each sheet name and CSV values. The current guide lists a 15 MB built-in parser limit. Workbook formatting, formula recalculation and shared-fixture accuracy were not established. Sources: librechat:librechat:r4-spreadsheet-parser, librechat:librechat:r4-text-current.
full_vs_chunked Is the whole file used or only retrieved parts, and does the user see which? [supported]: RAG retrieves indexed chunks; Upload as Text and Agent File Context inject extracted full text, subject to context limits. Sources: librechat:librechat:rag, librechat:librechat:text, librechat:librechat:ocr.

Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: librechat:librechat:ocr, librechat:librechat:filecfg, librechat:librechat:rag, librechat:librechat:text, librechat:librechat:r4-spreadsheet-parser, librechat:librechat:r4-text-current.

Perplexity Enterprise

Agent cross-checked Support: partial

Enterprise uploads have explicit product-specific limits; OCR and table fidelity remain untested.

Availability: generally-available · Delivery: native
Scope: surfaces=Enterprise Ask, Projects and Search web client, Enterprise Computer cloud tasks and scheduled automation, Computer Microsoft 365 add-ins and Teams; version=not specified; plan=Enterprise Pro/Max; sales-assisted roles or connector RBAC only where stated; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

Remaining atomic gaps: ocr.
Capabilities apply only to the surface named in each atomic answer. Computer, Office/Teams and Portable do not establish feature parity in Ask/Search.

formats Which formats are accepted? [supported]: Uploads support PDF/text/code/images and audio/video transcription; video visual frames are not indexed. Projects store any format, but Ask needs parseable text and Computer supports more formats. Sources: perplexity:perplexity:p-files, perplexity:perplexity:p-filelimits.
limits What size and count limits apply per file and chat? [supported]: Enterprise Ask: 30 files/upload, 50 MB/file and 30 images/query. Computer: 200 MB/file. Weekly sessions: 100 Pro/1,000 Max. Project files use a separate 100 MB limit. Sources: perplexity:perplexity:p-filelimits.
ocr Are scanned PDFs read? [unknown]: Unknown for ocr. No scanned-PDF OCR or spreadsheet structure benchmark was run. The guides do not establish exact context selection disclosure for every Enterprise upload mode.
spreadsheets Are Excel tables read with structure intact? [partial]: Projects accept spreadsheet files and Computer/Excel add-in analyses workbooks. Preservation of formulas, sheets and table structure was not tested. Sources: perplexity:perplexity:p-filelimits, perplexity:perplexity:p-office.
full_vs_chunked Is the whole file used or only retrieved parts, and does the user see which? [partial]: Generic upload guide says short documents fit fully while long ones use selected important parts. Per-file inclusion indicators and exact Computer context behavior are unverified. Sources: perplexity:perplexity:p-files.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-files, perplexity:perplexity:p-filelimits, perplexity:perplexity:p-office.

KNOW-02 Knowledge bases and shared collections

Judgment rule: Record curated document collections that persist across chats, who can create and share them, size limits, and how they attach to assistants. Distinguish personal, group and organisation-wide scope.

LibreChat

Agent cross-checked Support: partial

Agents and personal Projects keep files across chats; shared Agent access is distinct from personal Project ownership.

Limitations

sharing_scope: Agents can share files/knowledge with permitted users/groups/roles; Projects themselves are personal and cannot be shared or transferred.
size_limits: What are the collection limits? No universal collection storage/size allowance was established; limits are deployment and file-configuration dependent.

persistent_collections Can users keep document collections across chats? [supported]: Agent File Search/File Context and Project reference files persist for later chats. Sources: librechat:librechat:agents, librechat:librechat:projects.
sharing_scope Can collections be shared with users, groups or the whole organisation? [partial]: Agents can share files/knowledge with permitted users/groups/roles; Projects themselves are personal and cannot be shared or transferred. Sources: librechat:librechat:access, librechat:librechat:agents, librechat:librechat:projects.
size_limits What are the collection limits? [unknown]: size_limits: What are the collection limits? No universal collection storage/size allowance was established; limits are deployment and file-configuration dependent.
assistant_binding Can collections be bound to an assistant? [supported]: Agent File Search and File Context bind retrieved or extracted knowledge to an Agent. Sources: librechat:librechat:agents, librechat:librechat:ocr.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:projects, librechat:librechat:access, librechat:librechat:ocr.

Perplexity Enterprise

Agent cross-checked Support: partial

Projects are persistent shared file/task workspaces, with a distinct storage and access model.

Limitations

The partial atomic answers state their documentation or verification limits.

persistent_collections Can users keep document collections across chats? [supported]: Projects persist searches, Computer tasks, files, instructions and tools across sessions. Sources: perplexity:perplexity:p-projects.
sharing_scope Can collections be shared with users, groups or the whole organisation? [partial]: Projects private by default; owner/editor/viewer roles and individual invites, with organisation sharing on Enterprise. Exact identity-group grants were not established. Sources: perplexity:perplexity:p-projects.
size_limits What are the collection limits? [supported]: Unlimited Projects, each up to 10,000 files, 5 GB total and 100 MB/file. New uploads rejected at the limit; Enterprise owner may invite 9,999 contributors. Sources: perplexity:perplexity:p-projects, perplexity:perplexity:p-filelimits.
assistant_binding Can collections be bound to an assistant? [partial]: Project instructions and files apply to its Computer work; this establishes project-bound context. A separate reusable assistant binding interface was not established. Sources: perplexity:perplexity:p-projects.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-projects, perplexity:perplexity:p-filelimits.

KNOW-03 Enterprise connectors

Judgment rule: List each connector separately with plan, availability and setup owner: SharePoint, OneDrive, Outlook, Teams, Google Drive, Gmail, Confluence, Jira, Notion, Box, Salesforce, ServiceNow, file shares. Record whether the vendor or a third party (or the customer via MCP) provides it, and whether it needs admin consent. A connector listed on a roadmap or partner page is `announced`. An on-prem connector or gateway proves access to local data, not a self-hosted platform (DATA-02).

LibreChat

Agent cross-checked Support: partial

SharePoint and OneDrive have a documented delegated file picker. Other enterprise systems require separately verified tools or connectors.

Limitations

microsoft_365: SharePoint Online and OneDrive for Business can be browsed and attached through Entra token reuse/OBO, delegated AllSites.Read and Files.Read.All, and admin consent. Outlook/Teams source access was not established.
google_workspace: Which Google sources are connected? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog.
atlassian: Confluence and Jira? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog.
other_systems: Which other business systems? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog.
on_prem_sources: Custom local MCP stdio servers can reach systems available to the deployment, but a maintained file-share/database connector and its permissions were not verified.

microsoft_365 Which M365 sources (SharePoint, OneDrive, Outlook, Teams) are connected? [partial]: SharePoint Online and OneDrive for Business can be browsed and attached through Entra token reuse/OBO, delegated AllSites.Read and Files.Read.All, and admin consent. Outlook/Teams source access was not established. Sources: librechat:librechat:sharepoint.
google_workspace Which Google sources are connected? [unknown]: google_workspace: Which Google sources are connected? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog.
atlassian Confluence and Jira? [unknown]: atlassian: Confluence and Jira? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog.
other_systems Which other business systems? [unknown]: other_systems: Which other business systems? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog.
on_prem_sources Can on-prem file shares or databases be connected? [partial]: Custom local MCP stdio servers can reach systems available to the deployment, but a maintained file-share/database connector and its permissions were not verified. Sources: librechat:librechat:mcpcfg.
connector_provider Who builds and maintains each connector? [supported]: LibreChat documents the Microsoft picker. Other MCP tool integrations are separately configured and maintained by their respective server authors/operators. Sources: librechat:librechat:sharepoint, librechat:librechat:mcp.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:sharepoint, librechat:librechat:mcpcfg, librechat:librechat:mcp.

Perplexity Enterprise

Agent cross-checked Support: partial

Live file connectors, Computer apps, Teams and remote MCP provide business data access.

Availability: generally-available · Delivery: official-integration
Scope: surfaces=Enterprise Ask, Projects and Search web client, Enterprise Computer cloud tasks and scheduled automation, Portable Computer local inference on supported NVIDIA Windows/Linux hardware, Computer Microsoft 365 add-ins and Teams; version=not specified; plan=Enterprise Pro/Max; sales-assisted roles or connector RBAC only where stated; add_ons=none stated; deployment_mode=not specified; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

Remaining atomic gaps: atlassian.
Capabilities apply only to the surface named in each atomic answer. Computer, Office/Teams and Portable do not establish feature parity in Ask/Search.
Hosted functions use Perplexity cloud services; Portable local execution is device-local on supported NVIDIA hardware. Portable is not a self-hosted Enterprise backend.

microsoft_365 Which M365 sources (SharePoint, OneDrive, Outlook, Teams) are connected? [supported]: OneDrive and SharePoint file connectors are documented. Computer also connects to Outlook and Teams through separate grants and installations. Sources: perplexity:perplexity:p-connectors, perplexity:perplexity:p-office, perplexity:perplexity:p-teams.
google_workspace Which Google sources are connected? [supported]: Google Drive file connector and personal Gmail/primary Google Calendar OAuth are documented. Send/edit scopes support actions; access is not uniformly read-only. Sources: perplexity:perplexity:p-connectors, perplexity:perplexity:p-gmail.
atlassian Confluence and Jira? [unknown]: Unknown for atlassian. The sources name several file and app connectors. A complete current connector/permission/maintainer matrix, including Atlassian and on-prem shares/databases, was not retrieved.
other_systems Which other business systems? [partial]: Dropbox and Box file connectors; the Microsoft integration page also names Salesforce, Amplitude, Asana, FactSet and Snowflake. Complete entitlements and partner contracts remain unknown. Sources: perplexity:perplexity:p-connectors, perplexity:perplexity:p-office.
on_prem_sources Can on-prem file shares or databases be connected? [partial]: Custom HTTPS MCP can use Cloudflare Access-protected endpoints; Portable uses local stdio MCP. Native on-prem file-share/database connectors and their permission guarantees remain unverified. Sources: perplexity:perplexity:p-mcp, perplexity:perplexity:p-local.
connector_provider Who builds and maintains each connector? [partial]: Perplexity documents built-in connectors; customers supply custom MCP servers and credentials. The maintainer and support contract for each external integration remain unverified. Sources: perplexity:perplexity:p-connectors, perplexity:perplexity:p-mcp.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-connectors, perplexity:perplexity:p-office, perplexity:perplexity:p-teams, perplexity:perplexity:p-gmail, perplexity:perplexity:p-mcp, perplexity:perplexity:p-local.

KNOW-04 Permission-aware retrieval

Judgment rule: Using two test users, verify that a restricted document in the fixture tenant is never cited or summarised for the user without access, including after a permission change. Record whether permissions are enforced at query time by the source system, mirrored into an index, or not enforced. Record the propagation delay of a revocation.

LibreChat

Agent cross-checked Support: partial

Product resource ACLs and delegated Microsoft file selection are documented. Continuing source permissions for copied content remain untested.

Limitations

source_permissions_respected: Are source permissions enforced per user? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified.
enforcement_point: LibreChat ACLs control Agent/file resources; Microsoft delegated OBO limits source downloads as the signed-in user. No query-time source ACL check for previously copied chunks was established.
revocation_delay: How quickly does a removed permission take effect? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified.
admin_scope_controls: Operators can scope Agent/resource grants and its selected files. Site/folder/label exclusion across sources was not established.
sensitivity_labels: Are Microsoft Purview or similar labels respected? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified.

source_permissions_respected Are source permissions enforced per user? [unknown]: source_permissions_respected: Are source permissions enforced per user? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified.
enforcement_point Does the source system, a mirrored index or nothing enforce them? [partial]: LibreChat ACLs control Agent/file resources; Microsoft delegated OBO limits source downloads as the signed-in user. No query-time source ACL check for previously copied chunks was established. Sources: librechat:librechat:access, librechat:librechat:sharepoint.
revocation_delay How quickly does a removed permission take effect? [unknown]: revocation_delay: How quickly does a removed permission take effect? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified.
admin_scope_controls Can admins exclude sites, folders or labels? [partial]: Operators can scope Agent/resource grants and its selected files. Site/folder/label exclusion across sources was not established. Sources: librechat:librechat:access, librechat:librechat:agents.
sensitivity_labels Are Microsoft Purview or similar labels respected? [unknown]: sensitivity_labels: Are Microsoft Purview or similar labels respected? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:access, librechat:librechat:sharepoint, librechat:librechat:agents.

Perplexity Enterprise

Agent cross-checked Support: partial

Live query permissions differ from static Project copies and shared answers.

Limitations

Remaining atomic gaps: sensitivity_labels.

source_permissions_respected Are source permissions enforced per user? [partial]: Live searches use the connected user's permissions. Shared answers can reveal file content to recipients without original-file access; Project copies use Project membership. No two-user scenario was run. Sources: perplexity:perplexity:p-connectors, perplexity:perplexity:p-connectfaq.
enforcement_point Does the source system, a mirrored index or nothing enforce them? [supported]: Source OAuth governs live queries; Project imports create static copies governed by Project access. Original-file links require source access, which does not prevent answer disclosure. Sources: perplexity:perplexity:p-connectors, perplexity:perplexity:p-connectfaq.
revocation_delay How quickly does a removed permission take effect? [partial]: FAQ says source permission changes affect live search immediately; this was not measured. Project copies require separate removal or access management. Sources: perplexity:perplexity:p-connectfaq.
admin_scope_controls Can admins exclude sites, folders or labels? [partial]: Admins enable connectors; users connect OAuth accounts and select folders. Sales-assisted connector RBAC gates runtime use. Admin site/folder/label exclusions were not established. Sources: perplexity:perplexity:p-connectors, perplexity:perplexity:p-connector-rbac.
sensitivity_labels Are Microsoft Purview or similar labels respected? [unknown]: Unknown for sensitivity_labels. No two-user permission-revocation or sensitivity-label scenario was run. A source-level administrator exclusion policy and Purview enforcement matrix were not retrieved.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-connectors, perplexity:perplexity:p-connectfaq, perplexity:perplexity:p-connector-rbac.

KNOW-05 Freshness and sync model

Judgment rule: Record live (federated) search versus a copied index, sync interval, deletion propagation, and where the index is stored. Edit and delete one fixture document and record when answers change. A copied index adds storage location to DATA-01.

LibreChat

Agent cross-checked Support: partial

The RAG API copies uploaded content into PGVector; imported files do not by themselves establish live enterprise synchronization.

Limitations

sync_interval: How often does an index refresh? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides.
deletion_propagation: How quickly does a deleted document disappear? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides.

live_or_indexed Is content searched live or copied into an index? [supported]: The RAG API indexes uploaded documents into PostgreSQL/PGVector; file-context mode stores extracted text in Agent instructions. Sources: librechat:librechat:rag, librechat:librechat:ocr.
sync_interval How often does an index refresh? [unknown]: sync_interval: How often does an index refresh? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides.
deletion_propagation How quickly does a deleted document disappear? [unknown]: deletion_propagation: How quickly does a deleted document disappear? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides.
index_location Where is indexed content stored? [supported]: The operator chooses the RAG database and its location, independently of the inference provider. Sources: librechat:librechat:rag, librechat:librechat:compose-pin.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:rag, librechat:librechat:ocr, librechat:librechat:compose-pin.

Perplexity Enterprise

Agent cross-checked Support: partial

Live searches query current sources; files imported into Projects are static snapshots.

Availability: generally-available · Delivery: native
Scope: surfaces=Enterprise Ask, Projects and Search web client; version=Document/Office file connector behavior; media connector support unverified and excluded; plan=Enterprise Pro/Max; sales-assisted roles or connector RBAC only where stated; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

The partial atomic answers state their documentation or verification limits.
No positive or negative connector audio/video capability is asserted. The documentation discrepancy is a named gap; the live-versus-copy finding is restricted to document formats common to both guides.

live_or_indexed Is content searched live or copied into an index? [partial]: For documented text/Office files, Standard Search queries sources live without a Perplexity file-index copy; attachments and Project imports keep snapshots. Media connector support is unknown because the introduction excludes audio/video while the FAQ lists them. Direct media uploads are a separate workflow. Sources: perplexity:perplexity:p-connectors, perplexity:perplexity:p-connectfaq.
sync_interval How often does an index refresh? [supported]: Project imports require manual reimport to refresh; no automatic sync. Live queries have no batch refresh interval. Sources: perplexity:perplexity:p-connectors, perplexity:perplexity:p-connectfaq.
deletion_propagation How quickly does a deleted document disappear? [partial]: New live queries reflect source changes. Existing Project copies remain until removed or reimported; propagation timing was not measured. Sources: perplexity:perplexity:p-connectors, perplexity:perplexity:p-connectfaq.
index_location Where is indexed content stored? [partial]: FAQ names AWS S3 for copied files without a region. Exact Project index, storage and backup locations remain unknown. Sources: perplexity:perplexity:p-connectfaq.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-connectors, perplexity:perplexity:p-connectfaq.

KNOW-06 Grounding and retrieval quality

Judgment rule: Run the shared question set over the fixture corpus: factual lookups, cross-document questions, German document with an English question, a question with no answer in the corpus. Record citation presence, link accuracy, correct answers and refusals to invent. Disclose model, settings, attempt count and failures. Single runs support a case study, not a ranking.

LibreChat

Agent cross-checked Support: partial

File-search citations are documented; retrieval accuracy remains unmeasured.

Limitations

citation_accuracy: Do the cited passages support the answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown.
cross_language: Does a question in one language find documents in another? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown.
no_answer_behaviour: Does it say when the corpus has no answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown.
observed_accuracy: How many of the question set were answered correctly? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown.

citations Are answers linked to specific sources? [supported]: RAG/File Search provides retrieved source references and citation controls. Sources: librechat:librechat:rag, librechat:librechat:access.
citation_accuracy Do the cited passages support the answer? [unknown]: citation_accuracy: Do the cited passages support the answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown.
cross_language Does a question in one language find documents in another? [unknown]: cross_language: Does a question in one language find documents in another? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown.
no_answer_behaviour Does it say when the corpus has no answer? [unknown]: no_answer_behaviour: Does it say when the corpus has no answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown.
observed_accuracy How many of the question set were answered correctly? [unknown]: observed_accuracy: How many of the question set were answered correctly? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:rag, librechat:librechat:access.

Perplexity Enterprise

Agent cross-checked Support: partial

Source-linked answers are documented; retrieval quality is unmeasured.

Availability: generally-available · Delivery: native
Scope: surfaces=Enterprise Ask, Projects and Search web client, Enterprise Computer cloud tasks and scheduled automation, Computer Microsoft 365 add-ins and Teams; version=not specified; plan=Enterprise Pro/Max; sales-assisted roles or connector RBAC only where stated; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

Remaining atomic gaps: citation_accuracy, cross_language, no_answer_behaviour, observed_accuracy.
Capabilities apply only to the surface named in each atomic answer. Computer, Office/Teams and Portable do not establish feature parity in Ask/Search.

citations Are answers linked to specific sources? [supported]: Connector answers link to files; Office and Deep Research cite source documents and web links. Citation correctness was not independently tested. Sources: perplexity:perplexity:p-connectors, perplexity:perplexity:p-office, perplexity:perplexity:p-research.
citation_accuracy Do the cited passages support the answer? [unknown]: Unknown for citation_accuracy. The shared DE/FR/EN question corpus was not run. Citation correctness, cross-language retrieval, abstention and measured accuracy remain unobserved.
cross_language Does a question in one language find documents in another? [unknown]: Unknown for cross_language. The shared DE/FR/EN question corpus was not run. Citation correctness, cross-language retrieval, abstention and measured accuracy remain unobserved.
no_answer_behaviour Does it say when the corpus has no answer? [unknown]: Unknown for no_answer_behaviour. The shared DE/FR/EN question corpus was not run. Citation correctness, cross-language retrieval, abstention and measured accuracy remain unobserved.
observed_accuracy How many of the question set were answered correctly? [unknown]: Unknown for observed_accuracy. The shared DE/FR/EN question corpus was not run. Citation correctness, cross-language retrieval, abstention and measured accuracy remain unobserved.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-connectors, perplexity:perplexity:p-office, perplexity:perplexity:p-research.

KNOW-07 Memory and personal context

Judgment rule: Record personal custom instructions, cross-chat memory, project or workspace context, and user controls to view, edit, delete or disable memory. Record whether admins can disable memory organisation-wide.

LibreChat

Agent cross-checked Support: supported

Opt-in user memory stores editable key/value context across chats; Projects and Agents provide additional persistent instructions.

custom_instructions Can users set persistent instructions? [supported]: Projects retain instructions across their chats; Agents retain system instructions. Sources: librechat:librechat:projects, librechat:librechat:agents.
cross_chat_memory Does the product remember facts across chats? [supported]: User Memory injects configured key/value entries across chats and is not semantic search over all past conversations. Sources: librechat:librechat:memory.
user_memory_controls Can users view, edit and delete memories? [supported]: Users add/edit/remove entries and can toggle memory when permitted. Sources: librechat:librechat:memory.
admin_memory_controls Can admins turn memory off? [supported]: Memory is disabled until configured and its feature permissions can be restricted by role. Sources: librechat:librechat:memory, librechat:librechat:access.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:projects, librechat:librechat:agents, librechat:librechat:memory, librechat:librechat:access.

Perplexity Enterprise

Agent cross-checked Support: supported

Enterprise history and saved-memory controls are documented; Computer Brain is a Max Research Preview, and Portable local mode excludes Brain and saved memory.

Availability: unknown · Delivery: native
Scope: surfaces=Enterprise Ask, Projects and Search web client, Enterprise Computer cloud tasks and scheduled automation, Portable Computer local inference on supported NVIDIA Windows/Linux hardware; version=Current Enterprise memory; Enterprise Max Brain Research Preview, not general availability for the whole criterion; plan=Enterprise Pro/Max; sales-assisted roles or connector RBAC only where stated; add_ons=none stated; deployment_mode=not specified; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

Capabilities apply only to the surface named in each atomic answer. Computer, Office/Teams and Portable do not establish feature parity in Ask/Search.
Hosted functions use Perplexity cloud services; Portable local execution is device-local on supported NVIDIA hardware. Portable is not a self-hosted Enterprise backend.
The schema has no public/research-preview state. Mixed memory availability remains unknown at criterion level; Brain is explicitly Research Preview.

custom_instructions Can users set persistent instructions? [supported]: Project instructions persist, with an 8,000-character limit. This does not establish organisation-wide instructions. Sources: perplexity:perplexity:p-projects.
cross_chat_memory Does the product remember facts across chats? [supported]: History reference, saved memory and Project Brain are documented. Enterprise Brain is a Max research preview. Portable local mode excludes Brain and saved memory. Sources: perplexity:perplexity:p-memory, perplexity:perplexity:p-projects, perplexity:perplexity:p-local.
user_memory_controls Can users view, edit and delete memories? [supported]: Users can disable, view, edit and delete saved memories. Deleted-memory logs may remain for 30 days. Sources: perplexity:perplexity:p-memory.
admin_memory_controls Can admins turn memory off? [supported]: Admins control history reference and saved memory. Disabling organisation memory deletes existing memories and turns it off for users. Sources: perplexity:perplexity:p-memory.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-projects, perplexity:perplexity:p-memory, perplexity:perplexity:p-local.

Assistants and agents

AGT-01 Custom assistants

Judgment rule: Record creation of assistants with instructions, model, knowledge and tools; who can create; sharing scope; versioning; and an internal catalogue or directory. Build one HR policy assistant on the fixture and share it with one group. Prompt templates and a prompt library are recorded here.

LibreChat

Agent cross-checked Support: supported

Agents combine instructions, a model, knowledge and tools, with version history and a permissioned internal catalog.

create_assistants Can users create assistants with instructions, knowledge and tools? [supported]: The Agent Builder creates reusable instructions/model/files/tools/skills configurations. Sources: librechat:librechat:agents.
creator_permissions Can admins limit who creates them? [supported]: AGENTS CREATE and sharing permissions can be restricted by role; resource grants control access. Sources: librechat:librechat:access.
sharing_scope Can assistants be shared with users, groups or everyone? [supported]: Agent ACLs support users, groups, roles and all authenticated users when public sharing is permitted. Sources: librechat:librechat:access.
catalogue Is there an internal assistant directory? [supported]: Agents have a marketplace/catalog and searchable builder tool library. Sources: librechat:librechat:agents.
prompt_library Are shared prompt templates available? [supported]: Prompt resources have use/create/share/share-public permissions and ACLs. Sources: librechat:librechat:access.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:access.

Perplexity Enterprise

Agent cross-checked Support: partial

Computer Skills and Projects package reusable instructions and context; managed Enterprise roles govern organization Skills and Plugins separately.

Availability: generally-available · Delivery: native
Scope: surfaces=Enterprise Ask, Projects and Search web client, Enterprise Computer cloud tasks and scheduled automation; version=not specified; plan=Enterprise Pro/Max; sales-assisted roles or connector RBAC only where stated; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

create_assistants: Users create custom Skills with SKILL.md/ZIP instructions. Projects combine instructions, files and tools. These establish task packages; a separate assistant directory remains unverified.
creator_permissions: The sales-assisted Enterprise Roles & Permissions guide lists Manage organization skills for creation/modification/review. Plugin creation/publishing permissions are separate and depend on rollout. This does not establish identical self-serve controls or a universal assistant-creation role.
sharing_scope: Project owner/editor/viewer permissions and Enterprise organisation sharing apply to task context. Custom Skill publishing to groups or the organisation remains unverified.
catalogue: Computer offers Installed and Discover views with Skill search by name or description. It is a Skills catalogue; a complete directory of organization assistants with model/knowledge/tool versions was not established. Plugins arrive first on individual/self-serve Enterprise, while managed Enterprise continues Skills until its rollout.
prompt_library: Custom Skills store reusable instructions, and eligible managed Enterprise roles can manage organization Skills. This supplies reusable task instructions rather than a verified separate shared prompt-template library.

create_assistants Can users create assistants with instructions, knowledge and tools? [partial]: Users create custom Skills with SKILL.md/ZIP instructions. Projects combine instructions, files and tools. These establish task packages; a separate assistant directory remains unverified. Sources: perplexity:perplexity:p-skills-20261026, perplexity:perplexity:p-projects-20261026.
creator_permissions Can admins limit who creates them? [partial]: The sales-assisted Enterprise Roles & Permissions guide lists Manage organization skills for creation/modification/review. Plugin creation/publishing permissions are separate and depend on rollout. This does not establish identical self-serve controls or a universal assistant-creation role. Sources: perplexity:perplexity:p-roles-20261026.
sharing_scope Can assistants be shared with users, groups or everyone? [partial]: Project owner/editor/viewer permissions and Enterprise organisation sharing apply to task context. Custom Skill publishing to groups or the organisation remains unverified. Sources: perplexity:perplexity:p-projects-20261026, perplexity:perplexity:p-skills-20261026.
catalogue Is there an internal assistant directory? [partial]: Computer offers Installed and Discover views with Skill search by name or description. It is a Skills catalogue; a complete directory of organization assistants with model/knowledge/tool versions was not established. Plugins arrive first on individual/self-serve Enterprise, while managed Enterprise continues Skills until its rollout. Sources: perplexity:perplexity:p-skills-20261026, perplexity:perplexity:p-roles-20261026.
prompt_library Are shared prompt templates available? [partial]: Custom Skills store reusable instructions, and eligible managed Enterprise roles can manage organization Skills. This supplies reusable task instructions rather than a verified separate shared prompt-template library. Sources: perplexity:perplexity:p-skills-20261026, perplexity:perplexity:p-roles-20261026.

Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: perplexity:perplexity:p-skills-20261026, perplexity:perplexity:p-projects-20261026, perplexity:perplexity:p-roles-20261026.

AGT-02 Tools, actions and MCP

Judgment rule: Record built-in tools, custom actions (OpenAPI), MCP client support (local and remote servers), authentication model per tool (shared service account or per-user OAuth), and admin approval of tools. Verify one external-tool call and its access boundary.

LibreChat

Agent cross-checked Support: partial

Agent tools include file search, code, web and Actions, with local/remote MCP and configurable approval boundaries.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Customer-operated or third-party MCP servers, Optional separate Code Interpreter service; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

tool_approval: Agent/code environments document approval modes and individual tool-call approvals. The default policy and every external side-effect boundary were not exercised.

builtin_tools Which tools are built in? [supported]: Agent capabilities include file search/context, web search, memory and optionally configured code execution/image tools. Sources: librechat:librechat:agents, librechat:librechat:images.
custom_actions Can admins add API actions? [supported]: Agents support custom API Actions configured in the tool library. Sources: librechat:librechat:agents.
mcp_client Can it use remote MCP servers, and with what admin control? [supported]: Configured MCP transports include stdio, SSE and Streamable HTTP; YAML and permissioned UI setup are documented. Sources: librechat:librechat:mcp, librechat:librechat:mcpcfg.
tool_auth Do tools act as the user or as a shared account? [supported]: MCP supports configured credentials/headers and OAuth; credential and resource ownership scope depends on each server configuration. Sources: librechat:librechat:mcp, librechat:librechat:mcpcfg.
tool_approval Can admins approve or block tools, and can users confirm actions before they run? [partial]: Agent/code environments document approval modes and individual tool-call approvals. The default policy and every external side-effect boundary were not exercised. Sources: librechat:librechat:agents, librechat:librechat:code.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:images, librechat:librechat:mcp, librechat:librechat:mcpcfg, librechat:librechat:code.

Perplexity Enterprise

Agent cross-checked Support: partial

Computer uses built-in tools and administratively controlled MCP connectors with several authentication modes.

Limitations

The partial atomic answers state their documentation or verification limits.
Capabilities apply only to the surface named in each atomic answer. Computer, Office/Teams and Portable do not establish feature parity in Ask/Search.
Hosted functions use Perplexity cloud services; Portable local execution is device-local on supported NVIDIA hardware. Portable is not a self-hosted Enterprise backend.

builtin_tools Which tools are built in? [supported]: Computer combines web research, code, data analysis, generated documents, browsers and connected apps. Portable adds local files and local MCP. Sources: perplexity:perplexity:p-computer, perplexity:perplexity:p-local.
custom_actions Can admins add API actions? [partial]: Customers add remote MCP tools and custom Skills. A standalone arbitrary API-action editor or schema was not established. Sources: perplexity:perplexity:p-mcp, perplexity:perplexity:p-skills.
mcp_client Can it use remote MCP servers, and with what admin control? [supported]: HTTPS MCP supports SSE and streamable HTTP. Admins enable custom connectors and manage organisation connectors; managed plans can grant role-specific runtime access. Sources: perplexity:perplexity:p-mcp, perplexity:perplexity:p-connector-rbac.
tool_auth Do tools act as the user or as a shared account? [supported]: OAuth2, API key or no authentication. Organisation OAuth can share an admin connection or require each member's login. Shared credentials do not automatically enforce each member's source ACLs. Sources: perplexity:perplexity:p-mcp, perplexity:perplexity:p-gmail.
tool_approval Can admins approve or block tools, and can users confirm actions before they run? [partial]: Admins disable connectors; managed RBAC gates execution. Portable requires cloud-egress approval and Office previews edits. Universal cloud action confirmation remains unverified. Sources: perplexity:perplexity:p-connector-rbac, perplexity:perplexity:p-local, perplexity:perplexity:p-office.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-computer, perplexity:perplexity:p-local, perplexity:perplexity:p-mcp, perplexity:perplexity:p-skills, perplexity:perplexity:p-connector-rbac, perplexity:perplexity:p-gmail, perplexity:perplexity:p-office.

AGT-03 Web search and deep research

Judgment rule: Record web search on/off control per organisation and group, search provider, citation of web sources, deep or multi-step research, and whether queries leave the residency boundary. Admins of regulated companies often need web search off.

LibreChat

Agent cross-checked Support: partial

Web search combines configured search, scraping and optional reranking services; source queries can leave the installation boundary.

Limitations

deep_research: Agents can perform repeated tool operations and web research. No dedicated report fixture, quality result or preset research SLA was verified.

web_search Is web search available? [supported]: Tool-capable chats/Agents can use the configured web search capability. Sources: librechat:librechat:web, librechat:librechat:agents.
admin_toggle Can admins disable it per organisation or group? [supported]: WEB_SEARCH feature permissions control use; operators configure whether its provider stack is available. Sources: librechat:librechat:access, librechat:librechat:web.
search_provider Which search provider handles queries, and where? [supported]: Documented choices include Serper, SearXNG, Tavily and Keenable, with Firecrawl/Tavily/Keenable scraping and optional Jina/Cohere reranking. Geography depends on the chosen services. Sources: librechat:librechat:web.
deep_research Is multi-step research with a report available? [partial]: Agents can perform repeated tool operations and web research. No dedicated report fixture, quality result or preset research SLA was verified. Sources: librechat:librechat:agents, librechat:librechat:web.
web_citations Are web sources cited? [supported]: The web-search guide documents source references/citations from search and fetched content. Sources: librechat:librechat:web.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:web, librechat:librechat:agents, librechat:librechat:access.

Perplexity Enterprise

Agent cross-checked Support: partial

Search and multi-step Deep Research are core functions; search routing geography is a gap.

Availability: generally-available · Delivery: native
Scope: surfaces=Enterprise Ask, Projects and Search web client, Enterprise Computer cloud tasks and scheduled automation, Computer Microsoft 365 add-ins and Teams; version=not specified; plan=Enterprise Pro/Max; sales-assisted roles or connector RBAC only where stated; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

Remaining atomic gaps: admin_toggle, search_provider.
Capabilities apply only to the surface named in each atomic answer. Computer, Office/Teams and Portable do not establish feature parity in Ask/Search.

web_search Is web search available? [supported]: Enterprise Ask and Computer search the web. Projects can combine files and web research. Sources: perplexity:perplexity:p-entpro, perplexity:perplexity:p-computer.
admin_toggle Can admins disable it per organisation or group? [unknown]: Unknown for admin_toggle. The current help pages do not establish search-backend subprocessor geography or a group-level web-search off switch.
search_provider Which search provider handles queries, and where? [unknown]: Unknown for search_provider. The current help pages do not establish search-backend subprocessor geography or a group-level web-search off switch.
deep_research Is multi-step research with a report available? [supported]: Deep Research creates multi-source reports with charts, executed code and downloadable files. Models are selected automatically. Sources: perplexity:perplexity:p-research, perplexity:perplexity:p-models.
web_citations Are web sources cited? [supported]: Deep Research and Office output cite web and connected sources; accuracy was not tested. Sources: perplexity:perplexity:p-research, perplexity:perplexity:p-office.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-entpro, perplexity:perplexity:p-computer, perplexity:perplexity:p-research, perplexity:perplexity:p-models, perplexity:perplexity:p-office.

AGT-04 Workflows and automation

Judgment rule: Record no-code or low-code workflows, scheduled prompts, triggers from email, forms or business systems, and multi-step chains. Name where they run and who can build them. A shared prompt template is not a workflow.

LibreChat

Agent cross-checked Support: partial

Experimental Scheduled Chats run saved Agents on cron schedules; beta Agent Events can receive external deliveries.

Availability: beta · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Experimental schedules explicitly enabled, Beta Agents API for external Agent Events; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

workflow_builder: Agent Builder supports tool workflows and subagent configurations; no general business no-code flow editor was established.
event_triggers: The beta Agents API includes authenticated Agent Events. A built-in email/form trigger catalog was not verified.

workflow_builder Is there a workflow or chain builder? [partial]: Agent Builder supports tool workflows and subagent configurations; no general business no-code flow editor was established. Sources: librechat:librechat:agents.
scheduled_tasks Can prompts or assistants run on a schedule? [supported]: Scheduled Chats supports hourly/daily/weekly/custom cron with time zones, owner scope and execution checks; it is experimental and off by default. Sources: librechat:librechat:schedule.
event_triggers Can external events start a workflow? [partial]: The beta Agents API includes authenticated Agent Events. A built-in email/form trigger catalog was not verified. Sources: librechat:librechat:api.
builder_audience Is building aimed at business users, IT or developers? [supported]: Agent Builder is a user UI; API-event and runtime configuration require technical deployment work. Sources: librechat:librechat:agents, librechat:librechat:schedule, librechat:librechat:api.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:schedule, librechat:librechat:api.

Perplexity Enterprise

Agent cross-checked Support: partial

Computer supports natural-language automation, scheduled jobs and condition-based triggers.

Availability: generally-available · Delivery: native
Scope: surfaces=Enterprise Computer cloud tasks and scheduled automation, Portable Computer local inference on supported NVIDIA Windows/Linux hardware; version=not specified; plan=Enterprise Pro/Max; sales-assisted roles or connector RBAC only where stated; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

The partial atomic answers state their documentation or verification limits.

workflow_builder Is there a workflow or chain builder? [partial]: Users describe multi-step work in prompts and package it in Skills. A visual versioned chain builder was not established. Sources: perplexity:perplexity:p-computer, perplexity:perplexity:p-skills.
scheduled_tasks Can prompts or assistants run on a schedule? [supported]: Recurring Computer tasks run at most hourly, up to 15 per conversation. Unattended runs use isolated agents; insufficient credits cause skips and eventual pauses. Sources: perplexity:perplexity:p-tasks.
event_triggers Can external events start a workflow? [partial]: Enterprise overview describes email, calendar, flight-status and file-condition triggers. Per-connector event coverage and limits remain unverified. Sources: perplexity:perplexity:p-computer.
builder_audience Is building aimed at business users, IT or developers? [supported]: Scheduling and Skills use natural language. Custom MCP requires technical server and authentication setup. Sources: perplexity:perplexity:p-tasks, perplexity:perplexity:p-skills, perplexity:perplexity:p-mcp.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-computer, perplexity:perplexity:p-skills, perplexity:perplexity:p-tasks, perplexity:perplexity:p-mcp.

AGT-05 Agentic task execution

Judgment rule: Record an agent mode that plans and carries out multi-step tasks with tools (browser, files, connectors), with visible steps, user confirmation of side effects and stop control. Run one fixture task (gather three documents, draft a summary, propose an email). Record interventions and what ran. A final claim of success is not proof.

LibreChat

Agent cross-checked Support: partial

Agent runs expose reasoning/tool activity and optional approval, interruption and cooperative stop controls.

Limitations

No gather-documents, draft-summary and propose-email task was run.
Highly experimental attached workspaces are distinct from ordinary Agent tool use.

agent_mode Is there an agent mode for multi-step tasks? [supported]: Agents execute multi-step tool workflows; code/workspace capabilities require a compatible separately deployed service. Sources: librechat:librechat:agents, librechat:librechat:code.
visible_steps Are steps and tool calls shown? [supported]: Activity groups and tool cards distinguish preparation, execution, completion, cancellation and failure. Sources: librechat:librechat:agents.
side_effect_confirmation Must the user confirm actions with side effects? [partial]: Attached environments can expose Ask before changes/Accept edits/Full access, bounded by operator tool rules. This is configurable, not a guarantee that all side effects require confirmation. Sources: librechat:librechat:agents, librechat:librechat:code.
stop_control Can the user stop a running task? [partial]: The release documents interruption/steering; ordinary background-tool cancellation is optional and cooperative, so an uncooperative tool may still finish. Sources: librechat:librechat:agents, librechat:librechat:releases.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:code, librechat:librechat:releases.

Perplexity Enterprise

Agent cross-checked Support: partial

Computer executes asynchronous multi-step tasks; universal confirmation and stopping behavior need a trial.

Availability: generally-available · Delivery: native
Scope: surfaces=Enterprise Computer cloud tasks and scheduled automation, Portable Computer local inference on supported NVIDIA Windows/Linux hardware, Computer Microsoft 365 add-ins and Teams; version=not specified; plan=Enterprise Pro/Max; sales-assisted roles or connector RBAC only where stated; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

Remaining atomic gaps: visible_steps, stop_control.

agent_mode Is there an agent mode for multi-step tasks? [supported]: Computer runs asynchronous multi-tool tasks combining research, analysis, documents, email and follow-ups. Sources: perplexity:perplexity:p-computer.
visible_steps Are steps and tool calls shown? [unknown]: Unknown for visible_steps. No live task was run. A universal side-effect approval policy and exact stop/rollback semantics were not retrieved.
side_effect_confirmation Must the user confirm actions with side effects? [partial]: Office promises review before edits; Portable asks before cloud steps. Mandatory confirmation for every cloud email/browser action remains unverified. Sources: perplexity:perplexity:p-office, perplexity:perplexity:p-local.
stop_control Can the user stop a running task? [unknown]: Unknown for stop_control. No live task was run. A universal side-effect approval policy and exact stop/rollback semantics were not retrieved.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-computer, perplexity:perplexity:p-office, perplexity:perplexity:p-local.

AGT-06 Programmable access

Judgment rule: Record a public API for chat, assistants and knowledge, SDKs, API authentication, rate limits and whether API use counts against the same governance (audit, budgets, model restrictions). Being an MCP client is different from exposing the product over MCP.

LibreChat

Agent cross-checked Support: partial

The beta Agents API provides inference, Agent management and authenticated events; deployment guards and limitations are explicit.

Availability: beta · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

knowledge_api: The beta management surface includes Agent/Skill management. A complete public knowledge-ingestion contract and fixture were not verified.
api_governance: Agent access and remote-agent permissions gate APIs, with source identity bound for events. Complete logging/budget/model parity across routes was not tested.
mcp_server: Does the product expose itself to other agents over MCP? A native product-wide MCP server was not established; being an MCP client does not establish that interface.

chat_api Is there an API for chat and assistants? [supported]: Chat Completions and Open Responses interfaces expose saved Agents, with API-key or configured OIDC authentication. Sources: librechat:librechat:api.
knowledge_api Can documents be loaded through an API? [partial]: The beta management surface includes Agent/Skill management. A complete public knowledge-ingestion contract and fixture were not verified. Sources: librechat:librechat:api.
api_governance Do audit, budgets and model rules apply to API use? [partial]: Agent access and remote-agent permissions gate APIs, with source identity bound for events. Complete logging/budget/model parity across routes was not tested. Sources: librechat:librechat:api, librechat:librechat:access.
mcp_server Does the product expose itself to other agents over MCP? [unknown]: mcp_server: Does the product expose itself to other agents over MCP? A native product-wide MCP server was not established; being an MCP client does not establish that interface.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:api, librechat:librechat:access.

Perplexity Enterprise

Agent cross-checked Support: partial

The API is billed separately; Enterprise tenant/workspace programmability is unverified.

Availability: unknown · Delivery: unknown
Scope: surfaces=Separately billed Perplexity API platform, not Enterprise seat workspace parity; version=not specified; plan=Separate API account/credits; Enterprise workspace parity unknown; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

Remaining atomic gaps: knowledge_api, mcp_server.

chat_api Is there an API for chat and assistants? [partial]: A separate API platform exists; Enterprise seats exclude API credits. This does not establish an API for Enterprise Projects or custom Skills. Sources: perplexity:perplexity:p-billing.
knowledge_api Can documents be loaded through an API? [unknown]: Unknown for knowledge_api. Enterprise billing explicitly separates API usage. No authenticated Enterprise Projects/assistant/document API, inherited API governance matrix or Enterprise MCP-server export was retrieved.
api_governance Do audit, budgets and model rules apply to API use? [partial]: Enterprise admins cannot manage other users' API credits through Enterprise billing. Inherited workspace audit, model and budget rules for API use remain unverified. Sources: perplexity:perplexity:p-billing.
mcp_server Does the product expose itself to other agents over MCP? [unknown]: Unknown for mcp_server. Enterprise billing explicitly separates API usage. No authenticated Enterprise Projects/assistant/document API, inherited API governance matrix or Enterprise MCP-server export was retrieved.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-billing.

Daily work

WORK-01 Clients and access points

Judgment rule: List web, desktop (Windows, macOS), iOS, Android, mobile browser and browser extension separately. For each, record login with company SSO, feature gaps against web, and MDM/Intune deployability. An installable app is different from a mobile website.

LibreChat

Agent cross-checked Support: partial

The main deployment is a responsive browser client. Native clients, MDM and a supported sidebar extension were not verified.

Limitations

desktop_apps: Windows and macOS apps? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration.
mobile_apps: Docs describe mobile navigation and temporary-chat controls in the web UI. No native iOS/Android client with company SSO was established.
browser_extension: Is there a browser extension or sidebar? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration.
managed_deployment: Can IT deploy and configure clients through MDM? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration.
client_feature_gaps: Desktop/mobile layouts expose different navigation controls; no comprehensive parity matrix was tested.

web Is a full web client available? [supported]: A Docker/npm deployment serves a browser application at the configured server URL. Sources: librechat:librechat:firstchat, librechat:librechat:local.
desktop_apps Windows and macOS apps? [unknown]: desktop_apps: Windows and macOS apps? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration.
mobile_apps iOS and Android apps with SSO? [partial]: Docs describe mobile navigation and temporary-chat controls in the web UI. No native iOS/Android client with company SSO was established. Sources: librechat:librechat:retention, librechat:librechat:insights.
browser_extension Is there a browser extension or sidebar? [unknown]: browser_extension: Is there a browser extension or sidebar? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration.
managed_deployment Can IT deploy and configure clients through MDM? [unknown]: managed_deployment: Can IT deploy and configure clients through MDM? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration.
client_feature_gaps Which features are missing on mobile? [partial]: Desktop/mobile layouts expose different navigation controls; no comprehensive parity matrix was tested. Sources: librechat:librechat:retention, librechat:librechat:insights.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:firstchat, librechat:librechat:local, librechat:librechat:retention, librechat:librechat:insights.

Perplexity Enterprise

Agent cross-checked Support: partial

Web, desktop and mobile clients exist, with platform differences and separate browser products.

Availability: generally-available · Delivery: native
Scope: surfaces=Enterprise Ask, Projects and Search web client, Enterprise Computer cloud tasks and scheduled automation, Perplexity Windows/macOS clients and local-file tools, Portable Computer local inference on supported NVIDIA Windows/Linux hardware, Perplexity iOS/Android clients; voice evidence scoped to iOS; version=not specified; plan=Enterprise Pro/Max; sales-assisted roles or connector RBAC only where stated; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

Remaining atomic gaps: browser_extension, managed_deployment.

web Is a full web client available? [supported]: Enterprise Ask, Projects and Computer are available on the web. Sources: perplexity:perplexity:p-entpro, perplexity:perplexity:p-projects.
desktop_apps Windows and macOS apps? [supported]: Native Windows/macOS apps support local files. macOS app control differs from Windows. Portable inference requires supported NVIDIA Windows/Linux hardware. Sources: perplexity:perplexity:p-desktop, perplexity:perplexity:p-local.
mobile_apps iOS and Android apps with SSO? [partial]: Enterprise homepage links mobile access and iOS voice is documented. Mobile SSO and Android parity were not tested. Sources: perplexity:perplexity:p-home, perplexity:perplexity:p-voice.
browser_extension Is there a browser extension or sidebar? [unknown]: Unknown for browser_extension. No managed-client MDM/configuration package or mobile SSO test was retrieved. Comet is a separate browser product and its full enterprise entitlement matrix was not reviewed.
managed_deployment Can IT deploy and configure clients through MDM? [unknown]: Unknown for managed_deployment. No managed-client MDM/configuration package or mobile SSO test was retrieved. Comet is a separate browser product and its full enterprise entitlement matrix was not reviewed.
client_feature_gaps Which features are missing on mobile? [partial]: Model Council is Max/Enterprise Max on web. Portable inference requires NVIDIA Windows/Linux; desktop app control differs by OS. A complete mobile gap inventory remains unknown. Sources: perplexity:perplexity:p-models, perplexity:perplexity:p-local, perplexity:perplexity:p-desktop.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-entpro, perplexity:perplexity:p-projects, perplexity:perplexity:p-desktop, perplexity:perplexity:p-local, perplexity:perplexity:p-home, perplexity:perplexity:p-voice, perplexity:perplexity:p-models.

WORK-02 Office suite and Teams integration

Judgment rule: Record presence inside Word, Excel, PowerPoint, Outlook and Teams (and Google Docs, Gmail), with what the assistant can do in each: read the open document, write into it, act on mail. Record extra licences and admin consent needed. A connector that searches Office files is KNOW-03, not WORK-02.

LibreChat

No public information found Support: not-published

We found no public information on this. A missing finding is not evidence that the product lacks the capability.

Perplexity Enterprise

Agent cross-checked Support: partial

Computer has Microsoft 365 add-ins plus Teams; this requires customer Microsoft access and deployment.

Availability: generally-available · Delivery: official-integration
Scope: surfaces=Computer Microsoft 365 add-ins and Teams; version=not specified; plan=Enterprise Pro/Max; sales-assisted roles or connector RBAC only where stated; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

Remaining atomic gaps: google_workspace_apps.

word_excel_powerpoint Does it work inside Word, Excel and PowerPoint? [supported]: Computer add-ins draft, edit and research inside Word, Excel and PowerPoint. Enterprise Pro/Max are eligible; normal Computer credits apply. Sources: perplexity:perplexity:p-office.
outlook Does it work inside Outlook? [supported]: Outlook add-in drafts and rewrites email using thread/attachment context. Vendor lists web, new/classic Outlook and Mac. Sources: perplexity:perplexity:p-office.
teams Is there a Teams app or bot? [supported]: Teams app supports DMs, mentions and channel tasks, with permissioned Teams search and response posting. Sources: perplexity:perplexity:p-teams, perplexity:perplexity:p-office.
google_workspace_apps Does it work inside Docs, Sheets or Gmail? [unknown]: Unknown for google_workspace_apps. Microsoft add-ins and Teams are documented. Equivalent in-app Google Docs/Sheets/Gmail add-ins and the complete Office version/consent matrix were not retrieved.
licence_prerequisites Which licences or consents are needed? [partial]: Paid Perplexity Computer plan and Microsoft app access required. IT assigns Marketplace add-ins through M365 admin centre; Teams may require Entra consent. Full version/consent matrix remains unknown. Sources: perplexity:perplexity:p-office, perplexity:perplexity:p-teams.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-office, perplexity:perplexity:p-teams.

WORK-03 Translation and writing

Judgment rule: Record document translation preserving layout, the translation engine (LLM or dedicated such as DeepL), glossaries, formality control, supported languages including Swiss German conventions (no ß), and rewriting/proofreading tools. Translate the shared German contract into French and Italian and record layout and glossary results.

LibreChat

No public information found Support: not-published

We found no public information on this. A missing finding is not evidence that the product lacks the capability.

Perplexity Enterprise

Agent cross-checked Support: partial

Office add-ins provide rewriting; a dedicated controlled document translation system was not established.

Limitations

Remaining atomic gaps: document_translation, translation_engine, glossaries, formality_and_variants.

document_translation Can whole documents be translated with formatting kept? [unknown]: Unknown for document_translation. The Office integration documents rewriting, but no dedicated document-translation service preserving layout, named translation engine, managed glossary or de-CH control matrix was retrieved.
translation_engine Which engine translates? [unknown]: Unknown for translation_engine. The Office integration documents rewriting, but no dedicated document-translation service preserving layout, named translation engine, managed glossary or de-CH control matrix was retrieved.
glossaries Are company glossaries supported? [unknown]: Unknown for glossaries. The Office integration documents rewriting, but no dedicated document-translation service preserving layout, named translation engine, managed glossary or de-CH control matrix was retrieved.
formality_and_variants Can formality and regional variants (de-CH) be set? [unknown]: Unknown for formality_and_variants. The Office integration documents rewriting, but no dedicated document-translation service preserving layout, named translation engine, managed glossary or de-CH control matrix was retrieved.
writing_tools Are dedicated rewrite and proofreading tools available? [partial]: Word/Outlook add-ins draft, rewrite, summarise and format in place. A separate proofreading service and measured quality were not established. Sources: perplexity:perplexity:p-office.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-office.

WORK-04 Image generation and editing

Judgment rule: Record available image models, editing (inpainting, reference images), admin control and per-image cost visibility, and licence or usage terms for generated images.

LibreChat

Agent cross-checked Support: partial

Configured Agent image tools generate and edit images; model service rights/costs remain separate.

Limitations

admin_control: Operators control tool credentials/configuration and Agent creation/access permissions. A dedicated per-group image-spend switch was not established.
usage_terms: What usage rights apply to output? Generated-output rights and complete per-image cost visibility were not established as a LibreChat software entitlement.

image_generation Can users generate images, with which models? [supported]: OpenAI Image Tools and additional documented provider tools attach to an Agent; the current guide defaults OpenAI tools to gpt-image-2.5-flare. Sources: librechat:librechat:images.
image_editing Can users edit uploaded images? [supported]: The image guide documents editing/remixing uploaded images using image IDs and compatible tools. Sources: librechat:librechat:images.
admin_control Can admins restrict image generation? [partial]: Operators control tool credentials/configuration and Agent creation/access permissions. A dedicated per-group image-spend switch was not established. Sources: librechat:librechat:images, librechat:librechat:access.
usage_terms What usage rights apply to output? [unknown]: usage_terms: What usage rights apply to output? Generated-output rights and complete per-image cost visibility were not established as a LibreChat software entitlement.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:images, librechat:librechat:access.

Perplexity Enterprise

Agent cross-checked Support: partial

Perplexity offers image generation with explicit enterprise commercial-use permission.

Limitations

Remaining atomic gaps: admin_control.

image_generation Can users generate images, with which models? [supported]: Guide lists GPT Image 1, Nano Banana, Seedream 4.5 and Auto; Nano Banana Pro on Max/Enterprise Max. Models and rolling limits may change. Sources: perplexity:perplexity:p-image.
image_editing Can users edit uploaded images? [partial]: Follow-up edits and regeneration count as new generations. Exact uploaded-image editing operations were not tested. Sources: perplexity:perplexity:p-image.
admin_control Can admins restrict image generation? [unknown]: Unknown for admin_control. Image generation and enterprise commercial use are documented. Exact admin image-feature permissions and every uploaded-image edit operation were not tested.
usage_terms What usage rights apply to output? [supported]: Guide allows commercial use of Enterprise images. Terms assign output rights to the customer where law permits; third-party model terms can apply. Sources: perplexity:perplexity:p-image, perplexity:perplexity:p-terms-gb.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-image, perplexity:perplexity:p-terms-gb.

WORK-05 Voice and meetings

Judgment rule: Record dictation, read-aloud, live voice conversation, meeting transcription and summarisation, supported languages including Swiss German speech, and where audio is processed.

LibreChat

Agent cross-checked Support: partial

LibreChat documents STT, TTS and a hands-free conversation mode that chains them. Real-time speech-to-speech behavior, meeting outcomes and Swiss German recognition remain unverified.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Current self-hosted LibreChat Speech Settings documentation retrieved 2026-10-21; no voice-latency or dialect fixture performed; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Optional configured STT/TTS engines and provider credentials; self-hosted speech services need allowedAddresses; deployment_mode=on-premise; region=Customer-selected app infrastructure; audio processing depends on browser or configured external/self-hosted speech engines, with no universal region verified; os=not specified.

Limitations

Conversation mode is a chain of transcription, text generation and playback; real-time audio-to-audio behavior, interruption and latency were not verified.
Audio location depends on the chosen engine. No meeting or Swiss German fixture was run.

dictation Can users dictate prompts? [supported]: Speech configuration provides STT for audio input. Sources: librechat:librechat:speech.
read_aloud Can answers be read aloud? [supported]: Speech configuration provides TTS for model responses. Sources: librechat:librechat:speech.
voice_conversation Is a live voice mode available? [partial]: speechTab.conversationMode chains STT and TTS for hands-free turns: autoSendText sends the transcript after a configured delay, and automaticPlayback reads a completed response. Microphone recording is initially started by the user. Real-time speech-to-speech, interruption behavior and end-to-end latency were not tested. Sources: librechat:librechat:speech-conversation-r2.
meeting_summaries Are meetings transcribed and summarised? [unknown]: No meeting capture/integration, speaker diarization or meeting-summary fixture was verified in the reviewed speech documentation.
swiss_german_speech Is Swiss German speech recognised? [unknown]: Swiss German recognition and transcript quality were not tested; a language setting does not establish dialect accuracy.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:speech, librechat:librechat:speech-conversation-r2.

Perplexity Enterprise

Agent cross-checked Support: partial

Enterprise voice-conversation entitlement remains unknown. Uploaded recordings separately support transcription and queries; automatic meeting capture remains unverified.

Availability: unknown · Delivery: native
Scope: surfaces=Enterprise Ask, Projects and Search web client, Perplexity iOS/Android clients; voice evidence scoped to iOS; version=not specified; plan=Enterprise Pro / Max; consumer iOS voice does not establish Enterprise entitlement; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

Remaining atomic gaps: dictation, read_aloud, voice_conversation, swiss_german_speech.
The consumer iOS guide is not evidence of Enterprise Pro/Max voice entitlement or Enterprise SSO parity.

dictation Can users dictate prompts? [unknown]: Unknown for dictation. iOS voice and file transcription are documented. Enterprise-specific voice entitlement, read-aloud controls and Swiss German recognition were not tested.
read_aloud Can answers be read aloud? [unknown]: Unknown for read_aloud. iOS voice and file transcription are documented. Enterprise-specific voice entitlement, read-aloud controls and Swiss German recognition were not tested.
voice_conversation Is a live voice mode available? [unknown]: Unknown. The public iOS Voice Assistant guide does not establish Enterprise Pro/Max voice-conversation or Enterprise SSO entitlement, and no Enterprise voice fixture was run.
meeting_summaries Are meetings transcribed and summarised? [partial]: Uploaded audio/video can be transcribed with speaker recognition and queried. Automatic meeting capture and Swiss German quality remain unverified. Sources: perplexity:perplexity:p-files.
swiss_german_speech Is Swiss German speech recognised? [unknown]: Unknown for swiss_german_speech. iOS voice and file transcription are documented. Enterprise-specific voice entitlement, read-aloud controls and Swiss German recognition were not tested.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-files.

WORK-06 Data analysis and document output

Judgment rule: Record code execution for data analysis, charts, and generation of downloadable Word, Excel, PowerPoint and PDF files. Analyse the fixture Excel and request a PowerPoint summary. Record where code runs and whether files are editable.

LibreChat

Agent cross-checked Support: partial

The separate Code Interpreter runs analysis and produces downloadable files; artifacts provide code/HTML/diagram previews.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Separately operated compatible Code Interpreter service, Experimental stateful workspaces only if explicitly configured; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

charts: Code execution and generated-file downloads support chart artifacts, but the shared spreadsheet/chart fixture was not run.
office_file_output: Generated files are downloadable; editable Word/Excel/PowerPoint fidelity was not established with a fixture.
canvas_editing: Artifacts render React/HTML/Mermaid content and source; a rich Office document editor was not established.

data_analysis Can it analyse spreadsheets with executed code? [supported]: Configured Code Interpreter executes programs against uploaded files in its separate sandbox. Sources: librechat:librechat:code.
charts Can it produce charts? [partial]: Code execution and generated-file downloads support chart artifacts, but the shared spreadsheet/chart fixture was not run. Sources: librechat:librechat:code.
office_file_output Can it create Word, Excel or PowerPoint files? [partial]: Generated files are downloadable; editable Word/Excel/PowerPoint fidelity was not established with a fixture. Sources: librechat:librechat:code.
canvas_editing Is there a document or canvas editor for iterating on output? [partial]: Artifacts render React/HTML/Mermaid content and source; a rich Office document editor was not established. Sources: librechat:librechat:artifacts.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:code, librechat:librechat:artifacts.

Perplexity Enterprise

Agent cross-checked Support: partial

Computer and assets create Office files with previews, version history and prompt-based iteration.

Availability: generally-available · Delivery: native
Scope: surfaces=Enterprise Ask, Projects and Search web client, Enterprise Computer cloud tasks and scheduled automation, Computer Microsoft 365 add-ins and Teams; version=not specified; plan=Enterprise Pro/Max; sales-assisted roles or connector RBAC only where stated; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

The partial atomic answers state their documentation or verification limits.
Capabilities apply only to the surface named in each atomic answer. Computer, Office/Teams and Portable do not establish feature parity in Ask/Search.

data_analysis Can it analyse spreadsheets with executed code? [partial]: Computer/Deep Research execute analysis code; Office add-in reads/writes Excel. Correctness and formula preservation were not benchmarked. Sources: perplexity:perplexity:p-research, perplexity:perplexity:p-computer, perplexity:perplexity:p-office.
charts Can it produce charts? [partial]: Deep Research generates charts; assets insert visuals/tables and PowerPoint can use workbook context. Chart accuracy was not observed. Sources: perplexity:perplexity:p-research, perplexity:perplexity:p-assets, perplexity:perplexity:p-office, perplexity:perplexity:p-models.
office_file_output Can it create Word, Excel or PowerPoint files? [supported]: DOCX, PDF, XLSX, PPTX and HTML output; Google Drive export when connected. Sources: perplexity:perplexity:p-assets.
canvas_editing Is there a document or canvas editor for iterating on output? [supported]: Preview, follow-up edits and version history support iteration. Specific templates and direct manual editing require downloaded files and external software. Sources: perplexity:perplexity:p-assets.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-research, perplexity:perplexity:p-computer, perplexity:perplexity:p-office, perplexity:perplexity:p-assets, perplexity:perplexity:p-models.

WORK-07 Sharing and team spaces

Judgment rule: Record chat sharing (link, user, group), shared projects or team spaces, channels or group chat with AI, and commenting. Test sharing a chat with a colleague in another group and record what the recipient sees, including knowledge they lack access to.

LibreChat

Agent cross-checked Support: partial

Shared chat links publish transcript snapshots and optional files. Projects are personal, and shared source permission boundaries need care.

Limitations

group_chat: Can several people chat together with the AI? Simultaneous multi-person AI group chat was not established from Projects and shareable-link documentation; link continuation creates a separate personal copy.
share_permission_boundary: Published file snapshots are served independently of the owner’s live file ACL. Sharing grants access to the published copy, not continuing source-system authorization; no restricted-source fixture was run.

share_chats Can chats be shared inside the organisation? [supported]: Authenticated shared links are supported, with optional public viewing; public unauthenticated access is off by default. Sources: librechat:librechat:share.
team_spaces Are shared projects or workspaces available? [unsupported]: Projects specifically cannot be shared or transferred and are personal to the creator. Shared Agents/resources are a separate capability. Sources: librechat:librechat:projects.
group_chat Can several people chat together with the AI? [unknown]: group_chat: Can several people chat together with the AI? Simultaneous multi-person AI group chat was not established from Projects and shareable-link documentation; link continuation creates a separate personal copy.
share_permission_boundary Does sharing respect the recipient's access to sources? [partial]: Published file snapshots are served independently of the owner’s live file ACL. Sharing grants access to the published copy, not continuing source-system authorization; no restricted-source fixture was run. Sources: librechat:librechat:share.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:share, librechat:librechat:projects.

Perplexity Enterprise

Agent cross-checked Support: partial

Projects and organisation links enable collaboration; answer-sharing can cross source ACLs.

Availability: generally-available · Delivery: native
Scope: surfaces=Enterprise Ask, Projects and Search web client, Enterprise Computer cloud tasks and scheduled automation, Computer Microsoft 365 add-ins and Teams; version=not specified; plan=Enterprise Pro/Max; sales-assisted roles or connector RBAC only where stated; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

The partial atomic answers state their documentation or verification limits.
Capabilities apply only to the surface named in each atomic answer. Computer, Office/Teams and Portable do not establish feature parity in Ask/Search.

share_chats Can chats be shared inside the organisation? [supported]: Organisation-only and public links exist. Turning public sharing off does not revoke existing public links. Sources: perplexity:perplexity:p-security-hub.
team_spaces Are shared projects or workspaces available? [supported]: Private-by-default Projects share files, sessions, tasks and instructions through owner/editor/viewer roles. Sources: perplexity:perplexity:p-projects.
group_chat Can several people chat together with the AI? [partial]: Teams supports Computer in chats and channels. Concurrent multi-user AI conversation in the Perplexity web client remains unverified. Sources: perplexity:perplexity:p-teams.
share_permission_boundary Does sharing respect the recipient's access to sources? [supported]: Shared answers can reveal connector content without permission to open the original file. Static Project copies use Project membership; source ACLs alone do not protect shared answers. Sources: perplexity:perplexity:p-connectors, perplexity:perplexity:p-connectfaq.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-security-hub, perplexity:perplexity:p-projects, perplexity:perplexity:p-teams, perplexity:perplexity:p-connectors, perplexity:perplexity:p-connectfaq.

WORK-08 Interface languages and accessibility

Judgment rule: Record UI languages, focusing on German, French, Italian and English, with translation quality observed (complete, partial, machine-translated). Record response language handling and WCAG conformance statements.

LibreChat

Agent cross-checked Support: partial

English, German, French and Italian UI resources are registered in the pinned client; quality and accessibility conformance were not evaluated.

Limitations

dach_language_quality: Are German, French and Italian UIs complete and natural? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified.
accessibility_statement: Is there a WCAG conformance statement? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified.
admin_ui_languages: Is the admin interface available in German? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified.

ui_languages Which UI languages are offered? [supported]: The client i18n implementation registers en, de, fr and it among community-maintained translations. Sources: librechat:librechat:i18n-pin.
dach_language_quality Are German, French and Italian UIs complete and natural? [unknown]: dach_language_quality: Are German, French and Italian UIs complete and natural? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified.
accessibility_statement Is there a WCAG conformance statement? [unknown]: accessibility_statement: Is there a WCAG conformance statement? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified.
admin_ui_languages Is the admin interface available in German? [unknown]: admin_ui_languages: Is the admin interface available in German? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:i18n-pin.

Perplexity Enterprise

No public information found Support: not-published

We found no public information on this. A missing finding is not evidence that the product lacks the capability.

Administration and governance

ADM-01 Single sign-on and authentication

Judgment rule: Record SAML, OIDC, Microsoft Entra ID, Google, LDAP, MFA enforcement, conditional-access compatibility, domain verification and plan restrictions. Test one SSO login on a trial where possible.

LibreChat

Agent cross-checked Support: partial

Self-hosted authentication supports OAuth/OIDC, SAML and LDAP; local/LDAP TOTP can be enforced.

Limitations

conditional_access: Entra authentication and token reuse are documented, but an actual conditional-access/device-policy login was not tested.
domain_capture: Can the company claim its email domain? Registration/domain filters were not established as a tenant-wide company-domain ownership claim.

sso_protocols Which SSO protocols and identity providers work? [supported]: OIDC/OAuth providers include Entra, Google, Keycloak and Auth0; SAML and LDAP are documented separately. Sources: librechat:librechat:openid, librechat:librechat:saml, librechat:librechat:auth.
sso_plan Which plan includes SSO? [supported]: The authentication configuration belongs to the MIT self-hosted project, with no separate SSO licence tariff. Sources: librechat:librechat:license, librechat:librechat:auth.
mfa Can MFA be enforced? [supported]: ENFORCE_TWO_FACTOR_AUTHENTICATION requires local/LDAP enrollment and prevents disabling it; federated accounts depend on IdP MFA. Sources: librechat:librechat:auth.
conditional_access Do Entra conditional-access policies apply? [partial]: Entra authentication and token reuse are documented, but an actual conditional-access/device-policy login was not tested. Sources: librechat:librechat:entra.
domain_capture Can the company claim its email domain? [unknown]: domain_capture: Can the company claim its email domain? Registration/domain filters were not established as a tenant-wide company-domain ownership claim.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:openid, librechat:librechat:saml, librechat:librechat:auth, librechat:librechat:license, librechat:librechat:entra.

Perplexity Enterprise

Agent cross-checked Support: partial

Paid Enterprise SSO and DNS-verified domains exist; enforcement details need a tenant check.

Limitations

Remaining atomic gaps: mfa, conditional_access.

sso_protocols Which SSO protocols and identity providers work? [partial]: Enterprise material names SAML SSO; setup permits one identity provider by default. Exact protocol versions and OIDC support matrix were not retrieved. Sources: perplexity:perplexity:p-hub-faq, perplexity:perplexity:p-sso.
sso_plan Which plan includes SSO? [supported]: SSO is available for paid organisations, scoped here to Enterprise Pro/Max. Sources: perplexity:perplexity:p-sso.
mfa Can MFA be enforced? [unknown]: Unknown for mfa. Paid SSO and DNS domain verification are documented. Exact supported protocol versions, customer-enforced MFA and Entra conditional-access behavior were not verified.
conditional_access Do Entra conditional-access policies apply? [unknown]: Unknown for conditional_access. Paid SSO and DNS domain verification are documented. Exact supported protocol versions, customer-enforced MFA and Entra conditional-access behavior were not verified.
domain_capture Can the company claim its email domain? [partial]: Admins verify domains by DNS TXT. Users must be invited for SSO; verification does not establish capture of every personal account on that domain. Sources: perplexity:perplexity:p-sso.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-hub-faq, perplexity:perplexity:p-sso.

ADM-02 User provisioning and lifecycle

Judgment rule: Record SCIM, just-in-time provisioning, group sync from the identity provider, deprovisioning effects (chats, assistants, knowledge ownership transfer) and licence assignment. Deprovision a test user and record what happens to their content.

LibreChat

Agent cross-checked Support: partial

Entra group synchronization and federated account creation are documented; SCIM and leaver content transfer remain unknown.

Limitations

scim: Is SCIM provisioning supported? SCIM was not established in the authentication/access docs or pinned repository path review. No two-user deprovisioning fixture was run.
deprovisioning: The docs provide user deletion scripts, but content ownership transfer and revocation behavior were not fixture-tested.
seat_assignment: Operators manage accounts/roles under an MIT licence; there is no per-seat licence entitlement in the scoped source.

scim Is SCIM provisioning supported? [unknown]: scim: Is SCIM provisioning supported? SCIM was not established in the authentication/access docs or pinned repository path review. No two-user deprovisioning fixture was run.
group_sync Are identity-provider groups synced? [supported]: With Entra OIDC token reuse, Graph groups sync at login; resource ACL principal membership has a documented cache. Sources: librechat:librechat:access, librechat:librechat:entra.
jit_provisioning Are users created at first login? [supported]: Federated login creates accounts according to the authentication configuration; OpenID/SAML registration cannot be independently disabled. Sources: librechat:librechat:auth.
deprovisioning What happens to a removed user's data and shared assets? [partial]: The docs provide user deletion scripts, but content ownership transfer and revocation behavior were not fixture-tested. Sources: librechat:librechat:auth.
seat_assignment Can admins assign and reclaim seats? [partial]: Operators manage accounts/roles under an MIT licence; there is no per-seat licence entitlement in the scoped source. Sources: librechat:librechat:auth, librechat:librechat:license.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:access, librechat:librechat:entra, librechat:librechat:auth, librechat:librechat:license.

Perplexity Enterprise

Agent cross-checked Support: partial

Core SCIM provisioning and legacy role mapping are documented separately from the gradually rolled-out managed Roles & Permissions directory-group controls.

Availability: generally-available · Delivery: native
Scope: surfaces=Enterprise Ask, Projects and Search web client; version=not specified; plan=Legacy SCIM route: 50 seats or one Enterprise Max seat per SCIM guide; new directory groups/custom roles only on eligible sales-assisted managed plans after UI upgrade; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

Remaining atomic gaps: jit_provisioning.
New directory-group/custom-role capability is not inferred from the older numeric SCIM threshold. The guides describe different UI generations; no rollout completion is assumed.

scim Is SCIM provisioning supported? [partial]: The SCIM guide documents provisioning for organizations with at least 50 seats or one Max seat. This is not evidence that self-serve Pro/Max includes the newer custom-role or directory-group controls; those depend on eligible sales-assisted plans and UI upgrade. Sources: perplexity:perplexity:p-scim, perplexity:perplexity:p-roles-rollout-correction.
group_sync Are identity-provider groups synced? [partial]: The new Roles & Permissions guide supports upstream, read-only SCIM directory groups on eligible managed plans. Its explicit gradual-upgrade notice reconciles this with the legacy guide's Admin/Member role mapping; entitlement and UI generation must be checked for a specific tenant. Sources: perplexity:perplexity:p-scim, perplexity:perplexity:p-roles-rollout-correction.
jit_provisioning Are users created at first login? [unknown]: Unknown for jit_provisioning. SCIM and roles pages describe different plan generations. JIT behaviour and complete departing-user/shared-asset reassignment were not verified.
deprovisioning What happens to a removed user's data and shared assets? [partial]: SCIM manages account lifecycle; departing members lose organisation memory and credits do not transfer. Shared Project ownership and data reassignment remain unverified. Sources: perplexity:perplexity:p-scim, perplexity:perplexity:p-memory, perplexity:perplexity:p-credits.
seat_assignment Can admins assign and reclaim seats? [supported]: Admins add/remove users. Removal frees a seat but does not lower the paid seat count or refund the current term; billing reductions apply next period. Sources: perplexity:perplexity:p-billing.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-scim, perplexity:perplexity:p-roles, perplexity:perplexity:p-memory, perplexity:perplexity:p-credits, perplexity:perplexity:p-billing, perplexity:perplexity:p-roles-rollout-correction.

ADM-03 Roles, groups and feature permissions

Judgment rule: Record admin roles, delegated admins, groups, per-feature permissions (web search, image generation, connectors, file upload, agents), separation of subsidiaries or departments, and enforcement. Test one disabled feature for one group.

LibreChat

Agent cross-checked Support: partial

Role permissions, resource ACLs and system grants support granular governance; the separate management UI remains preview.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server, Separately deployed LibreChat Admin Panel preview; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Separate Admin Panel preview for GUI management; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

Separate admin management UI is preview; the core authorization model is documented as available.
No two-group disabled-feature fixture was run.

admin_roles Which admin roles exist, and can admin rights be delegated? [supported]: ADMIN/USER and custom roles exist; capability grants can delegate selected administrative functions without full admin. Sources: librechat:librechat:access.
groups Can permissions be set per group? [supported]: Local and Entra groups can receive ACLs, system grants and configuration overrides. Sources: librechat:librechat:access, librechat:librechat:admin.
feature_toggles Which features can be switched on or off per group? [supported]: Permissions include Agents, MCP, prompts, memory, search, file search/citations and code execution. Sources: librechat:librechat:access.
multi_entity Can subsidiaries or departments be separated within one contract? [partial]: Tenant-scoped API queries and group/configuration boundaries are documented. A commercial multi-entity contract and tested tenant isolation were not established. Sources: librechat:librechat:insights, librechat:librechat:access.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:access, librechat:librechat:admin, librechat:librechat:insights.

Perplexity Enterprise

Agent cross-checked Support: partial

Sales-assisted Roles & Permissions provides delegated roles and group-based feature grants.

Availability: generally-available · Delivery: native
Scope: surfaces=Enterprise Ask, Projects and Search web client; version=not specified; plan=Sales-assisted Enterprise; custom roles/groups and SCIM sync depend on contracted plan; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

Remaining atomic gaps: multi_entity.

admin_roles Which admin roles exist, and can admin rights be delegated? [supported]: Admin, Member and Billing Admin base roles plus custom roles and delegated permissions. Member applies to everyone; grants are additive. Sources: perplexity:perplexity:p-roles.
groups Can permissions be set per group? [supported]: Custom roles assign users/groups; SCIM groups are read-only in Perplexity. Availability depends on the managed contract. Sources: perplexity:perplexity:p-roles.
feature_toggles Which features can be switched on or off per group? [partial]: Organisation master switches bound Computer/Comet grants; connector RBAC enforces runtime permissions. Full group matrix and group model settings remain unverified. Sources: perplexity:perplexity:p-roles, perplexity:perplexity:p-connector-rbac.
multi_entity Can subsidiaries or departments be separated within one contract? [unknown]: Unknown for multi_entity. New Roles & Permissions are sales-assisted and staged. One-contract multi-entity isolation and the complete group feature matrix were not established.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-roles, perplexity:perplexity:p-connector-rbac.

ADM-04 Usage and adoption analytics

Judgment rule: Record dashboards for active users, usage by feature, model, group and assistant, export, and privacy controls (aggregation, pseudonymisation, works-council-friendly settings). Distinguish aggregate adoption metrics from per-person monitoring.

LibreChat

Agent cross-checked Support: partial

Optional Insights reports identifiable activity; token transactions and optional tracing are separate sources of usage detail.

Limitations

breakdowns: Insights supports Agent filtering and user activity; recorded token/context cost details are per model/endpoint. Complete group/feature/assistant exports were not established.
export: Can usage data be exported? A documented complete admin analytics export and group/cost-centre dataset were not verified.
privacy_modes: Insights is off unless enabled and is capability-gated; it can display names, emails and first-message content. Pseudonymized reporting was not established.

adoption_dashboard Is there an adoption dashboard? [supported]: Opt-in Insights reports conversations, unique users, messages, tokens, top users and recent conversations. Sources: librechat:librechat:insights.
breakdowns Can usage be broken down by group, model, feature and assistant? [partial]: Insights supports Agent filtering and user activity; recorded token/context cost details are per model/endpoint. Complete group/feature/assistant exports were not established. Sources: librechat:librechat:insights, librechat:librechat:tokens.
export Can usage data be exported? [unknown]: export: Can usage data be exported? A documented complete admin analytics export and group/cost-centre dataset were not verified.
privacy_modes Can per-person reporting be limited or pseudonymised? [partial]: Insights is off unless enabled and is capability-gated; it can display names, emails and first-message content. Pseudonymized reporting was not established. Sources: librechat:librechat:insights.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:insights, librechat:librechat:tokens.

Perplexity Enterprise

Agent cross-checked Support: partial

Enterprise Insights offers adoption and per-user usage exports for eligible organisations.

Availability: generally-available · Delivery: native
Scope: surfaces=Enterprise Ask, Projects and Search web client; version=not specified; plan=Enterprise with 50 seats or at least one Enterprise Max; admins; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

Remaining atomic gaps: privacy_modes.

adoption_dashboard Is there an adoption dashboard? [supported]: Eligible admins with 50 seats or one Max see Insights users, monthly active users, monthly queries and weekly feature use. Sources: perplexity:perplexity:p-analytics.
breakdowns Can usage be broken down by group, model, feature and assistant? [partial]: Feature, internal-files/web and per-user 7/30-day queries documented. Group, model and assistant dimensions remain unverified. Sources: perplexity:perplexity:p-analytics.
export Can usage data be exported? [partial]: Usage tables can be filtered and exported. Exact download format/schema was not retrieved. Sources: perplexity:perplexity:p-analytics.
privacy_modes Can per-person reporting be limited or pseudonymised? [unknown]: Unknown for privacy_modes. Insights exports and per-user reporting are documented, but a group/model/assistant breakdown and customer pseudonymisation controls were not retrieved.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-analytics.

ADM-05 Spend controls and cost allocation

Judgment rule: Record cost visibility per user, group and cost centre, budgets and their behaviour (alert, block, downgrade model), pooled credits, and chargeback exports. Test a small budget on a trial where possible. Distinguish billed amounts, estimates and unavailable amounts.

LibreChat

Agent cross-checked Support: partial

Optional token-credit balances block admission when insufficient; credit estimates differ from actual cloud invoices.

Limitations

cost_visibility: Token transactions and configured token prices support per-user/model estimates. Insights explicitly reports activity rather than monetary billing.
budgets: Optional per-user start balances and automatic refills are documented. Group/cost-centre pooled budgets were not established.
chargeback: Can costs be exported per cost centre? Cost-centre chargeback exports and reconciliation to actual vendor invoices were not established.

cost_visibility Can admins see cost or consumption per user and group? [partial]: Token transactions and configured token prices support per-user/model estimates. Insights explicitly reports activity rather than monetary billing. Sources: librechat:librechat:tokens, librechat:librechat:insights.
budgets Can budgets be set per user or group? [partial]: Optional per-user start balances and automatic refills are documented. Group/cost-centre pooled budgets were not established. Sources: librechat:librechat:balance.
budget_enforcement Does reaching a budget alert, block or downgrade? [supported]: Pinned balance middleware reserves estimated token cost and throws an error if credits cannot be reserved; no low-budget trial was run. Sources: librechat:librechat:balance-pin.
chargeback Can costs be exported per cost centre? [unknown]: chargeback: Can costs be exported per cost centre? Cost-centre chargeback exports and reconciliation to actual vendor invoices were not established.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:tokens, librechat:librechat:insights, librechat:librechat:balance, librechat:librechat:balance-pin.

Perplexity Enterprise

Agent cross-checked Support: partial

Computer credits have user/group caps and organisation funding limits, with asynchronous authorization refresh.

Availability: generally-available · Delivery: native
Scope: surfaces=Enterprise Ask, Projects and Search web client, Enterprise Computer cloud tasks and scheduled automation; version=Named usage-limit and funding controls; purchased-pool expiry unverified; plan=Enterprise Pro/Max; sales-assisted roles or connector RBAC only where stated; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

Remaining atomic gaps: chargeback.
Capabilities apply only to the surface named in each atomic answer. Computer, Office/Teams and Portable do not establish feature parity in Ask/Search.
Purchased-pool expiry is explicitly excluded from the confirmed budget-control finding. Monthly seat grants separately expire at cycle end.

cost_visibility Can admins see cost or consumption per user and group? [partial]: Credits page shows user grants/use/remainder, group allocations, pool usage and applied limits. This is credit reporting, not a complete currency chargeback ledger. Sources: perplexity:perplexity:p-credits.
budgets Can budgets be set per user or group? [supported]: Named pool caps assign users/groups. Highest group limit wins; personal override precedes group, organisation default and legacy fallback. Auto-refill has a monthly reload limit. Sources: perplexity:perplexity:p-credits.
budget_enforcement Does reaching a budget alert, block or downgrade? [partial]: An empty pool or applicable cap blocks further use; funding or raising limits restores access, subject to asynchronous authorization/SCIM refresh. Purchased-pool expiry is unknown: the guide body says 12 months of inactivity and its FAQ says no current expiry. No non-expiry guarantee or overshoot bound is asserted. Sources: perplexity:perplexity:p-credits.
chargeback Can costs be exported per cost centre? [unknown]: Unknown for chargeback. Credit limits are documented, but no complete cost-centre chargeback export schema or measured enforcement/cache latency was retrieved.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-credits.

ADM-06 Audit logs and compliance export

Judgment rule: Record which events are logged (logins, admin changes, prompts, responses, file access, connector queries), retention, export or SIEM streaming, and eDiscovery/legal hold. Use the word audit only with a defined retention and integrity model.

LibreChat

Agent cross-checked Support: partial

Operational logs and persisted chats are available; a complete audit retention/integrity or eDiscovery system was not verified.

Limitations

admin_events: Backend logs capture errors/debug activity and can include operational/security actions. A complete immutable admin-event schema was not established.
content_logging: Chats are persisted in MongoDB subject to retention settings; external tracing is optional. This is not a verified compliance archive.
siem_export: Operators can feed log files to external systems such as ELK. A native managed SIEM stream and integrity guarantee were not verified.
ediscovery: Are eDiscovery and legal hold supported? No eDiscovery/legal hold, tamper-evident archive or complete prompt/file/connector event coverage was verified.
log_retention: The logging guide describes 14-day rotation. Rotation is not evidence of an enforced legal retention or deletion guarantee across external sinks.

admin_events Are admin and security events logged? [partial]: Backend logs capture errors/debug activity and can include operational/security actions. A complete immutable admin-event schema was not established. Sources: librechat:librechat:logging.
content_logging Can prompts and answers be retained for compliance, and is it configurable? [partial]: Chats are persisted in MongoDB subject to retention settings; external tracing is optional. This is not a verified compliance archive. Sources: librechat:librechat:retention, librechat:librechat:compose-pin.
siem_export Can logs stream to a SIEM or be exported? [partial]: Operators can feed log files to external systems such as ELK. A native managed SIEM stream and integrity guarantee were not verified. Sources: librechat:librechat:logging.
ediscovery Are eDiscovery and legal hold supported? [unknown]: ediscovery: Are eDiscovery and legal hold supported? No eDiscovery/legal hold, tamper-evident archive or complete prompt/file/connector event coverage was verified.
log_retention How long are logs kept? [partial]: The logging guide describes 14-day rotation. Rotation is not evidence of an enforced legal retention or deletion guarantee across external sinks. Sources: librechat:librechat:logging.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:logging, librechat:librechat:retention, librechat:librechat:compose-pin.

Perplexity Enterprise

Agent cross-checked Support: partial

Eligible enterprises can stream content-bearing audit events to a SIEM; this enables admin access to prompts and answers.

Availability: generally-available · Delivery: native
Scope: surfaces=Enterprise Ask, Projects and Search web client; version=not specified; plan=Enterprise with 50 seats or one Enterprise Max; audit webhook enabled; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

Remaining atomic gaps: ediscovery.

admin_events Are admin and security events logged? [supported]: Events cover login, settings, membership, roles/groups, files, connectors and Computer tasks/actions/errors. Sources: perplexity:perplexity:p-audit.
content_logging Can prompts and answers be retained for compliance, and is it configurable? [partial]: Query payload includes text; answer payload includes full answer and model. Audit configuration enables export. Fine-grained content exclusions remain unverified; admin-private chat cannot be assumed. Sources: perplexity:perplexity:p-audit, perplexity:perplexity:p-roles.
siem_export Can logs stream to a SIEM or be exported? [supported]: Realtime HTTP POST JSON with bearer/custom auth; Splunk HEC supported. Slack truncates metadata to 500 characters/value and 2,500 total, so it is not a full-content archive. Sources: perplexity:perplexity:p-audit.
ediscovery Are eDiscovery and legal hold supported? [unknown]: Unknown for ediscovery. Audit webhooks are documented. Vendor log retention, replay guarantees, tamper resistance, legal hold and an eDiscovery integration were not retrieved.
log_retention How long are logs kept? [partial]: Guide tells customers to retain/export logs long term. Vendor retention, replay window and immutability were not retrieved. Sources: perplexity:perplexity:p-audit.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-audit, perplexity:perplexity:p-roles.

ADM-07 Data loss prevention and personal data

Judgment rule: Record detection and handling of personal and confidential data before it reaches a model: redaction, masking, blocking, warning. Record integration with Purview, Netskope or similar, and whether filtering runs locally or at a third party. Send a fixture prompt with a Swiss AHV number and IBAN and record the outcome.

LibreChat

Agent cross-checked Support: partial

Optional server-side content filters support configured pattern detection, blocking and auditing, plus narrowly scoped Agent text redaction. External DLP integration and fixture accuracy remain unknown.

Availability: source-only · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Development source a378657583567310c841d652b0f6b00c83e2bd6b; current Latest (dev) documentation; limited redaction announced in config v1.3.18 on 2026-10-22; plan=Customer-operated LibreChat; optional base-YAML content policies, disabled unless configured; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

Development-source finding; no running instance or AHV/IBAN fixture.
Filtering is opt-in and limited to configured sources/fields. Default patterns cover credential shapes, not every PII class.
Redaction applies only to eligible fresh Agent text; encrypted originals remain stored.
A dedicated external DLP integration remains unverified.

pii_detection Is personal data detected in prompts and files? [partial]: Configured source-aware policies can inspect selected prompt fields and file names/extracted text/transcripts. Built-in starter rules match credentials; admins must supply additional personal-data patterns. Opaque files may be allowed by default or explicitly blocked. AHV/IBAN and confidential-file detection accuracy were not tested. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-pii-runtime, librechat:librechat:r4-patterns, librechat:librechat:r4-private-submission, librechat:librechat:r4-filter-middleware.
pii_action Is it redacted, masked, blocked or only warned? [partial]: Configured matches can block or audit. Redaction transforms only fresh, text-only interactive Agent submissions carrying clientRequestId and a valid CREDS_KEY; edits, resumes, files, quotes and other endpoints retain blocking checks. Original text is encrypted and unindexed, rather than discarded. No running deployment was tested. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-pii-runtime, librechat:librechat:r4-patterns, librechat:librechat:r4-private-submission, librechat:librechat:r4-filter-middleware.
custom_patterns Can admins add custom patterns or terms? [supported]: Operators can add labelled custom RE2JS regular expressions in base librechat.yaml, with optional categories. Database/role/group/user overrides cannot modify the policy; all replicas must load matching configuration. Invalid rules are rejected on configuration load. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-patterns, librechat:librechat:r4-filter-middleware.
dlp_integration Does it integrate with an existing DLP product? [unknown]: No first-party Purview/Netskope or other external DLP connector was established from the content-filter guide, current public repository tree and targeted official-site search. Configurable local patterns are not evidence of an external enterprise DLP integration.
filter_location Where does filtering run? [supported]: Inspected content-filter middleware and rule evaluation run in the customer-operated LibreChat API backend. Optional extraction/OCR and inference providers remain separate data flows; no named deployment region or traffic path was tested. Sources: librechat:librechat:r4-pii-runtime, librechat:librechat:r4-filter-middleware.

Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-pii-runtime, librechat:librechat:r4-patterns, librechat:librechat:r4-private-submission, librechat:librechat:r4-filter-middleware, librechat:librechat:r4-config-1318.

Perplexity Enterprise

No public information found Support: not-published

We found no public information on this. A missing finding is not evidence that the product lacks the capability.

ADM-08 AI policy and guardrails

Judgment rule: Record organisation-wide system instructions, acceptable-use notices and acknowledgement, content filters, topic restrictions, AI-output labelling, and admin visibility of policy violations. Separate enforced policy from instructions the model is expected to follow.

LibreChat

Agent cross-checked Support: partial

Operators can configure prompts and usage terms; abuse moderation is distinct from semantic content-policy enforcement.

Limitations

org_instructions: Enforced model-spec presets and Agent instructions can guide behavior; model-followed instructions are not guaranteed policy enforcement.
content_filters: Automated moderation scores rate/authentication/message abuse and can ban users. Semantic topic or PII policy coverage was not established.
violation_reporting: Abuse scoring is documented, but a complete organization content-policy violation dashboard and reporting fixture were not established.

org_instructions Can admins set organisation-wide instructions? [partial]: Enforced model-spec presets and Agent instructions can guide behavior; model-followed instructions are not guaranteed policy enforcement. Sources: librechat:librechat:modelspec, librechat:librechat:agents.
usage_notice Can users be required to accept a usage policy? [supported]: Interface configuration includes custom terms of service and acceptance settings. Sources: librechat:librechat:interface.
content_filters Are content filters configurable? [partial]: Automated moderation scores rate/authentication/message abuse and can ban users. Semantic topic or PII policy coverage was not established. Sources: librechat:librechat:mod.
violation_reporting Are policy hits visible to admins? [partial]: Abuse scoring is documented, but a complete organization content-policy violation dashboard and reporting fixture were not established. Sources: librechat:librechat:mod.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:modelspec, librechat:librechat:agents, librechat:librechat:interface, librechat:librechat:mod.

Perplexity Enterprise

No public information found Support: not-published

We found no public information on this. A missing finding is not evidence that the product lacks the capability.

Data protection and sovereignty

DATA-01 Hosting location and data residency

Judgment rule: Record country or region separately for chat storage, files and indexes, model inference, backups, logs and telemetry, and support access. Name the cloud provider. Record whether residency is default, a paid option or plan-dependent. "EU data boundary" programmes are recorded with their documented exceptions.

LibreChat

Agent cross-checked Support: partial

Customer operators choose storage and service locations; external model, OCR, search and code services need separate residency decisions.

Limitations

backups_logs_region: Logs and mounted data reside in the configured deployment; backup, telemetry and optional tracing geographies depend on operator choices and were not audited.
support_access_region: From where can vendor staff access data? No vendor or integrator support-access country restriction was reviewed for this customer-operated deployment.
swiss_hosting: A customer may run the software on Swiss infrastructure; no bundled Swiss managed inference/support commitment was established.

storage_region Where are chats, files and indexes stored? [supported]: The reference self-hosted stack keeps application data in configured MongoDB/files and retrieval data in PGVector. Its country is chosen by the deployer. Sources: librechat:librechat:compose-pin, librechat:librechat:remote.
inference_region Where do model calls run, per provider? [supported]: Customer-selected cloud endpoints/regions or local endpoints determine inference; hosting LibreChat in Switzerland does not place every external model there. Sources: librechat:librechat:custom, librechat:librechat:bedrock, librechat:librechat:vertex.
backups_logs_region Where are backups, logs and telemetry? [partial]: Logs and mounted data reside in the configured deployment; backup, telemetry and optional tracing geographies depend on operator choices and were not audited. Sources: librechat:librechat:logging, librechat:librechat:compose-pin.
support_access_region From where can vendor staff access data? [unknown]: support_access_region: From where can vendor staff access data? No vendor or integrator support-access country restriction was reviewed for this customer-operated deployment.
swiss_hosting Is Swiss hosting available? [partial]: A customer may run the software on Swiss infrastructure; no bundled Swiss managed inference/support commitment was established. Sources: librechat:librechat:remote, librechat:librechat:license.
residency_plan Which plan or option provides residency? [supported]: Customer-controlled placement is a self-hosted deployment property, not a separately priced residency licence. Sources: librechat:librechat:remote, librechat:librechat:license.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:compose-pin, librechat:librechat:remote, librechat:librechat:custom, librechat:librechat:bedrock, librechat:librechat:vertex, librechat:librechat:logging, librechat:librechat:license.

Perplexity Enterprise

Agent cross-checked Support: partial

AWS storage is named for connector copies; a full cloud residency commitment is unavailable.

Availability: unknown · Delivery: native
Scope: surfaces=Enterprise Ask, Projects and Search web client, Portable Computer local inference on supported NVIDIA Windows/Linux hardware; version=not specified; plan=Enterprise Pro/Max; sales-assisted roles or connector RBAC only where stated; add_ons=none stated; deployment_mode=not specified; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

Remaining atomic gaps: backups_logs_region, swiss_hosting, residency_plan.
Capabilities apply only to the surface named in each atomic answer. Computer, Office/Teams and Portable do not establish feature parity in Ask/Search.
Hosted functions use Perplexity cloud services; Portable local execution is device-local on supported NVIDIA hardware. Portable is not a self-hosted Enterprise backend.

storage_region Where are chats, files and indexes stored? [partial]: FAQ names AWS S3 for connector copies without a region. Cloud chat/index residency and EU/Swiss SKU remain unknown; Portable local files/models can remain on the customer's device. Sources: perplexity:perplexity:p-connectfaq, perplexity:perplexity:p-local.
inference_region Where do model calls run, per provider? [partial]: Portable local inference runs on the customer's device; approved cloud steps leave it. Cloud per-provider inference countries remain unknown. Sources: perplexity:perplexity:p-local.
backups_logs_region Where are backups, logs and telemetry? [unknown]: Unknown for backups_logs_region. Cloud connector copies use AWS S3, but no binding Enterprise storage/inference/backups/logs/support region matrix or Swiss/EU residency SKU was retrieved. Portable local execution is scoped separately.
support_access_region From where can vendor staff access data? [partial]: Security material describes just-in-time scoped staff production access, without access countries or customer region restrictions. Sources: perplexity:perplexity:p-security.
swiss_hosting Is Swiss hosting available? [unknown]: Unknown for swiss_hosting. Cloud connector copies use AWS S3, but no binding Enterprise storage/inference/backups/logs/support region matrix or Swiss/EU residency SKU was retrieved. Portable local execution is scoped separately.
residency_plan Which plan or option provides residency? [unknown]: Unknown for residency_plan. Cloud connector copies use AWS S3, but no binding Enterprise storage/inference/backups/logs/support region matrix or Swiss/EU residency SKU was retrieved. Portable local execution is scoped separately.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-connectfaq, perplexity:perplexity:p-local, perplexity:perplexity:p-security.

DATA-02 Deployment options

Judgment rule: Record multi-tenant SaaS, dedicated single-tenant instance, deployment in the customer's cloud account, on-premise and air-gapped as separate options with plan and availability. Record which features are missing in each mode, who operates it, and the documented seat or contract threshold for each mode, which can differ from the enterprise plan threshold (e.g. dedicated SaaS from 2,000 seats, own cloud from 5,000). A local-network connector or gateway that reaches on-prem data from a vendor-hosted platform is KNOW-03, not on-premise deployment.

LibreChat

Agent cross-checked Support: partial

The project documents local and customer-cloud installs. A free public demo is separate from a production managed service.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server, LibreChat public evaluation demo; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

multi_tenant_saas: The project operates a free public evaluation Demo, not a reviewed production business SaaS offer. Its terms permit data cleanups and disclaim persistence.
dedicated_instance: Is a dedicated single-tenant instance offered, from what size? A vendor-operated dedicated production service and its contractual size floor were not established.
air_gapped: Local chat/embedding routes exist, but a complete disconnected installation and its full dependency behavior were not verified.
mode_feature_gaps: External APIs, OCR/search services and separate code runtimes need their own availability/networking; there is no verified SaaS/on-prem feature-parity matrix.

multi_tenant_saas Is a shared SaaS offered? [partial]: The project operates a free public evaluation Demo, not a reviewed production business SaaS offer. Its terms permit data cleanups and disclaim persistence. Sources: librechat:librechat:demo, librechat:librechat:firstchat.
dedicated_instance Is a dedicated single-tenant instance offered, from what size? [unknown]: dedicated_instance: Is a dedicated single-tenant instance offered, from what size? A vendor-operated dedicated production service and its contractual size floor were not established.
customer_cloud Can it run in the customer's own cloud account, from what size? [supported]: Remote hosting documentation describes customer-selected servers/cloud hosting without a software seat minimum. Sources: librechat:librechat:remote, librechat:librechat:license.
on_premise Can the whole platform run on customer infrastructure, from what size? [supported]: Docker/npm installation can run the application and dependencies on customer infrastructure. Sources: librechat:librechat:local, librechat:librechat:compose-pin.
air_gapped Can it run without internet access? [partial]: Local chat/embedding routes exist, but a complete disconnected installation and its full dependency behavior were not verified. Sources: librechat:librechat:custom, librechat:librechat:ragcfg.
mode_feature_gaps Which features are missing outside SaaS? [partial]: External APIs, OCR/search services and separate code runtimes need their own availability/networking; there is no verified SaaS/on-prem feature-parity matrix. Sources: librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:code.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:demo, librechat:librechat:firstchat, librechat:librechat:remote, librechat:librechat:license, librechat:librechat:local, librechat:librechat:compose-pin, librechat:librechat:custom, librechat:librechat:ragcfg, librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:code.

Perplexity Enterprise

Agent cross-checked Support: partial

Cloud Enterprise and Portable local execution coexist; local mode is not a complete hosted Enterprise replacement.

Availability: generally-available · Delivery: native
Scope: surfaces=Enterprise Computer cloud tasks and scheduled automation, Portable Computer local inference on supported NVIDIA Windows/Linux hardware; version=not specified; plan=Enterprise Pro/Max; sales-assisted roles or connector RBAC only where stated; add_ons=none stated; deployment_mode=not specified; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

Remaining atomic gaps: dedicated_instance, customer_cloud.

multi_tenant_saas Is a shared SaaS offered? [partial]: Enterprise is vendor-hosted. Computer cloud tasks have isolated per-session environments; complete SaaS multi-tenancy architecture was not published in the inspected guide. Sources: perplexity:perplexity:p-billing, perplexity:perplexity:p-computer.
dedicated_instance Is a dedicated single-tenant instance offered, from what size? [unknown]: Unknown for dedicated_instance. Portable Computer supports local execution, but no whole-Enterprise single-tenant, customer-cloud, on-prem or air-gap deployment terms or seat floor were retrieved.
customer_cloud Can it run in the customer's own cloud account, from what size? [unknown]: Unknown for customer_cloud. Portable Computer supports local execution, but no whole-Enterprise single-tenant, customer-cloud, on-prem or air-gap deployment terms or seat floor were retrieved.
on_premise Can the whole platform run on customer infrastructure, from what size? [partial]: Portable runs model, agent, scheduler, queue, local index and sandbox on customer hardware. Whole Enterprise control plane/Projects/SSO hosting and seat minimum remain unverified. Sources: perplexity:perplexity:p-local.
air_gapped Can it run without internet access? [partial]: Local tasks do not need a cloud round trip after setup. Sign-in, model/engine downloads and cloud steps need internet. Fully air-gapped Enterprise operation and offline licence lifetime remain unknown. Sources: perplexity:perplexity:p-local.
mode_feature_gaps Which features are missing outside SaaS? [supported]: Local mode excludes Brain/saved memory and loads one smaller model at a time. Web research, frontier models or cloud tools may require approved, credit-consuming escalation. Sources: perplexity:perplexity:p-local.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-billing, perplexity:perplexity:p-computer, perplexity:perplexity:p-local.

DATA-03 Training use and provider retention

Judgment rule: Record whether customer content trains vendor or provider models, by plan and default; zero-data-retention arrangements with model providers; abuse-monitoring retention and human review; and the model provider's terms that apply. A "no training" claim on a marketing page is `vendor-claimed` until the contract or DPA says so.

LibreChat

Agent cross-checked Support: partial

The customer configures model contracts and data paths; a universal no-training or provider-retention promise was not established.

Limitations

vendor_training: The self-hosted application stores data in the customer’s configured stack; this architecture is not a contractual promise covering every optional external service.
provider_training: Do model providers train on it under this product's contracts? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers.
provider_retention: How long do model providers keep prompts, including for abuse monitoring? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers.
zero_retention: Is zero data retention available, and on which plan? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers.
human_review: Can provider staff review content? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers.

vendor_training Does the vendor train on customer content? [partial]: The self-hosted application stores data in the customer’s configured stack; this architecture is not a contractual promise covering every optional external service. Sources: librechat:librechat:compose-pin, librechat:librechat:firstchat.
provider_training Do model providers train on it under this product's contracts? [unknown]: provider_training: Do model providers train on it under this product's contracts? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers.
provider_retention How long do model providers keep prompts, including for abuse monitoring? [unknown]: provider_retention: How long do model providers keep prompts, including for abuse monitoring? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers.
zero_retention Is zero data retention available, and on which plan? [unknown]: zero_retention: Is zero data retention available, and on which plan? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers.
human_review Can provider staff review content? [unknown]: human_review: Can provider staff review content? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:compose-pin, librechat:librechat:firstchat.

Perplexity Enterprise

Agent cross-checked Support: partial

Enterprise terms prohibit model training; per-provider retention and review are unverified.

Limitations

Remaining atomic gaps: provider_retention.

vendor_training Does the vendor train on customer content? [supported]: Enterprise terms 1.3.3 prohibit using customer content to train, retrain, fine-tune or improve generative AI. Nonpersonal/aggregated usage data can improve operations. Specific product terms control conflicts. Sources: perplexity:perplexity:p-terms-gb.
provider_training Do model providers train on it under this product's contracts? [supported]: Same clause prohibits authorising third parties to train on customer content. Provider contracts and retention exceptions were not inspected. Sources: perplexity:perplexity:p-terms-gb.
provider_retention How long do model providers keep prompts, including for abuse monitoring? [unknown]: Unknown for provider_retention. Enterprise no-training terms are explicit. Per-model abuse-monitoring retention, zero-retention add-ons and provider human-review rules were not retrieved.
zero_retention Is zero data retention available, and on which plan? [partial]: Enforced Incognito retains sessions/attachments for 24 hours. Provider-level zero-retention contracts or add-ons were not established. Sources: perplexity:perplexity:p-security-hub.
human_review Can provider staff review content? [partial]: Vendor documents just-in-time staff production access. Model-provider human-review rules remain unknown; absolute no-staff-access cannot be claimed. Sources: perplexity:perplexity:p-security.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-terms-gb, perplexity:perplexity:p-security-hub, perplexity:perplexity:p-security.

DATA-04 Retention and deletion

Judgment rule: Record default retention for chats, files, indexes and logs; admin-configured retention; user deletion; deletion after contract end; and deletion confirmation.

LibreChat

Agent cross-checked Support: partial

Normal chats have no default expiry; temporary chats default to 30 days and admins can configure broader expiry modes.

Limitations

user_deletion: Users can delete conversations/data and retention sweeps remove files. Copies, backups and external provider deletion were not end-to-end verified.
contract_end_deletion: What is deleted at contract end, and when? No commercial contract-end purge/confirmation deadline was reviewed; the Demo’s retention terms are a separate offer.

default_retention What is retained and for how long by default? [supported]: The default temporary retention is 720 hours; normal chats persist unless configured under all/ephemeral modes. Memories do not expire with chats. Sources: librechat:librechat:retention.
admin_retention Can admins set retention periods? [supported]: Admins set all or ephemeral retention, regular/temporary deadlines and Agent file retention. New settings apply on later saves rather than rewriting every existing record immediately. Sources: librechat:librechat:retention.
user_deletion Can users delete their chats and files permanently? [partial]: Users can delete conversations/data and retention sweeps remove files. Copies, backups and external provider deletion were not end-to-end verified. Sources: librechat:librechat:retention, librechat:librechat:settings.
contract_end_deletion What is deleted at contract end, and when? [unknown]: contract_end_deletion: What is deleted at contract end, and when? No commercial contract-end purge/confirmation deadline was reviewed; the Demo’s retention terms are a separate offer.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:retention, librechat:librechat:settings.

Perplexity Enterprise

Agent cross-checked Support: partial

The cited English DPA describes personal-data deletion/return within 30 days after service end, subject to its exceptions. This does not establish the terms of a French-language or individually negotiated agreement.

Availability: generally-available · Delivery: native
Scope: surfaces=Enterprise Ask, Projects and Search web client; version=English en-GB DPA August 13, 2026 and Enterprise terms August 3, 2026; French edition not included in contractual finding; plan=Enterprise agreement incorporating the cited English DPA; executed agreement and alternate-language contract terms unverified; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

The partial atomic answers state their documentation or verification limits.
The July 2025 French Annex uses later-of wording. It is not treated as an equivalent translation or superseded contract. Applicable language/version for a particular customer remains unknown; this claim is restricted to the named English documents.

default_retention What is retained and for how long by default? [partial]: Session files default to seven days; My Files/Projects persist under their own deletion policies. Enforced Incognito retains sessions/attachments for 24 hours. Ordinary default session duration remains unknown. Sources: perplexity:perplexity:p-retention, perplexity:perplexity:p-security-hub.
admin_retention Can admins set retention periods? [supported]: Custom session retention requires 50 seats or one Max, measured from last activity. Shortening hides older data immediately and deletes within seven days; pre-join personal sessions excluded. Sources: perplexity:perplexity:p-retention.
user_deletion Can users delete their chats and files permanently? [partial]: Under the cited August 13 English DPA, Annex 1 uses the earlier of customer deletion or 30 days after service end. This is an English-document finding only; application retention policies apply and backup completion was not tested. Sources: perplexity:perplexity:p-dpa-gb, perplexity:perplexity:p-retention.
contract_end_deletion What is deleted at contract end, and when? [supported]: Section 10 of the cited English DPA requires personal-data deletion/return within 30 days after service end, with legal retention exceptions. The English Enterprise terms allow automated backups under standard deletion procedures. The finding applies only where those documents govern. Sources: perplexity:perplexity:p-dpa-gb, perplexity:perplexity:p-terms-gb.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-retention, perplexity:perplexity:p-security-hub, perplexity:perplexity:p-dpa-gb, perplexity:perplexity:p-terms-gb.

DATA-05 Sub-processors and foreign-law exposure

Judgment rule: Record the published sub-processor list with countries, change-notification rules, the vendor's and parent company's jurisdiction, transfer mechanisms (EU-US Data Privacy Framework, Swiss-US DPF, SCCs) and the vendor's documented position on foreign government access requests (e.g. US CLOUD Act). Record facts, not a legal assessment.

LibreChat

Agent cross-checked Support: partial

ClickHouse’s acquisition is sourced; the self-hosted deployment still selects its own external processors and contracts.

Limitations

subprocessor_list: Is a dated sub-processor list published? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.
subprocessor_countries: Which countries do sub-processors operate in? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.
change_notification: Are customers notified of sub-processor changes? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.
parent_jurisdiction: ClickHouse, Inc. announced the LibreChat acquisition on 2025-11-04 from San Francisco and brought founder/team into ClickHouse. A self-hosted customer contracting entity/governing jurisdiction was not established from that announcement.
transfer_mechanism: Which transfer mechanism applies to non-EU/CH processing? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.
government_access_policy: Is there a published government-access or transparency policy? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.

subprocessor_list Is a dated sub-processor list published? [unknown]: subprocessor_list: Is a dated sub-processor list published? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.
subprocessor_countries Which countries do sub-processors operate in? [unknown]: subprocessor_countries: Which countries do sub-processors operate in? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.
change_notification Are customers notified of sub-processor changes? [unknown]: change_notification: Are customers notified of sub-processor changes? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.
parent_jurisdiction Which jurisdiction governs the vendor and its parent? [partial]: ClickHouse, Inc. announced the LibreChat acquisition on 2025-11-04 from San Francisco and brought founder/team into ClickHouse. A self-hosted customer contracting entity/governing jurisdiction was not established from that announcement. Sources: librechat:librechat:owner.
transfer_mechanism Which transfer mechanism applies to non-EU/CH processing? [unknown]: transfer_mechanism: Which transfer mechanism applies to non-EU/CH processing? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.
government_access_policy Is there a published government-access or transparency policy? [unknown]: government_access_policy: Is there a published government-access or transparency policy? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:owner.

Perplexity Enterprise

Agent cross-checked Support: partial

The DPA defines subprocessors and change notices; full current country inventory remains a gap.

Limitations

Remaining atomic gaps: subprocessor_countries.

subprocessor_list Is a dated sub-processor list published? [partial]: DPA links the Trust Center list; full current dated rows were not extractable. Sources: perplexity:perplexity:p-dpa-gb.
subprocessor_countries Which countries do sub-processors operate in? [unknown]: Unknown for subprocessor_countries. The DPA links the Trust Center subprocessor list, whose full current dated contents were not extractable. Parent structure and each subprocessor country remain unverified.
change_notification Are customers notified of sub-processor changes? [supported]: Nonmodel subprocessors have ten business days' prior notice via list/in-product/email; email requires subscription, objections within five business days. Model changes get notice/list update; remedy is stop using that model. Sources: perplexity:perplexity:p-dpa-gb.
parent_jurisdiction Which jurisdiction governs the vendor and its parent? [partial]: Counterparty is Perplexity AI, Inc.; contract law is California. Ultimate parent and incorporation jurisdiction were not sourced. Sources: perplexity:perplexity:p-terms-gb.
transfer_mechanism Which transfer mechanism applies to non-EU/CH processing? [partial]: DPA incorporates EU SCC modules 2/3 and UK addendum, with Irish SCC law/courts and Irish DPC. Swiss-specific adaptations were not retrieved. Sources: perplexity:perplexity:p-dpa-gb.
government_access_policy Is there a published government-access or transparency policy? [partial]: DPA requires notice of binding law-enforcement requests where legally permitted. Transparency statistics and a broader challenge policy were not retrieved. Sources: perplexity:perplexity:p-dpa-gb.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-dpa-gb, perplexity:perplexity:p-terms-gb.

DATA-06 Contracts and regulatory coverage

Judgment rule: Record DPA availability and form (click-through, negotiable), reference to Swiss revDSG and GDPR, governing law and court, EU AI Act documentation (provider or deployer role, transparency materials), and sector-specific materials (FINMA outsourcing, banking secrecy, public sector). No compliance verdict.

LibreChat

No public information found Support: not-published

We found no public information on this. A missing finding is not evidence that the product lacks the capability.

Perplexity Enterprise

Agent cross-checked Support: partial

A public DPA and California Enterprise terms exist; DACH-specific regulatory packages are unknown.

Limitations

Remaining atomic gaps: ai_act_materials.

dpa Is a DPA available, and is it negotiable? [partial]: Public English DPA updated August 13, 2026, incorporated into Enterprise terms. Negotiability unknown. Sources: perplexity:perplexity:p-dpa-gb, perplexity:perplexity:p-terms-gb.
revdsg_gdpr Does the DPA cover revDSG and GDPR? [partial]: DPA expressly covers GDPR, UK privacy, SCCs and generic applicable privacy laws. Explicit revised Swiss DSG adaptation was not located. Sources: perplexity:perplexity:p-dpa-gb.
governing_law Which law and court govern the contract? [supported]: Enterprise agreement 11.1 chooses California law and San Francisco County state/federal courts. EU SCCs separately choose Irish law/courts. Sources: perplexity:perplexity:p-terms-gb, perplexity:perplexity:p-dpa-gb.
ai_act_materials Is EU AI Act documentation provided? [unknown]: Unknown for ai_act_materials. Current English Enterprise terms and DPA were retrieved. Negotiation terms, explicit revDSG addendum, EU AI Act package and FINMA sector materials were not retrieved.
sector_materials Are FINMA or other sector materials provided? [partial]: Security material describes HIPAA alignment. Full BAA/regulatory scope and FINMA material were not retrieved; alignment does not establish blanket healthcare suitability. Sources: perplexity:perplexity:p-security.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-dpa-gb, perplexity:perplexity:p-terms-gb, perplexity:perplexity:p-security.

DATA-07 Certifications and attestations

Judgment rule: Record each certificate or report separately: ISO 27001, 27017, 27018, 27701, 42001; SOC 2 Type I/II with period; BSI C5; TISAX; national schemes. Record issuer, scope (which product and entity), validity and access route. A cloud provider's certificate does not certify the product.

LibreChat

No public information found Support: not-published

We found no public information on this. A missing finding is not evidence that the product lacks the capability.

Perplexity Enterprise

Agent cross-checked Support: partial

SOC 2 Type II and independent testing are vendor claims, not inspected attestations.

Availability: unknown · Delivery: native
Scope: surfaces=Enterprise Ask, Projects and Search web client; version=not specified; plan=Enterprise Pro/Max; sales-assisted roles or connector RBAC only where stated; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

Remaining atomic gaps: iso_27001, c5, other_certifications.

iso_27001 ISO 27001 with scope and validity? [unknown]: Unknown for iso_27001. Public security material claims SOC 2 Type II. Auditor, coverage dates, full reports, ISO scope/validity, BSI C5 and independent penetration-test results were not retrieved.
soc2 SOC 2 type, period and covered service? [partial]: Vendor claims SOC 2 Type II. Auditor, report period, covered systems, exceptions and current validity were not inspected. Sources: perplexity:perplexity:p-security.
c5 BSI C5 attestation? [unknown]: Unknown for c5. Public security material claims SOC 2 Type II. Auditor, coverage dates, full reports, ISO scope/validity, BSI C5 and independent penetration-test results were not retrieved.
other_certifications Which other certificates (27701, 42001, TISAX)? [unknown]: Unknown for other_certifications. Public security material claims SOC 2 Type II. Auditor, coverage dates, full reports, ISO scope/validity, BSI C5 and independent penetration-test results were not retrieved.
report_access How can customers obtain reports? [partial]: Security page directs documentation requests to Trust Center. Reports were not downloaded and access conditions remain unverified. Sources: perplexity:perplexity:p-security.
pentest Are independent penetration test summaries available? [partial]: Vendor states annual independent penetration testing. Scope, report date, findings and remediation were not retrieved. Sources: perplexity:perplexity:p-security.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-security.

DATA-08 Encryption and key control

Judgment rule: Record encryption at rest and in transit, customer-managed keys (BYOK/HYOK), key location, and private networking (private link, IP allow-lists, VPN).

LibreChat

Agent cross-checked Support: partial

Network and storage security depend on the customer’s deployment; application authentication does not certify encryption of all stored content.

Limitations

encryption_at_rest: Is data encrypted at rest? No default at-rest encryption guarantee covering MongoDB/files/PGVector or audited multi-tenant managed-service isolation was established from the installation guides.
customer_managed_keys: Operators own infrastructure and application secrets; a documented product HYOK/customer-managed content-encryption service was not verified.
tenant_isolation: How are customers separated in shared SaaS? No default at-rest encryption guarantee covering MongoDB/files/PGVector or audited multi-tenant managed-service isolation was established from the installation guides.

encryption_at_rest Is data encrypted at rest? [unknown]: encryption_at_rest: Is data encrypted at rest? No default at-rest encryption guarantee covering MongoDB/files/PGVector or audited multi-tenant managed-service isolation was established from the installation guides.
customer_managed_keys Can the customer manage or hold the keys? [partial]: Operators own infrastructure and application secrets; a documented product HYOK/customer-managed content-encryption service was not verified. Sources: librechat:librechat:auth, librechat:librechat:compose-pin.
private_networking Is private connectivity or IP restriction available? [supported]: Operators deploy the stack on their own network and configure reverse proxies/HTTPS for remote access. Sources: librechat:librechat:remote, librechat:librechat:local.
tenant_isolation How are customers separated in shared SaaS? [unknown]: tenant_isolation: How are customers separated in shared SaaS? No default at-rest encryption guarantee covering MongoDB/files/PGVector or audited multi-tenant managed-service isolation was established from the installation guides.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:auth, librechat:librechat:compose-pin, librechat:librechat:remote, librechat:librechat:local.

Perplexity Enterprise

Agent cross-checked Support: partial

Encrypted connector credentials and isolated task environments are documented; customer keys are a gap.

Availability: unknown · Delivery: native
Scope: surfaces=Enterprise Ask, Projects and Search web client, Enterprise Computer cloud tasks and scheduled automation; version=not specified; plan=Enterprise Pro/Max; sales-assisted roles or connector RBAC only where stated; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

Remaining atomic gaps: customer_managed_keys.
Capabilities apply only to the surface named in each atomic answer. Computer, Office/Teams and Portable do not establish feature parity in Ask/Search.

encryption_at_rest Is data encrypted at rest? [partial]: FAQ says connector credentials are encrypted at rest/in transit. Full chat/file cipher and key matrix were not retrieved. Sources: perplexity:perplexity:p-connectfaq, perplexity:perplexity:p-security.
customer_managed_keys Can the customer manage or hold the keys? [unknown]: Unknown for customer_managed_keys. The FAQ describes encrypted connector credentials and the security page describes access control. Customer-managed keys, SaaS private networking and detailed tenant-key isolation were not retrieved.
private_networking Is private connectivity or IP restriction available? [partial]: MCP can use Cloudflare Access credentials for protected tools. This does not establish private connectivity or IP restrictions for the whole Enterprise app. Sources: perplexity:perplexity:p-mcp.
tenant_isolation How are customers separated in shared SaaS? [partial]: Computer isolates each task's cloud filesystem/browser/sandbox from other users and organisation networks. SaaS database/key isolation remains unverified. Sources: perplexity:perplexity:p-computer.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-connectfaq, perplexity:perplexity:p-security, perplexity:perplexity:p-mcp, perplexity:perplexity:p-computer.

DATA-09 Professional secrecy

Judgment rule: For professional secrecy holders (Berufsgeheimnisträger: lawyers, doctors, auditors, tax advisers) under § 203 StGB (DE) and Art. 321 StGB (CH), record whether the vendor signs a contractual secrecy undertaking or a § 203 agreement that binds its staff and its sub-processors; whether this comes as a dedicated offering or a paid add-on, and on which plan; who can access content in plain text (vendor staff, sub-processors, model providers); and the documentation provided. A DPA or a no-training clause alone is not a secrecy undertaking. Banking secrecy and FINMA outsourcing belong to DATA-06, not here. Record contract facts, not a legal assessment.

LibreChat

Agent cross-checked Support: partial

Customer-operated message storage and configurable local/external inference establish part of the content-access boundary. A LibreChat-scoped staff/sub-processor secrecy undertaking or professional-secrecy offering remains unverified.

Availability: unknown · Delivery: unknown
Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; message schema and reference Compose pinned to v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional commercial secrecy terms unverified. Public Demo and website policies checked only to distinguish their scope; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected application, storage and model-service locations; no DE/CH professional-secrecy contract variant verified; os=not specified.

Limitations

The secrecy undertaking, sub-processor coverage, offering and professional-secrecy-specific documentation remain unknown.
content_access: Operator permissions, vendor/support grants, optional service access and provider staff access were not tested or contractually verified.
Technical data controls, a DPA, privacy wording and no-training statements do not establish the requested contractual undertaking. No legal compliance assessment is made.

secrecy_undertaking Does the vendor sign a secrecy undertaking or § 203 StGB / Art. 321 StGB agreement covering its own staff? [unknown]: No LibreChat-scoped § 203 StGB / Art. 321 StGB undertaking binding vendor staff was obtained from the reviewed project documentation and public legal pages. The website privacy policy expressly excludes the self-hosted application; ClickHouse ownership does not establish a product-specific agreement. Sources: librechat:librechat:siteprivacy, librechat:librechat:owner.
subprocessor_coverage Does the undertaking extend to its sub-processors, and is that documented? [unknown]: No self-hosted LibreChat professional-secrecy annex or documented extension to sub-processors was obtained. The separate Demo policy describes processor instruction/security obligations, which do not establish the undertaking requested here or coverage of a customer deployment. Sources: librechat:librechat:secrecy-demo-policy.
secrecy_offering Is it a dedicated offering or add-on, and on which plan? [unknown]: No dedicated professional-secrecy edition, paid add-on, eligible plan or price was established in the public project/legal materials and targeted searches. The public Demo is evaluation-only and excludes confidential or regulated data; it is a separate surface. Sources: librechat:librechat:demo.
content_access Who can access content in plain text: vendor staff, sub-processors, model providers? [partial]: The pinned reference deployment mounts customer-controlled MongoDB, uploads and logs; the message schema declares ordinary text/content fields. This places host/database operators inside the application trust boundary (an architectural inference, not a permissions audit). The first-chat and endpoint guides route prompts to a selected local or external model with customer credentials. Vendor/support access, optional service operators and provider human access remain deployment- and contract-specific and unverified. Sources: librechat:librechat:compose-pin, librechat:librechat:secrecy-message-pin, librechat:librechat:firstchat, librechat:librechat:custom.
secrecy_documentation Is the offering publicly documented (contract template, data-flow description, professional-body guidance)? [unknown]: Public installation, endpoint and privacy documents describe technical data paths and distinguish website, Demo and self-hosted software. No LibreChat-specific DE/CH secrecy contract template, covered-party annex or professional-body guidance was located in the reviewed sources. Sources: librechat:librechat:firstchat, librechat:librechat:siteprivacy.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:siteprivacy, librechat:librechat:owner, librechat:librechat:secrecy-demo-policy, librechat:librechat:demo, librechat:librechat:compose-pin, librechat:librechat:secrecy-message-pin, librechat:librechat:firstchat, librechat:librechat:custom.

Perplexity Enterprise

Agent cross-checked Support: partial

Profession-specific secrecy undertaking and add-on remain unknown; general confidentiality and scoped content-access controls do not establish §203 StGB or Art.321 StGB coverage.

Availability: unknown · Delivery: unknown
Scope: surfaces=Enterprise Ask, Projects and Search web client, Enterprise Computer cloud tasks and scheduled automation; version=not specified; plan=Enterprise Pro/Max; cloud Enterprise, with optional customer audit export; add_ons=none stated; deployment_mode=multi-tenant-saas; region=No profession-specific DE/CH contractual scope verified; deployment/provider regions follow the other scoped claims.; os=not specified.

Limitations

Contract facts only; no legal suitability assessment. No profession-specific commitment or paid option inferred from generic confidentiality, hosting, encryption or no-training terms.
Public, unauthenticated source pass only; no sales contact, NDA request or authenticated access-control test.

secrecy_undertaking Does the vendor sign a secrecy undertaking or § 203 StGB / Art. 321 StGB agreement covering its own staff? [unknown]: Unknown. Reviewed current English Enterprise terms, August13 DPA, Security Hub, security page and targeted first-party professional-secrecy searches. No §203 StGB or Art.321 StGB contract template or dedicated secrecy SKU was retrieved. No NDA or sales request was made. A DPA or no-training clause alone does not answer whether a profession-specific undertaking is signed.
subprocessor_coverage Does the undertaking extend to its sub-processors, and is that documented? [unknown]: Unknown. No retrieved §203/Art.321 undertaking establishes flow-down to all relevant subcontractors/model providers. General DPA confidentiality is not equivalent.
secrecy_offering Is it a dedicated offering or add-on, and on which plan? [unknown]: Unknown. No documented profession-specific plan, dedicated instance option or paid secrecy add-on and its entitlements/pricing were established.
content_access Who can access content in plain text: vendor staff, sub-processors, model providers? [partial]: Security material describes just-in-time vendor production access; DPA4.d requires confidentiality for people processing personal data. Eligible Enterprise audit exports include full queries/answers to customer endpoints. Per-provider plaintext access/retention and any profession-specific staff/subprocessor restrictions remain unverified. Sources: perplexity:perplexity:p-dpa-gb, perplexity:perplexity:p-security, perplexity:perplexity:p-audit.
secrecy_documentation Is the offering publicly documented (contract template, data-flow description, professional-body guidance)? [unknown]: Unknown. Reviewed current English Enterprise terms, August13 DPA, Security Hub, security page and targeted first-party professional-secrecy searches. No §203 StGB or Art.321 StGB contract template or dedicated secrecy SKU was retrieved. No NDA or sales request was made. General data-flow/security pages are available but do not document such a secrecy offering.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-dpa-gb, perplexity:perplexity:p-security, perplexity:perplexity:p-audit.

Commercials and vendor

VEN-01 Pricing model and list prices

Judgment rule: Record pricing unit (per seat, per active user, usage-based, platform fee, hybrid), list prices per plan in original currency with date, included usage and credits, add-on prices (connectors, agents, image generation) and overage rates. Cite public prices or dated quotes. Per-seat versus usage is a fact, not a quality judgment.

LibreChat

Agent cross-checked Support: partial

MIT software has no licence subscription; hosting, inference and optional runtime services are separately procured.

Limitations

add_ons: Optional external code/OCR/search/image services need separately configured endpoints and credentials. Their rates depend on the operator’s contracts.
overage: Provider APIs charge their account holder; internal credit balances are governance configuration rather than a single LibreChat usage tariff.

pricing_unit What is the pricing unit? [supported]: The pinned MIT permission grant has no per-user fee; self-hosting and model accounts are customer responsibilities. Sources: librechat:librechat:license, librechat:librechat:firstchat.
list_prices What are list prices per plan, with date and currency? [supported]: The repository’s MIT licence permits use without a software fee as retrieved 2026-10-21; there is no bundled inference subscription in this scope. Sources: librechat:librechat:license, librechat:librechat:firstchat.
included_usage What usage is included? [supported]: LibreChat ships with no model API key and no included provider token balance. Sources: librechat:librechat:firstchat.
add_ons Which features cost extra? [partial]: Optional external code/OCR/search/image services need separately configured endpoints and credentials. Their rates depend on the operator’s contracts. Sources: librechat:librechat:code, librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:images.
overage What do usage beyond limits and premium models cost? [partial]: Provider APIs charge their account holder; internal credit balances are governance configuration rather than a single LibreChat usage tariff. Sources: librechat:librechat:balance, librechat:librechat:tokens, librechat:librechat:firstchat.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:firstchat, librechat:librechat:code, librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:images, librechat:librechat:balance, librechat:librechat:tokens.

Perplexity Enterprise

Agent cross-checked Support: partial

Enterprise seats have public USD prices; Computer extras use credits with unpriced conversion.

Limitations

The partial atomic answers state their documentation or verification limits.

pricing_unit What is the pricing unit? [supported]: Per-seat monthly/annual subscription plus Computer credits and optional pool; API billed separately. Sources: perplexity:perplexity:p-billing, perplexity:perplexity:p-credits.
list_prices What are list prices per plan, with date and currency? [supported]: Retrieved October 21, 2026: Enterprise Pro USD40/seat/month or USD400/year; Max USD325/month or USD3,250/year, excl tax. Potential 250+ discounts not assumed. Sources: perplexity:perplexity:p-billing, perplexity:perplexity:p-terms-gb.
included_usage What usage is included? [supported]: Computer includes 500 credits/Pro seat/month or 15,000/Max, expiring each cycle. Ask/standard Search do not use these credits; session/file limits still apply. Sources: perplexity:perplexity:p-credits, perplexity:perplexity:p-entpro, perplexity:perplexity:p-filelimits.
add_ons Which features cost extra? [partial]: Admins purchase pooled credits/auto-refill after billing consent; API credits separate. Advanced roles/connector RBAC depend on managed contracts; separate prices unknown. Sources: perplexity:perplexity:p-credits, perplexity:perplexity:p-billing, perplexity:perplexity:p-roles.
overage What do usage beyond limits and premium models cost? [partial]: After individual credits, use draws purchased pool within the applicable cap. Dollar-per-credit/task tariff was not established; currency overage remains unknown. Sources: perplexity:perplexity:p-credits.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-billing, perplexity:perplexity:p-credits, perplexity:perplexity:p-terms-gb, perplexity:perplexity:p-entpro, perplexity:perplexity:p-filelimits, perplexity:perplexity:p-roles.

VEN-02 Scenario cost

Judgment rule: Price three workloads for 12 months: 200, 1,000 and 5,000 users with a disclosed light/regular/power usage mix, in CHF and EUR excluding VAT. Include licences, platform fees, add-ons, model usage and, for self-hosted options, a stated operating assumption. Separate fixed, variable, included and unknown costs. No invented discounts.

LibreChat

Agent cross-checked Support: partial

ALM-14 shared cost assumptions v1.4, 2026-10-21: zero standard licence plus a disclosed Swiss infrastructure/operations and direct-BYO-model budget. Annual CHF/EUR figures are floors plus named unknown costs.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Analyst-selected direct OpenAI API proxy, not a bundled model, Assumed operations staffing; optional commercial services excluded; deployment_mode=customer-cloud; region=Azure Switzerland North for the reference application infrastructure; standard OpenAI API inference has no Swiss/EU residency assumption; os=not specified.

Limitations

ALM-14 shared cost assumptions v1.4, 2026-10-21 are analyst inputs, not vendor sizing or an uptime promise.
The budget is a floor because named infrastructure and service costs are unpriced.

cost_200 Year-one cost at 200 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21. 200 users, 12 months excluding VAT: from CHF 34778.28 / EUR 37651.06 plus unpriced items. Includes zero standard-software licence, reference infrastructure EUR 4749.26, operations CHF 30000.00, and BYO model usage USD 475.20. This is an assumption-based budget floor, not a vendor quote or validated capacity plan. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort.
cost_1000 Year-one cost at 1,000 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21. 1,000 users, 12 months excluding VAT: from CHF 88600.40 / EUR 95919.02 plus unpriced items. Includes zero standard-software licence, reference infrastructure EUR 12605.23, operations CHF 75000.00, and BYO model usage USD 2376.00. This is an assumption-based budget floor, not a vendor quote or validated capacity plan. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort.
cost_5000 Year-one cost at 5,000 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21. 5,000 users, 12 months excluding VAT: from CHF 189541.24 / EUR 205197.83 plus unpriced items. Includes zero standard-software licence, reference infrastructure EUR 32214.49, operations CHF 150000.00, and BYO model usage USD 11880.00. This is an assumption-based budget floor, not a vendor quote or validated capacity plan. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort.
variable_share Which part depends on usage? [partial]: Shared mix is 60% light at 100, 30% regular at 400 and 10% power at 1,500 messages/user/month, or 330 weighted messages. Each message is 3,000 input and 600 output tokens. Direct BYO proxy is gpt-6-luna, reasoning effort none, Standard short-context uncached rates USD 0.10/0.50 per million input/output tokens. It costs USD 2.376/user/year before optional tools, embedding, caching or regional processing. This proxy is an analyst assumption, not the product default. Sources: librechat:librechat:cost-model, librechat:librechat:cost-effort.
unknown_parts Which costs could not be priced? [partial]: Unpriced additions are file/object storage beyond the assumed 500 GB PostgreSQL storage, VM OS/data disks, backup excess, egress/load balancers, Redis or additional database services, high availability, embeddings, OCR, search, audio/images, integration work and optional commercial services. MongoDB remains the primary store, so its infrastructure, file storage and other required dependencies are additional unpriced items; PostgreSQL is only the shared RAG/reference compute assumption. The shared VM/PG sizes have not been load-tested and do not replace each product’s documented runtime dependencies. Sources: librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:license.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort.

Perplexity Enterprise

Agent cross-checked Support: partial

Annual Pro-seat floors are calculable; total shared-scenario cost remains a floor plus unknown extras.

Availability: generally-available · Delivery: native
Scope: surfaces=Enterprise Ask, Projects and Search web client, Enterprise Computer cloud tasks and scheduled automation; version=not specified; plan=All seats Enterprise Pro at USD400/year; optional Max and managed features excluded from baseline; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

The partial atomic answers state their documentation or verification limits.

cost_200 Year-one cost at 200 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21. Twelve months, excl VAT, no discounts; mix averages 330 messages/user/month. All 200 seats Enterprise Pro at USD400/year: USD80,000.00 = EUR71,333.04 = CHF65,890.33, using ECB 2026-10-20 EUR1=USD1.1215=CHF0.9237. Total is this floor plus unknown Computer extras, managed-plan features, support and implementation. Sources: perplexity:perplexity:p-billing, perplexity:perplexity:p-credits, perplexity:perplexity:p-entpro, perplexity:perplexity:fx-ecb.
cost_1000 Year-one cost at 1,000 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21. Twelve months, excl VAT, no discounts; mix averages 330 messages/user/month. All 1,000 seats Enterprise Pro at USD400/year: USD400,000.00 = EUR356,665.18 = CHF329,451.63, using ECB 2026-10-20 EUR1=USD1.1215=CHF0.9237. Total is this floor plus unknown Computer extras, managed-plan features, support and implementation. Sources: perplexity:perplexity:p-billing, perplexity:perplexity:p-credits, perplexity:perplexity:p-entpro, perplexity:perplexity:fx-ecb.
cost_5000 Year-one cost at 5,000 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21. Twelve months, excl VAT, no discounts; mix averages 330 messages/user/month. All 5,000 seats Enterprise Pro at USD400/year: USD2,000,000.00 = EUR1,783,325.90 = CHF1,647,258.14, using ECB 2026-10-20 EUR1=USD1.1215=CHF0.9237. Total is this floor plus unknown Computer extras, managed-plan features, support and implementation. Sources: perplexity:perplexity:p-billing, perplexity:perplexity:p-credits, perplexity:perplexity:p-entpro, perplexity:perplexity:fx-ecb.
variable_share Which part depends on usage? [partial]: Ask/standard Search are outside Computer credits; 330 messages do not have a fixed Computer-credit conversion. Task cost and currency tariff remain unknown; no model/token proxy is used for proprietary credits. Sources: perplexity:perplexity:p-entpro, perplexity:perplexity:p-credits.
unknown_parts Which costs could not be priced? [partial]: Unknown credit tariff/task consumption, managed entitlements, optional Max mix, premium data contracts, local hardware, implementation and support. No invented discounts or complete total. Sources: perplexity:perplexity:p-billing, perplexity:perplexity:p-credits, perplexity:perplexity:p-roles.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-billing, perplexity:perplexity:p-credits, perplexity:perplexity:p-entpro, perplexity:perplexity:fx-ecb, perplexity:perplexity:p-roles.

VEN-03 Evaluation access

Judgment rule: Distinguish free tier, self-serve trial, sales-led pilot, paid proof of concept and open-source self-install. Record card requirement, duration, seat limit, and which features (SSO, connectors, admin) the trial includes. Map which shared scenarios can be run without sales approval.

LibreChat

Agent cross-checked Support: supported

Customers can self-install without licence payment; the public demo is an evaluation-only alternative.

free_tier Is there a free tier for business use? [supported]: MIT self-installation permits organizational use without a software licence fee. Sources: librechat:librechat:license.
self_serve_trial Is a self-serve business trial available? [supported]: Self-installation has no trial clock or software card requirement; the free hosted Demo can be tried separately under its terms. Sources: librechat:librechat:local, librechat:librechat:demo.
trial_scope Do trials include SSO, connectors and admin features? [supported]: Self-installed instances can configure SSO, Agents, file retrieval and administration with their own service accounts. It is not evidence that every experimental add-on is enabled by default. Sources: librechat:librechat:auth, librechat:librechat:agents, librechat:librechat:rag.
sales_gate Does meaningful evaluation require sales contact? [supported]: The documented Docker install does not require sales approval; optional third-party services have separate account requirements. Sources: librechat:librechat:local, librechat:librechat:firstchat.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:local, librechat:librechat:demo, librechat:librechat:auth, librechat:librechat:agents, librechat:librechat:rag, librechat:librechat:firstchat.

Perplexity Enterprise

Agent cross-checked Support: partial

Enterprise self-serve subscriptions are available, but the vendor explicitly offers no self-serve trial.

Limitations

The partial atomic answers state their documentation or verification limits.

free_tier Is there a free tier for business use? [partial]: Individual Free access exists; Enterprise is paid. Free business governance entitlements were not established. Sources: perplexity:perplexity:p-models, perplexity:perplexity:p-sso.
self_serve_trial Is a self-serve business trial available? [unsupported]: FAQ expressly says no self-serve Enterprise Pro/Max trials. Assisted evaluation may be offered through sales; no contact made. Sources: perplexity:perplexity:p-billing.
trial_scope Do trials include SSO, connectors and admin features? [partial]: No self-serve trial. Assisted evaluation SSO, connector and admin entitlements remain unknown; individual Free cannot verify them. Sources: perplexity:perplexity:p-billing.
sales_gate Does meaningful evaluation require sales contact? [partial]: Paid self-serve purchase exists. Free Enterprise evaluation needs assistance per FAQ; advanced managed roles are sales-assisted. Sources: perplexity:perplexity:p-billing, perplexity:perplexity:p-roles.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-models, perplexity:perplexity:p-sso, perplexity:perplexity:p-billing, perplexity:perplexity:p-roles.

VEN-04 Contract terms and pricing transparency

Judgment rule: Record minimum seats or commitment, contract length, monthly versus annual billing, price-change rules, cancellation and downgrade terms, and invoicing in CHF/EUR. Classify pricing as transparent, partially specified, quote-only or unknown, naming the missing fields. Quote-only pricing is a disclosed constraint.

LibreChat

Agent cross-checked Support: partial

The MIT licence has no seat or contract-term subscription; optional service contracts are outside that licence.

Limitations

cancellation: An operator can stop running the application; this does not cancel its separately purchased cloud/model services or establish deletion of all copies.
local_invoicing: Can it be invoiced in CHF or EUR from a European entity? CHF/EUR commercial invoicing from a European entity was not established for optional project services.
transparency_class: Source licensing is transparent; a complete all-in hosted/support/inference tariff is not included in this self-hosted offer.

minimum_commitment What seat or spend minimum applies? [supported]: The MIT permission grant has no user-count or spending minimum for software use. Sources: librechat:librechat:license.
contract_length What contract lengths are offered? [supported]: There is no monthly/annual licence subscription in the MIT permission grant. External hosting/API contracts are separate. Sources: librechat:librechat:license.
cancellation How can the contract be cancelled or reduced? [partial]: An operator can stop running the application; this does not cancel its separately purchased cloud/model services or establish deletion of all copies. Sources: librechat:librechat:license, librechat:librechat:local.
local_invoicing Can it be invoiced in CHF or EUR from a European entity? [unknown]: local_invoicing: Can it be invoiced in CHF or EUR from a European entity? CHF/EUR commercial invoicing from a European entity was not established for optional project services.
transparency_class Is pricing transparent, partial, quote-only or unknown? [partial]: Source licensing is transparent; a complete all-in hosted/support/inference tariff is not included in this self-hosted offer. Sources: librechat:librechat:license, librechat:librechat:firstchat.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:local, librechat:librechat:firstchat.

Perplexity Enterprise

Agent cross-checked Support: partial

Public USD monthly/annual plans coexist with managed contract pricing.

Limitations

The partial atomic answers state their documentation or verification limits.

minimum_commitment What seat or spend minimum applies? [partial]: Terms refer minimum seats to ordering documentation/account; no numeric minimum retrieved. The 50-seat feature qualifier is not a subscription minimum. Sources: perplexity:perplexity:p-terms-gb, perplexity:perplexity:p-billing.
contract_length What contract lengths are offered? [supported]: Monthly and annual billing; annual Pro USD400 and Max USD3,250 per seat. Sources: perplexity:perplexity:p-billing.
cancellation How can the contract be cancelled or reduced? [supported]: Removing users does not reduce billing. Admin reduces paid seats in Billing for next month/annual renewal without current-term refund; seat increases prorated immediately. Sources: perplexity:perplexity:p-billing, perplexity:perplexity:p-terms-gb.
local_invoicing Can it be invoiced in CHF or EUR from a European entity? [partial]: Invoices/wire available. Terms specify USD and Perplexity AI, Inc.; European-entity EUR/CHF invoicing was not established. Sources: perplexity:perplexity:p-billing, perplexity:perplexity:p-terms-gb.
transparency_class Is pricing transparent, partial, quote-only or unknown? [supported]: Partial. Seat prices and quotas public; advanced managed entitlements, Computer variable cost and premium partner costs unpriced here. Sources: perplexity:perplexity:p-billing, perplexity:perplexity:p-credits, perplexity:perplexity:p-roles.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-terms-gb, perplexity:perplexity:p-billing, perplexity:perplexity:p-credits, perplexity:perplexity:p-roles.

VEN-05 Source licence

Judgment rule: Record licence per component (client, server, connectors, hosted extensions) and revision. Distinguish OSI open source, source-available with restrictions (branding clauses, user caps), and closed. Repository visibility is not a licence classification. Licences change between releases: record the current terms, and never carry a fork's historical licence over to the upstream product or the reverse.

LibreChat

Agent cross-checked Support: partial

The pinned main repository is MIT licensed; no user-count or product-branding clause appears in that licence.

Limitations

enterprise_features_closed: The project documents a separate preview admin panel and optional code services. A closed enterprise-edition boundary for the main repository was not established.

licence_type Which licence applies to each component? [supported]: The main client/server repository at v0.8.8 is MIT. Separate Code Interpreter, admin-panel, connector or hosted-service components need their own licence review. Sources: librechat:librechat:license.
branding_restrictions Do licence terms restrict branding or user counts? [supported]: The MIT grant permits use/modification/distribution subject to retaining its copyright and permission notice; it includes no 50-user cap or mandatory UI branding clause. Sources: librechat:librechat:license.
enterprise_features_closed Are enterprise features in a separate closed edition? [partial]: The project documents a separate preview admin panel and optional code services. A closed enterprise-edition boundary for the main repository was not established. Sources: librechat:librechat:admin, librechat:librechat:code, librechat:librechat:license.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:admin, librechat:librechat:code.

Perplexity Enterprise

Agent cross-checked Support: partial

The Enterprise service is proprietary with a business-use subscription licence.

Limitations

The partial atomic answers state their documentation or verification limits.

licence_type Which licence applies to each component? [partial]: Nonexclusive, nontransferable, nonsublicensable business-use service licence; Perplexity/licensors retain IP. Complete component/model licence inventory not retrieved. Sources: perplexity:perplexity:p-terms-gb.
branding_restrictions Do licence terms restrict branding or user counts? [partial]: Named accounts limited to purchased seats; sharing accounts forbidden. White-label rights were not established. Sources: perplexity:perplexity:p-terms-gb.
enterprise_features_closed Are enterprise features in a separate closed edition? [partial]: Hosted Enterprise administration falls under the proprietary service agreement. This does not establish that every component is closed. Sources: perplexity:perplexity:p-terms-gb.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-terms-gb.

VEN-06 Data export and exit

Judgment rule: Record admin export of chats, assistants, knowledge bases, prompts and audit logs, formats, export completeness, user self-export, and what survives contract end. Run an admin export on a trial. Exported chats alone do not make assistants and knowledge portable.

LibreChat

Agent cross-checked Support: partial

Users can export conversations in machine-readable formats; organization-wide Agent/knowledge exit completeness remains unverified.

Limitations

chat_export: Pinned client code exports a user-selected conversation, including optional branches/options. A documented admin bulk export of every user’s chats was not established.
assistant_export: Beta management APIs expose Agent/Skill objects, but a reusable complete assistant/prompt export fixture was not verified.
knowledge_export: Can knowledge bases and their sources be exported? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned.
post_termination_window: How long can data be retrieved after termination? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned.

chat_export Can admins export all chats? [partial]: Pinned client code exports a user-selected conversation, including optional branches/options. A documented admin bulk export of every user’s chats was not established. Sources: librechat:librechat:export-pin.
assistant_export Can assistants and prompts be exported in a reusable format? [partial]: Beta management APIs expose Agent/Skill objects, but a reusable complete assistant/prompt export fixture was not verified. Sources: librechat:librechat:api.
knowledge_export Can knowledge bases and their sources be exported? [unknown]: knowledge_export: Can knowledge bases and their sources be exported? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned.
export_format Are formats documented and machine-readable? [supported]: Conversation export code supports JSON, CSV, Markdown and text. This establishes format availability, not complete organization-data portability. Sources: librechat:librechat:export-pin.
post_termination_window How long can data be retrieved after termination? [unknown]: post_termination_window: How long can data be retrieved after termination? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:export-pin, librechat:librechat:api.

Perplexity Enterprise

Agent cross-checked Support: partial

Audit events and files provide some exits, but complete tenant and assistant export is unverified.

Availability: generally-available · Delivery: native
Scope: surfaces=Enterprise Ask, Projects and Search web client, Enterprise Computer cloud tasks and scheduled automation; version=not specified; plan=Enterprise Pro/Max; sales-assisted roles or connector RBAC only where stated; add_ons=none stated; deployment_mode=multi-tenant-saas; region=Cloud region and residency option unverified; local device location customer-controlled; os=not specified.

Limitations

chat_export: Eligible audit webhooks stream queries/full answers prospectively. A retrospective complete tenant-chat export was not established.
assistant_export: Custom Skills accept SKILL.md/ZIP. Export of installed Skills, Project instructions and connections was not established.
knowledge_export: Download files is a current permission for downloadable user uploads, including session and Project files; connector files retain source permissions. This is not a bulk export of all indexed content, metadata or ACLs. The retired organization-repository ZIP procedure is only lifecycle evidence.
export_format: Audit JSON and DOCX/PDF/XLSX/PPTX/HTML assets are documented. A complete machine-readable tenant/knowledge-state export was not established.
post_termination_window: DPA gives 30-day personal-data delete/return deadline with legal exceptions. A customer retrieval UI or guaranteed window was not established.

chat_export Can admins export all chats? [partial]: Eligible audit webhooks stream queries/full answers prospectively. A retrospective complete tenant-chat export was not established. Sources: perplexity:perplexity:p-audit.
assistant_export Can assistants and prompts be exported in a reusable format? [partial]: Custom Skills accept SKILL.md/ZIP. Export of installed Skills, Project instructions and connections was not established. Sources: perplexity:perplexity:p-skills-20261026.
knowledge_export Can knowledge bases and their sources be exported? [partial]: Download files is a current permission for downloadable user uploads, including session and Project files; connector files retain source permissions. This is not a bulk export of all indexed content, metadata or ACLs. The retired organization-repository ZIP procedure is only lifecycle evidence. Sources: perplexity:perplexity:p-security-hub-20261026, perplexity:perplexity:p-roles-20261026.
export_format Are formats documented and machine-readable? [partial]: Audit JSON and DOCX/PDF/XLSX/PPTX/HTML assets are documented. A complete machine-readable tenant/knowledge-state export was not established. Sources: perplexity:perplexity:p-audit, perplexity:perplexity:p-assets.
post_termination_window How long can data be retrieved after termination? [partial]: DPA gives 30-day personal-data delete/return deadline with legal exceptions. A customer retrieval UI or guaranteed window was not established. Sources: perplexity:perplexity:p-dpa-gb-20261026.

Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-20. Sources: perplexity:perplexity:p-audit, perplexity:perplexity:p-skills-20261026, perplexity:perplexity:p-assets, perplexity:perplexity:p-dpa-gb-20261026, perplexity:perplexity:p-security-hub-20261026, perplexity:perplexity:p-roles-20261026.

VEN-07 Support and service levels

Judgment rule: Record support channels, languages (German, French, Italian), hours and time zone, local or regional presence, documented response times, uptime SLA and credits, public status page and incident history. Popularity is not a reliability score.

LibreChat

Agent cross-checked Support: partial

Public project/community channels are available; a binding business support SLA was not established.

Limitations

support_channels: Public GitHub issue reporting and community channels are documented; a supported enterprise channel/response-time matrix was not established for MIT self-hosting.
support_languages: Is support available in German, French or Italian? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass.
regional_presence: Is there a DACH or Swiss entity, team or partner? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass.
uptime_sla: Is there an uptime SLA with credits? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass.
status_page: Is there a public status page with history? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass.

support_channels Which support channels are available on each plan? [partial]: Public GitHub issue reporting and community channels are documented; a supported enterprise channel/response-time matrix was not established for MIT self-hosting. Sources: librechat:librechat:logging, librechat:librechat:firstchat.
support_languages Is support available in German, French or Italian? [unknown]: support_languages: Is support available in German, French or Italian? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass.
regional_presence Is there a DACH or Swiss entity, team or partner? [unknown]: regional_presence: Is there a DACH or Swiss entity, team or partner? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass.
uptime_sla Is there an uptime SLA with credits? [unknown]: uptime_sla: Is there an uptime SLA with credits? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass.
status_page Is there a public status page with history? [unknown]: status_page: Is there a public status page with history? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:logging, librechat:librechat:firstchat.

Perplexity Enterprise

Agent cross-checked Support: partial

Public help, support contact and status exist; contractual service levels remain unknown.

Limitations

Remaining atomic gaps: support_languages, regional_presence, uptime_sla.

support_channels Which support channels are available on each plan? [partial]: Help/contact support and Enterprise email; Portable guide mentions in-product live chat. Response times and languages remain unverified. Sources: perplexity:perplexity:p-terms-gb, perplexity:perplexity:p-local.
support_languages Is support available in German, French or Italian? [unknown]: Unknown for support_languages. Public help and status exist, but contracted uptime credits, support languages and a Swiss/DACH delivery entity were not retrieved.
regional_presence Is there a DACH or Swiss entity, team or partner? [unknown]: Unknown for regional_presence. Public help and status exist, but contracted uptime credits, support languages and a Swiss/DACH delivery entity were not retrieved.
uptime_sla Is there an uptime SLA with credits? [unknown]: Unknown for uptime_sla. Public help and status exist, but contracted uptime credits, support languages and a Swiss/DACH delivery entity were not retrieved.
status_page Is there a public status page with history? [partial]: Public status covers website, app, Computer and API with a calendar. History completeness and contracted SLA were not audited. Sources: perplexity:perplexity:p-status-web.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-terms-gb, perplexity:perplexity:p-local, perplexity:perplexity:p-status-web.

VEN-08 Onboarding, training and adoption

Judgment rule: Record vendor-led onboarding, admin training, end-user training (live, e-learning, languages), use-case libraries, champion programmes, change-management materials and their cost. Distinguish included services from paid professional services and partner offerings.

LibreChat

Agent cross-checked Support: partial

Self-hosting and Agent use have public setup guides; vendor-led training/adoption packages were not verified.

Limitations

onboarding_service: Is guided onboarding included? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site.
user_training: Is end-user training offered, in which languages? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site.
use_case_library: The Agent and setup guides include examples and tutorials; a role-based enterprise training/use-case program was not established.
adoption_programme: Is there a champion or adoption programme? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site.
service_cost: Which services cost extra? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site.

onboarding_service Is guided onboarding included? [unknown]: onboarding_service: Is guided onboarding included? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site.
user_training Is end-user training offered, in which languages? [unknown]: user_training: Is end-user training offered, in which languages? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site.
use_case_library Are role-based use cases and templates provided? [partial]: The Agent and setup guides include examples and tutorials; a role-based enterprise training/use-case program was not established. Sources: librechat:librechat:agents, librechat:librechat:firstchat.
adoption_programme Is there a champion or adoption programme? [unknown]: adoption_programme: Is there a champion or adoption programme? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site.
service_cost Which services cost extra? [unknown]: service_cost: Which services cost extra? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:firstchat.

Perplexity Enterprise

Agent cross-checked Support: partial

Vendor guides and business task examples exist; included adoption services remain unpriced.

Limitations

Remaining atomic gaps: onboarding_service, user_training, adoption_programme, service_cost.

onboarding_service Is guided onboarding included? [unknown]: Unknown for onboarding_service. Public examples and help guides exist. Included onboarding, language-specific user training, champion programmes and separately priced adoption services were not established.
user_training Is end-user training offered, in which languages? [unknown]: Unknown for user_training. Public examples and help guides exist. Included onboarding, language-specific user training, champion programmes and separately priced adoption services were not established.
use_case_library Are role-based use cases and templates provided? [supported]: Computer and Microsoft integration guides give research, analysis, document and email examples. Skills provide reusable task instructions. Sources: perplexity:perplexity:p-computer, perplexity:perplexity:p-office, perplexity:perplexity:p-skills.
adoption_programme Is there a champion or adoption programme? [unknown]: Unknown for adoption_programme. Public examples and help guides exist. Included onboarding, language-specific user training, champion programmes and separately priced adoption services were not established.
service_cost Which services cost extra? [unknown]: Unknown for service_cost. Public examples and help guides exist. Included onboarding, language-specific user training, champion programmes and separately priced adoption services were not established.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: perplexity:perplexity:p-computer, perplexity:perplexity:p-office, perplexity:perplexity:p-skills.

Sources

Custom endpoints librechat:librechat:custom
Operators configure compatible endpoints and customer-held keys, including local and hosted services.
Endpoint setup; API key; base URL; model list · documented · Source date not stated · Retrieved 2026-10-21
Azure OpenAI configuration librechat:librechat:azure
Azure OpenAI uses customer deployment groups, instance names and credentials.
Deployment groups; API credentials · documented · Source date not stated · Retrieved 2026-10-21
AWS Bedrock object structure librechat:librechat:bedrock
Bedrock routes use customer AWS configuration and region selection.
Region; credentials; model selection · documented · Source date not stated · Retrieved 2026-10-21
Anthropic Vertex AI configuration librechat:librechat:vertex
Claude can run through customer Google Vertex AI credentials and regions.
Project and region configuration · documented · Source date not stated · Retrieved 2026-10-21
Model specifications librechat:librechat:modelspec
Administrators can enforce configured model presets and defaults; available endpoints still depend on customer credentials.
enforce; preset; modelSelect; addedEndpoints · documented · Source date not stated · Retrieved 2026-10-21
Agents librechat:librechat:agents
Agents combine instructions, models, files, tools, skills and sharing permissions, with visible execution and configurable approval.
Builder; Capabilities; Version history; Sharing; Activity; tool approval · documented · Source date not stated · Retrieved 2026-10-21
OCR for documents librechat:librechat:ocr
OCR can augment text extraction, or files can be sent to compatible provider APIs; format and model limitations remain.
File Context; Upload as Text; Optional OCR; Limitations · documented · Source date not stated · Retrieved 2026-10-21
LibreChat v0.8.8 release librechat:librechat:releases
The stable release documents agent controls, current model updates and explicitly experimental schedules/workspaces and beta Agents API.
Highlights, 2026-10-01 · documented · Source date 2026-10-01 · Retrieved 2026-10-21
Advanced AI models included in subscriptions perplexity:perplexity:p-models
Lists current Enterprise Search models and user/automatic routing; availability depends on settings, rollout and region.
Enterprise table; modes and availability notes; snapshot October 17, 2026 · documented · Source date 2026-10-17 · Retrieved 2026-10-21
What is Portable Computer? perplexity:perplexity:p-local
Portable runs local models on supported NVIDIA hardware, including Enterprise plans; cloud escalation needs approval, memory remains cloud-only.
Requirements; local/cloud routing; controls and offline FAQ · documented · Source date 2026-09-15 · Retrieved 2026-10-21
File uploads perplexity:perplexity:p-files
Files, images and audio/video transcription are documented; long documents use selected parts. Generic size limits are not substituted for Enterprise.
Supported input and long-file processing · documented · Source date 2026-09-07 · Retrieved 2026-10-21
Enterprise file limits perplexity:perplexity:p-filelimits
Ask permits 30 files of 50 MB per upload; Computer 200 MB/file; Projects up to 10,000 files, 5 GB total and 100 MB/file. Organisation repository retirement is stated.
Ask, Computer, weekly sessions and Projects tables · documented · Source date 2026-10-08 · Retrieved 2026-10-21
Computer for Enterprise perplexity:perplexity:p-computer
Multi-step tasks use tools and generated files, inherited governance, per-task isolated cloud environment and per-step models.
Task orchestration, triggers, isolation and model settings · documented · Source date not stated · Retrieved 2026-10-21
Audit logs perplexity:perplexity:p-audit
50seats or oneMax can stream query/answer/admin/Computer events as JSON; Splunk HEC supported; Slack payloads truncate content.
Eligibility, event taxonomy, full query/answer payload and SIEM webhooks · documented · Source date not stated · Retrieved 2026-10-21
Perplexity changelog perplexity:perplexity:p-changelog
Dated product/model releases are public; these are arrival dates, not a three-release provider-lag dataset.
October 19, October 5, September 21 and August 2026 releases · documented · Source date not stated · Retrieved 2026-10-21
Your first chat librechat:librechat:firstchat
LibreChat ships without a model key; the public demo is for evaluation rather than private or durable data.
Software you host yourself; endpoint credentials; public demo · documented · Source date not stated · Retrieved 2026-10-21
Code Interpreter API librechat:librechat:code
A separate code execution service supports multiple languages and downloadable generated files; stateful/attached modes are experimental.
Setup; self-hosted service; workspace permissions; generated files · documented · Source date not stated · Retrieved 2026-10-21
LibreChat v0.8.8 MIT licence librechat:librechat:license
The pinned repository is MIT licensed with copyright/permission notice preservation and an as-is disclaimer.
LICENSE, permission grant and notice requirement · documented · Source date not stated · Retrieved 2026-10-21
RAG API configuration librechat:librechat:ragcfg
OpenAI, Hugging Face and Ollama embedding configurations are documented; image choice affects local embedding support.
Embedding providers; lite image; full image · documented · Source date not stated · Retrieved 2026-10-21
Granular access control librechat:librechat:access
Roles, groups and resource ACLs govern features and sharing, with Entra groups synchronized at sign-in.
Feature permissions; Resource ACLs; System grants; Groups · documented · Source date not stated · Retrieved 2026-10-21
LibreChat Admin Panel librechat:librechat:admin
A separate browser management panel is available for testing and uses the underlying LibreChat admin APIs.
Status Preview; separate service; admin APIs · documented · Source date not stated · Retrieved 2026-10-21
Balance configuration librechat:librechat:balance
Optional token-credit balances initialize and refill user credits; tracking is disabled by default.
enabled; startBalance; refill configuration · documented · Source date not stated · Retrieved 2026-10-21
Automated moderation librechat:librechat:mod
Moderation scores abusive login/registration/message activity and may ban users; it is not a documented content DLP classifier.
Violation scoring and limits · documented · Source date not stated · Retrieved 2026-10-21
LibreChat balance admission implementation librechat:librechat:balance-pin
The pinned middleware reserves user credits and throws a TOKEN_BALANCE error when the reservation cannot be admitted.
packages/api/src/middleware/checkBalance.ts, checkBalance · source-inspected · Source date not stated · Retrieved 2026-10-21
Commit e8f3be08623663d4ad7f7241e693c94469b63bb0, path packages/api/src/middleware/checkBalance.ts
Enterprise credits admin guide perplexity:perplexity:p-credits
Monthly Computer allocations are 500/Pro and 15,000/Max credits; user/group pool caps and auto-refill exist. The page conflicts about pool-credit expiry.
Individual/pool allocations; named usage limits; FAQ · documented · Source date 2026-09-09 · Retrieved 2026-10-21
Perplexity Tasks perplexity:perplexity:p-tasks
Recurring natural-language tasks minimum hourly, up to15 per conversation; no credits causes skipped runs and repeated skips pause them.
Scheduled Computer runs, cadence, unattended tasks and credits · documented · Source date 2026-09-21 · Retrieved 2026-10-21
Enterprise roles and permissions perplexity:perplexity:p-roles
Managed-plan Admin/Member/BillingAdmin, custom roles and synced groups; feature grants additive; model settings remain organisation-wide in inspected text.
Sales-assisted availability; base/custom roles; groups and master switches · documented · Source date not stated · Retrieved 2026-10-21
RAG API librechat:librechat:rag
A separate RAG API indexes uploaded content in PostgreSQL/PGVector for retrieval.
Architecture; document indexing; embeddings; semantic search · documented · Source date not stated · Retrieved 2026-10-21
Upload files as text librechat:librechat:text
Text upload injects extracted file content rather than relying only on vector retrieval.
Full text extraction and context · documented · Source date not stated · Retrieved 2026-10-21
File configuration librechat:librechat:filecfg
File limits and formats are configurable by endpoint and file processing route.
File limits; MIME patterns; provider routes · documented · Source date not stated · Retrieved 2026-10-21
LibreChat spreadsheet text parser librechat:librechat:r4-spreadsheet-parser
The built-in parser accepts XLSX/XLS/ODS and serializes each sheet as its name followed by CSV values. It does not establish preserved workbook layout, recalculated formulas or fixture accuracy.
getParserForMimeType; excelSheetToText, lines 109-129 · source-inspected · Source date 2026-10-24 · Retrieved 2026-10-26
Commit a378657583567310c841d652b0f6b00c83e2bd6b, path packages/api/src/files/documents/crud.ts
LibreChat current Upload as Text guide librechat:librechat:r4-text-current
The development guide lists XLSX/XLS/ODS parsing up to 15 MB and token-bounded text injection, not a formatted spreadsheet editor.
Built-in parser; supported documents; truncation · documented · Source date not stated · Retrieved 2026-10-26
Perplexity Computer in Microsoft Office perplexity:perplexity:p-office
Computer add-ins support Word/Excel/PowerPoint/Outlook plus Teams; Microsoft admin centre assigns users/groups; Enterprise Pro/Max use normal Computer credits.
App capabilities, supported plans, deployment and Outlook clients · vendor-claimed · Source date not stated · Retrieved 2026-10-21
Projects librechat:librechat:projects
Projects persist files and instructions across a user’s chats but cannot be shared or transferred.
Availability; personal scope; files and instructions · documented · Source date not stated · Retrieved 2026-10-21
What are Projects? perplexity:perplexity:p-projects
Persistent workspaces with instructions, files, tasks and owner/editor/viewer access; Brain updates can spend owner credits.
Instructions, sharing permissions, files and Brain · documented · Source date not stated · Retrieved 2026-10-21
SharePoint and OneDrive integration librechat:librechat:sharepoint
The Microsoft file picker uses Entra token reuse and delegated on-behalf-of downloads to attach files.
Prerequisites; delegated permissions; admin consent · documented · Source date not stated · Retrieved 2026-10-21
MCP librechat:librechat:mcp
MCP servers can be configured through YAML or the permission-gated UI, including per-user OAuth.
YAML/UI setup; authentication; ownership and selection · documented · Source date not stated · Retrieved 2026-10-21
MCP server configuration librechat:librechat:mcpcfg
Configuration includes stdio, SSE and Streamable HTTP transports and server-specific credentials.
Transport examples; headers; OAuth · documented · Source date not stated · Retrieved 2026-10-21
File connectors for Enterprise organisations perplexity:perplexity:p-connectors
Live search uses source queries; Project import makes static copies. Shared answers can reveal connected content to recipients without original-file permission.
Live search, attachments, Project imports and sharing boundary · documented · Source date not stated · Retrieved 2026-10-21
Gmail and Google Calendar connection perplexity:perplexity:p-gmail
Personal OAuth reads mailbox/calendar, with send/edit scopes for actions; source permissions differ from shared-answer visibility.
OAuth scopes, primary calendar and Comet actions · documented · Source date not stated · Retrieved 2026-10-21
Adding custom remote connectors perplexity:perplexity:p-mcp
Custom HTTPS MCP via SSE/streamable HTTP supports OAuth2, API key or no auth; admin shared OAuth and per-member auth are separate options.
Transport, authentication and organisation settings · documented · Source date not stated · Retrieved 2026-10-21
Using Perplexity in Microsoft Teams perplexity:perplexity:p-teams
Computer runs in Teams DMs/channels and can search Teams content within granted permissions; Teams license and Entra consent may be required.
Requirements, installation and channel/chat interaction · documented · Source date not stated · Retrieved 2026-10-21
Perplexity connectors for Enterprise FAQ perplexity:perplexity:p-connectfaq
Copied files are stored on AWS S3; live source changes and static Project imports differ. Format statements conflict with connector overview.
Storage, formats, permissions and manual reimport · documented · Source date not stated · Retrieved 2026-10-21
Role-based access control for connectors perplexity:perplexity:p-connector-rbac
Sales-assisted role grants and master enable switch enforce connector access before task runtime and credits; group entitlement is plan-dependent.
Managed-plan availability and runtime authorization · documented · Source date not stated · Retrieved 2026-10-21
LibreChat Docker service configuration librechat:librechat:compose-pin
The pinned example runs a MongoDB primary store and a separate PGVector/RAG service with customer-mounted data.
docker-compose.yml, api/mongodb/vectordb/rag_api services · source-inspected · Source date not stated · Retrieved 2026-10-21
Commit e8f3be08623663d4ad7f7241e693c94469b63bb0, path docker-compose.yml
What is new in advanced Deep Research? perplexity:perplexity:p-research
Deep Research performs multi-step web/file research with citations, charts and downloadable reports. Older named models are not used as the current Enterprise inventory.
Reports, source research, code execution and files · documented · Source date 2026-09-15 · Retrieved 2026-10-21
User memory librechat:librechat:memory
Configured user memory stores cross-chat key/value context with user editing controls; it does not index all past chats.
Key/value store; controls; disabled by default · documented · Source date not stated · Retrieved 2026-10-21
Memory for Enterprise organisations perplexity:perplexity:p-memory
Users can manage memory; admins can disable it and delete organisation memories; deleted memory logs may remain30days.
Saved memory, history and admin controls · documented · Source date 2026-09-01 · Retrieved 2026-10-21
Enterprise roles and permissions perplexity:perplexity:p-roles-20261026
Managed-plan Admin/Member/BillingAdmin, custom roles and synced groups; feature grants additive; model settings remain organisation-wide in inspected text.
Sales-assisted availability; base/custom roles; groups and master switches; public web-reader representation retrieved 2026-10-26, representation SHA256 06fe5a476f097c102d380d35bf9db56348d1e4e3e89633e6017163cada5e6538 · documented · Source date not stated · Retrieved 2026-10-26
How to use Computer Skills perplexity:perplexity:p-skills-20261026
Computer selects task Skills; users create or upload SKILL.md/zip instruction packages.
Built-in/custom Skills; creation and upload; public web-reader representation retrieved 2026-10-26, representation SHA256 f582e50af86ba66a0b7f4ba097202e67618a8d8aa3b4b93c7b5652833085eeb1 · documented · Source date not stated · Retrieved 2026-10-26
What are Projects? perplexity:perplexity:p-projects-20261026
Persistent workspaces with instructions, files, tasks and owner/editor/viewer access; Brain updates can spend owner credits.
Instructions, sharing permissions, files and Brain; public web-reader representation retrieved 2026-10-26, representation SHA256 30fa9a960823ef5efa0ac26cb0ffc1e69256a5e6d2d8b07acd1b32e04b661acb · documented · Source date not stated · Retrieved 2026-10-26
Image generation and editing librechat:librechat:images
Agents can use configured image tools for generation/editing; provider credentials and model parameters are separate.
OpenAI Image Tools; provider setup; admin configuration · documented · Source date not stated · Retrieved 2026-10-21
How to use Computer Skills perplexity:perplexity:p-skills
Computer selects task Skills; users create or upload SKILL.md/zip instruction packages.
Built-in/custom Skills; creation and upload · documented · Source date not stated · Retrieved 2026-10-21
Web search librechat:librechat:web
Search can use Serper, SearXNG, Tavily or Keenable, with independently configured scraping and optional reranking.
Provider, scraper and reranker configuration · documented · Source date not stated · Retrieved 2026-10-21
What is Enterprise Pro? perplexity:perplexity:p-entpro
Ask and standard search do not consume Computer credits; cloud Computer uses included and pooled credits.
Computer, Ask, data protections and retention sections · documented · Source date 2026-10-06 · Retrieved 2026-10-21
Scheduled Chats librechat:librechat:schedule
Opt-in experimental schedules execute saved Agents with cron/time zones and recheck access and balance before running.
Experimental and disabled by default; runtime and permissions · documented · Source date not stated · Retrieved 2026-10-21
Agents API beta librechat:librechat:api
The beta API exposes chat/Responses inference, Agent/Skill management and authenticated event delivery.
Inference; management; Agent Events; authentication · documented · Source date not stated · Retrieved 2026-10-21
Enterprise pricing and billing FAQ perplexity:perplexity:p-billing
Pro costs USD40/month or400/year; Max325/month or3250/year. No self-serve Enterprise trial; API billed separately.
Pricing, API exclusion, trials, invoicing and seat reductions · documented · Source date 2026-10-08 · Retrieved 2026-10-21
Temporary chat and data retention librechat:librechat:retention
Operators configure expiry for chats/messages/files/shared links; normal chats do not expire by default and memories are excluded.
Default 30-day temporary retention; all/ephemeral; deadlines; memories · documented · Source date not stated · Retrieved 2026-10-21
Admin Insights librechat:librechat:insights
Insights reports persisted MongoDB activity and identifiable recent conversations; it is not monetary billing analytics.
Opt-in; capabilities; metrics; tenant scope · documented · Source date not stated · Retrieved 2026-10-21
Docker installation librechat:librechat:local
Docker self-installation runs LibreChat with its configured service dependencies.
Installation; configuration; updating · documented · Source date not stated · Retrieved 2026-10-21
Perplexity Enterprise perplexity:perplexity:p-home
Enterprise offers cloud Search/Computer, business connectors and administration.
Product overview and security FAQ · vendor-claimed · Source date not stated · Retrieved 2026-10-21
About the Perplexity desktop app perplexity:perplexity:p-desktop
Windows/macOS clients have local-file access; macOS app control and remote access are distinct from on-device inference.
Desktop platforms, local folders and app control · documented · Source date 2026-09-15 · Retrieved 2026-10-21
Perplexity Voice Assistant for iOS perplexity:perplexity:p-voice
iOS voice conversations are documented; Enterprise SSO and Swiss German quality were not tested.
Voice activation and conversation history · documented · Source date 2026-09-11 · Retrieved 2026-10-21
Generating images with Perplexity perplexity:perplexity:p-image
GPT Image1, Nano Banana, Seedream4.5; Nano Banana Pro on Max. Enterprise image commercial use allowed.
Image models, edits and enterprise use rights · documented · Source date 2026-08-31 · Retrieved 2026-10-21
Perplexity Enterprise terms and conditions perplexity:perplexity:p-terms-gb
Perplexity AI, Inc. contracts under California law with USD fees, no model training and customer output ownership; specific product terms govern conflicts.
Sections1–3,5,7,9,11; August3,2026 English edition · documented · Source date 2026-08-03 · Retrieved 2026-10-21
Speech configuration librechat:librechat:speech
Administrators configure audio provider engines and models separately from text generation.
Speech-to-text and text-to-speech engines · documented · Source date not stated · Retrieved 2026-10-21
LibreChat conversation-mode speech settings librechat:librechat:speech-conversation-r2
Conversation mode chains transcription, auto-send and TTS playback for hands-free turns after microphone activation; engines and audio routing are separately configured.
Speech Tab: conversationMode, autoTranscribeAudio, autoSendText, automaticPlayback; engine and allowedAddresses settings · documented · Source date not stated · Retrieved 2026-10-21
Artifacts librechat:librechat:artifacts
Artifacts render generated React, HTML and Mermaid content in the chat interface.
React, HTML and Mermaid previews · documented · Source date not stated · Retrieved 2026-10-21
Creating assets with Perplexity perplexity:perplexity:p-assets
DOCX/PDF/XLSX/PPTX/HTML outputs, previews and version history are documented; exact templates require external editing.
Output formats, preview, follow-up editing and exports · documented · Source date 2026-09-01 · Retrieved 2026-10-21
Shareable links librechat:librechat:share
Shared links publish a transcript branch and optional file snapshots independently of the owner’s live file ACL.
Authentication defaults; file snapshots; continuation · documented · Source date not stated · Retrieved 2026-10-21
Enterprise Security Hub settings perplexity:perplexity:p-security-hub
Disabling public sharing leaves existing public links live; enforced incognito retains attachments/sessions24h.
Organisation/public links and Enforce Incognito · documented · Source date 2026-09-07 · Retrieved 2026-10-21
LibreChat locale registration librechat:librechat:i18n-pin
The pinned client registers English, German, French and Italian translations among its supported locales.
client/src/locales/i18n.ts, language resources · source-inspected · Source date not stated · Retrieved 2026-10-21
Commit e8f3be08623663d4ad7f7241e693c94469b63bb0, path client/src/locales/i18n.ts
Authentication system librechat:librechat:auth
Local/LDAP accounts can be required to use TOTP; federated MFA belongs to the identity provider and account creation/deletion scripts are documented.
Required two-factor authentication; Registration; User scripts · documented · Source date not stated · Retrieved 2026-10-21
OAuth2 and OIDC librechat:librechat:openid
LibreChat documents OAuth2/OIDC providers including Microsoft Entra, Google, Keycloak and Auth0.
Supported providers; setup · documented · Source date not stated · Retrieved 2026-10-21
SAML authentication librechat:librechat:saml
SAML is a documented authentication option for the self-hosted application.
Overview and requirements · documented · Source date not stated · Retrieved 2026-10-21
Azure Entra authentication librechat:librechat:entra
Entra OIDC supports group-based admission and Graph integration using configured scopes and token reuse.
Group claims; token reuse; Microsoft Graph integration · documented · Source date not stated · Retrieved 2026-10-21
SSO integration getting started perplexity:perplexity:p-sso
Paid Enterprise SSO needs verified domains and invited users; one IdP by default. Generic standards examples are not a full protocol matrix.
Paid organisation requirement, DNS domains and invitations · documented · Source date 2026-09-14 · Retrieved 2026-10-21
Perplexity product FAQ perplexity:perplexity:p-hub-faq
Vendor identifies SAML SSO and SCIM for Enterprise and lists web, mobile, Comet and API access.
FAQ, information protection and client access · vendor-claimed · Source date not stated · Retrieved 2026-10-21
SCIM-based user account management perplexity:perplexity:p-scim
SCIM needs50seats or oneMax; Okta/Entra/Google/customSCIM. Older basic role-group statement differs from newer managed roles rollout.
Eligibility, supported providers and UI authority · documented · Source date 2026-09-05 · Retrieved 2026-10-21
Enterprise roles and permissions perplexity:perplexity:p-roles-rollout-correction
The new Roles & Permissions UI rolls out gradually and requires eligible sales-assisted plans for custom roles and directory groups; legacy UI settings carry over.
Overview availability and gradual upgrades; Groups · documented · Source date not stated · Retrieved 2026-10-21
Token usage librechat:librechat:tokens
Usage and estimated costs use recorded tokens and configured provider rates; transactions are distinct from balance enforcement.
Context cost; transactions; per-endpoint token rates · documented · Source date not stated · Retrieved 2026-10-21
Enterprise usage analytics perplexity:perplexity:p-analytics
Insights requires50seats or oneMax and provides adoption, feature and per-user query reporting with export.
Eligibility, Insights metrics, user table and export · documented · Source date 2026-09-29 · Retrieved 2026-10-21
Logging librechat:librechat:logging
Backend operational logs are written to customer files and can feed external tools; the guide describes 14-day rotation rather than a compliance archive.
Error/debug logs; rotation; external tools · documented · Source date not stated · Retrieved 2026-10-21
LibreChat development content-filter configuration librechat:librechat:r4-content-filter
Opt-in base-YAML policies inspect selected message/file content; block and audit differ from limited Agent text redaction. This is development documentation, not a hosted DLP assurance.
Source-Aware Filters; Pattern Configuration; Redaction; File Fields · documented · Source date not stated · Retrieved 2026-10-26
LibreChat content-inspection runtime librechat:librechat:r4-pii-runtime
Source-aware configured inspection executes in the LibreChat API. Missing policy disables that scope; configured actions and fields bound inspection.
createConfiguredContentInspector; source rule configuration · source-inspected · Source date 2026-10-24 · Retrieved 2026-10-26
Commit a378657583567310c841d652b0f6b00c83e2bd6b, path packages/api/src/protection/runtime.ts
LibreChat pattern detector librechat:librechat:r4-patterns
Default starter patterns detect credential-shaped tokens/headers. Operator custom patterns use bounded regular expressions; a generic comprehensive PII classifier is not established.
STARTER_PATTERNS; configured RE2JS rules · source-inspected · Source date 2026-10-24 · Retrieved 2026-10-26
Commit a378657583567310c841d652b0f6b00c83e2bd6b, path packages/api/src/protection/detectors/pattern.ts
LibreChat private text submission librechat:librechat:r4-private-submission
The private text ingress permits configured redaction only on eligible fresh interactive Agent text. Original content is encrypted; edit/resume/file paths do not gain blanket redaction.
createPrivateTextIngress; fresh Agent text and clientRequestId checks · source-inspected · Source date 2026-10-24 · Retrieved 2026-10-26
Commit a378657583567310c841d652b0f6b00c83e2bd6b, path packages/api/src/protection/private/submission.ts
LibreChat API content-filter middleware librechat:librechat:r4-filter-middleware
The server middleware applies configured inspection and rejects blocked/uninspectable requests with HTTP 400. No deployment or detection fixture was run.
createMessageFilterPii; contentFilterBlockResponse; uninspectable response · source-inspected · Source date 2026-10-24 · Retrieved 2026-10-26
Commit a378657583567310c841d652b0f6b00c83e2bd6b, path packages/api/src/middleware/messageFilterPii.ts
LibreChat config v1.3.18 changelog librechat:librechat:r4-config-1318
Dated development config changes add limited Agent text redaction and ephemeral retention mode. These are not a promise of universal redaction or a vendor zero-retention contract.
October 22, 2026; opt-in PII redaction; retention mode · documented · Source date 2026-10-22 · Retrieved 2026-10-26
Interface configuration librechat:librechat:interface
Administrators configure UI feature permissions and usage terms in the self-hosted deployment.
Feature permissions; custom welcome and terms · documented · Source date not stated · Retrieved 2026-10-21
Remote hosting librechat:librechat:remote
The application can be deployed on customer-selected remote servers with operator-managed security.
Hosting options; security considerations · documented · Source date not stated · Retrieved 2026-10-21
Perplexity security perplexity:perplexity:p-security
Vendor claims SOC2TypeII and annual independent testing; staff JIT access and production segregation described, reports not inspected.
Enterprise controls, access management and penetration tests · vendor-claimed · Source date 2026-08-21 · Retrieved 2026-10-21
LibreChat Demo terms librechat:librechat:demo
The free hosted Demo is offered as-is with possible data cleanups and no durable business-service guarantee.
Evaluation scope; retention; disclaimer · documented · Source date 2026-03-12 · Retrieved 2026-10-21
Personal settings librechat:librechat:settings
Users configure interface language, audio and personal data controls.
Language; speech; data controls · documented · Source date not stated · Retrieved 2026-10-21
Data retention for Enterprise perplexity:perplexity:p-retention
Session-file default7days; custom session retention50seats or oneMax uses last activity and deletes outside-window data within7days.
Session-file default, custom windows and deletion · documented · Source date 2026-09-07 · Retrieved 2026-10-21
Perplexity data processing addendum perplexity:perplexity:p-dpa-gb
DPA provides employee confidentiality, subprocessor notices, SCCs and 30-day personal-data deletion/return at service end with legal exceptions.
August13,2026 English edition; sections4,6,10,11 andAnnex1 · documented · Source date 2026-08-13 · Retrieved 2026-10-21
ClickHouse acquisition of LibreChat librechat:librechat:owner
ClickHouse announced the acquisition of LibreChat and that Danny Avila and the team joined ClickHouse.
Announcement, November 4, 2025 · documented · Source date 2025-11-04 · Retrieved 2026-10-21
LibreChat website privacy policy librechat:librechat:siteprivacy
Website, demo and self-hosted software are distinct privacy scopes; website terms do not establish a customer deployment DPA.
Scope and exclusions · documented · Source date not stated · Retrieved 2026-10-21
LibreChat v0.8.8 message storage schema librechat:librechat:secrecy-message-pin
The pinned Mongoose schema declares message text as a String and content as mixed fields; this source does not establish operator exclusion from live content.
packages/data-schemas/src/schema/message.ts, text at lines 55-58 and content at lines 139-143 · source-inspected · Source date not stated · Retrieved 2026-10-21
Commit e8f3be08623663d4ad7f7241e693c94469b63bb0, path packages/data-schemas/src/schema/message.ts
LibreChat Demo privacy policy librechat:librechat:secrecy-demo-policy
The Demo policy describes model-provider transmission and contractual processor instruction/security duties for the Demo; it does not cover a customer self-hosted deployment.
Scope; section 4 Third-Party AI Model Providers; section 6 Data Sharing and Sub-Processors · documented · Source date 2026-03-12 · Retrieved 2026-10-21
Azure Retail Prices, Switzerland North Linux VMs librechat:librechat:cost-vm
EUR hourly PAYG rates retrieved 2026-10-21 are 0.2226, 0.4453 and 0.8905 for D4s, D8s and D16s v5 respectively.
Consumption; Virtual Machines Dsv5 Series; Standard_D4s_v5/D8s_v5/D16s_v5 · documented · Source date not stated · Retrieved 2026-10-21
Azure Retail Prices, PostgreSQL Flexible Server librechat:librechat:cost-pg
EUR hourly PAYG GP compute is 0.2288, 0.4576 and 0.9152 for 2/4/8 vCore; storage is EUR 0.1325 per GB-month.
General Purpose Ddsv5 Series Compute, 2/4/8 vCore; Flex Server Storage · documented · Source date not stated · Retrieved 2026-10-21
ECB euro reference rate history librechat:librechat:cost-fx
The 2026-10-20 reference rates are EUR 1 = USD 1.1215 and CHF 0.9237.
Cube time=2026-10-20; USD and CHF · documented · Source date 2026-10-20 · Retrieved 2026-10-21
OpenAI API pricing librechat:librechat:cost-model
Standard gpt-6-luna API price is USD 0.10 per million input tokens and USD 0.50 per million output tokens; caching, batch and regional premiums are separate.
Standard, short-context gpt-6-luna row · documented · Source date not stated · Retrieved 2026-10-21
GPT-6 Luna model documentation librechat:librechat:cost-effort
The model accepts reasoning effort none, the lowest documented effort, and lists the same standard text-token rates.
Reasoning effort and text-token pricing · documented · Source date not stated · Retrieved 2026-10-21
ECB historical euro reference exchange rates perplexity:perplexity:fx-ecb
EUR1=USD1.1215=CHF0.9237 on2026-10-20; conversion arithmetic is an analyst calculation.
Cube time=2026-10-20; USD and CHF · documented · Source date 2026-10-20 · Retrieved 2026-10-21
LibreChat conversation export implementation librechat:librechat:export-pin
The pinned user conversation exporter supports JSON, CSV, Markdown and text, plus screenshot export.
client/src/hooks/Conversations/useExportConversation.ts, export dispatch · source-inspected · Source date not stated · Retrieved 2026-10-21
Commit e8f3be08623663d4ad7f7241e693c94469b63bb0, path client/src/hooks/Conversations/useExportConversation.ts
Enterprise Security Hub settings perplexity:perplexity:p-security-hub-20261026
Disabling public sharing leaves existing public links live; enforced incognito retains attachments/sessions24h.
Organisation/public links and Enforce Incognito; public web-reader representation retrieved 2026-10-26, representation SHA256 11f7eb441cbc7708f8686e2b8862ba5030d0ab3c2ebb39f22903c3296806004f · documented · Source date 2026-09-07 · Retrieved 2026-10-26
Perplexity data processing addendum perplexity:perplexity:p-dpa-gb-20261026
DPA provides employee confidentiality, subprocessor notices, SCCs and 30-day personal-data deletion/return at service end with legal exceptions.
August13,2026 English edition; sections4,6,10,11 andAnnex1; public web-reader representation retrieved 2026-10-26, representation SHA256 9e139f0ef944a998aca7167ce408fc9f27611a18703995d720c0a773535e5462 · documented · Source date 2026-08-13 · Retrieved 2026-10-26
Perplexity status perplexity:perplexity:p-status-web
Public operational status and calendar are available; no contracted SLA inferred.
Website/App/Computer/API and calendar · documented · Source date not stated · Retrieved 2026-10-21
Download and move your organisation files perplexity:perplexity:p-repo-retire
Remaining organisation repository files are deleted after October 1, 2026; customers must manually move needed files to Projects or connectors.
Repository retirement and migration steps · documented · Source date not stated · Retrieved 2026-10-21