Features

Everything NXBrain does,
and the plan that includes it.

62 features across routing, data protection, cost control, agents, change management, privacy, proof and compliance. Each plan includes everything in the plans before it.

BasicStarterProEnterprise

Connect & route

One OpenAI-compatible endpoint in front of every model you use, in the cloud or on your own servers.

FeatureWhat it doesPlan
OpenAI-compatible APIPOST /v1/chat/completions with OpenAI’s request and response format, streaming included. Point your SDK at a new base URL.Basic
Abstract modelsYour code calls nxbrain/reasoning or nxbrain/fast. You decide which real model is behind each name.Basic
Versioned routesEach abstract model has a route: destinations with priority, weight, timeout and retries. A published version never changes.Basic
Fallback and circuit breakerRetryable errors move to the next destination. A gateway that fails three times in a row is skipped for 60 seconds.Basic
Conditional routingProject policies decide which models and gateways each project may use. The route skips any destination that doesn’t qualify and records why.Pro
Your own provider keysUse your OpenAI, Anthropic or Google keys. They are encrypted with your organization’s key, and we add no markup.Basic
Self-hosted modelsRegister your own OpenAI-compatible servers, such as Ollama, vLLM or llama.cpp, over HTTPS with their own key.Basic
Route simulatorSee which destination a request would take, and why the others were left out, without making the call.Basic

Protect data

Inspect every request and response, and decide per project what happens when something sensitive shows up.

FeatureWhat it doesPlan
Basic guardrailsTemplates for personal data and secrets: email, phone, payment cards, IBAN, API keys and private keys.Basic
All guardrails and your own rulesPrompt injection indicators, moderation by category, your own banned terms, a maximum input size and JSON output validation. Each detector can observe, warn, redact or block.Starter
Input and output, streams includedRequests are checked before they reach the model, and responses before they reach your app. Streams are inspected as they arrive.Basic
Incidents without contentEvery guardrail hit is logged with its detector, stage and decision. The text itself is never stored.Basic
Custom detectorsDetectors built for your data and your sector.Enterprise
Keys per app, team or agentVirtual keys with expiry, a rotation date and instant revocation. Archiving a project revokes all its keys at once.Basic
Project policiesAllowed models and gateways, maximum input and output tokens, and whether prompts must come from the catalog.Basic
Rate and concurrency limitsRequests and tokens per minute for each key, project and organization, answered with Retry-After when a limit is hit.Starter
Roles and two-factor sign-inAdmin, AI operator, FinOps, auditor and viewer roles, checked on the server, with optional two-factor codes.Basic
Single sign-onEntra ID, Google, Okta or any OIDC provider on your verified domains, with SSO-only sign-in if you want it.Pro

Control costs

Every call is reserved against its budget before it runs and settled after it finishes, so a budget is a limit, not a report.

FeatureWhat it doesPlan
Hard budgetsA budget per project and per agent, reserved before each call so parallel requests can’t overspend it. When it runs out, calls return 402 BUDGET_EXCEEDED.Starter
Alerts at 50, 75, 90 and 100%A metric, an alert and an email at each threshold.Starter
Cost by project, model, gateway and daySpend and tokens in real time, metered in millionths of a euro.Basic
Blocked calls cost nothingA request stopped by a guardrail never reaches the provider and never touches the budget.Basic
Access requestsTeams ask for a model, more budget, a tool or a project. Someone else decides, and an approval is a decision, not an automatic change.Starter

Agents

Give each agent its own keys, models, tools and budget, and keep a person in the loop for what matters.

FeatureWhat it doesPlan
Agent catalogPurpose, authorized models, status, limits per run (steps, duration, tokens and cost) and a running budget.Pro
Tool permissionsAllow or deny each tool for each agent, MCP tools included. Disabling a tool cuts it off for every agent at once.Pro
Human approvalSensitive tools wait for a person. Each approval works once and expires.Pro
Kill switchPause or stop an agent and every key linked to it is rejected instantly.Pro
Execution tracesSteps, tool calls and hand-offs between agents, recorded as metadata only.Pro

Ship changes safely

Routes, policies, guardrails and prompts change through the same reviewed process, and nothing is edited in place.

FeatureWhat it doesPlan
Change centerDraft, validate, approve and publish policies, routes and guardrails. The author can’t approve their own change.Basic
Versions and restorePublished configuration never changes. Restoring an older version creates a new one.Basic
Prompt catalogSystem prompts used by name, with versions, declared variables, two-person publishing and rollback. The text is encrypted.Starter
EvaluationsVersioned datasets; deterministic, model-based or external evaluators; weighted scorecards. Run them by hand, from CI or on a schedule.Pro
Promotion gatesA protected route or prompt only goes live with a recent evaluation that meets your minimum score and maximum regression.Pro
PlaygroundTry models and prompt versions with a real key’s identity, under the same policy, guardrails and budget as production.Basic

Privacy

We record what happened, not what was said.

FeatureWhat it doesPlan
No prompts stored by defaultOnly metadata, counts, hashes and IDs are kept.Basic
Opt-in encrypted captureKeep the full text if you need it: encrypted with AES-256-GCM, deleted automatically after the days you choose, every read logged.Pro
Your own encryption keyProvider keys, captured content, evidence and prompts are encrypted with a key that belongs to your organization.Basic
Isolation between organizationsRow-level security on every table that holds customer data.Basic
Export everythingYour full sealed history in an open format, verifiable without us.Basic

Proof

Every call, change and approval becomes evidence that anyone can check.

FeatureWhat it doesPlan
Sealed audit logEvery five minutes, new events are sealed into a Merkle chain (RFC 6962). Altered or deleted events are detected.Basic
Public verificationCheck a seal, an event or a report at /verify in the browser, or offline with the nxbrain-verify tool. No account needed.Basic
Trusted timestampsEach sealing pass can be timestamped by an independent authority (RFC 3161), with a daily locked copy of the seals.Pro
Inclusion proofs and exportProve that one event is in a sealed batch, and export any period as NDJSON.Basic
Systems outside the gatewaySend events from other AI systems with POST /v1/events, OpenTelemetry traces or the TypeScript and Python SDKs.Basic

Compliance

Organize AI compliance around what actually runs. A person always makes the final call.

FeatureWhat it doesPlan
AI inventoryEvery AI system, connected or not: purpose, role, data, providers and DPAs, linked to projects and agents, with 30 days of real activity. CSV import and export.Basic
Risk classificationAn EU AI Act questionnaire with an explainable result that cites its articles. It is indicative, and two people approve it.Basic
ObligationsEach with an owner, a start date and a due date, and reminders by email and webhook.Starter
Impact assessments and AI policyDPIA, FRIA, transparency notice and AI policy, drafted from your inventory and approved by two people.Starter
Reports without watermarkPDF reports per system and per organization. On Basic they carry a watermark.Starter
Technical documentationEU AI Act Annex IV documentation drafted from your inventory and classification.Pro
ISO/IEC 42001Statement of applicability for the 38 Annex A controls, with evidence collected from real activity.Pro
IncidentsAI Act incident categories with their notification deadlines (2, 10 or 15 days), followed up to closure.Pro
AI literacyTraining records per person, with expiry (AI Act, article 4).Pro
Evidence packsA ZIP with a manifest. Every file is sealed and anyone can verify it.Pro

Developer tools

Wire NXBrain into the tools you already run.

FeatureWhat it doesPlan
WebhooksSigned with HMAC-SHA256 for access requests, compliance, prompt and team events, with retries and delivery history.Pro
Automation APITokens with scopes, expiry and revocation to read configuration and manage access requests. Documented in OpenAPI.Pro
SDKsTypeScript and Python, to send events from systems outside the gateway.Basic
OpenAPI contractThe full contract at /openapi.json.Basic

Enterprise

For regulated industries, built to fit.

FeatureWhat it doesPlan
Dedicated deploymentNXBrain deployed for your organization only.Enterprise
Custom limits and retentionLimits and retention set in your contract.Enterprise
SLA and dedicated supportA service-level agreement and a named support contact.Enterprise
Assisted reviewWe review your setup with your team.Enterprise

Plan limits

Plans differ in how much you can govern and how long the record is kept. Priced by AI systems and usage, not per seat: each plan includes its users. No markup on your model keys.

Basic€10/mo · €0 during the betaStarter€79/mo · €790/yrPro€399/mo · €3,990/yrEnterpriseCustom
AI systems31050Custom
Users2520Custom
Events a month10,000250,000, then €20 per 100k2M, then €15 per 100kCustom
Retention7 days30 days12 monthsCustom

High-risk AI systems keep their activity for at least 183 days, as the EU AI Act requires, within your plan’s retention.