# Models and prompts · Neural Inverse Govern > A model catalog you control, deny-by-default assignment to teams and projects, versioned prompts served through the gateway, and adoption and cost reporting without prompt content. Source: https://neuralinverse.com/govern/models/ --- ![](/photos/facility.jpg) [Neural Inverse Govern / Models and prompts](https://neuralinverse.com/govern/) # Which models exist for whom, and which prompts they run. A model catalog you control, deny-by-default assignment to teams and projects, versioned prompts served through the gateway, and adoption and cost reporting without prompt content. Catalog Entered by you, with your prices Assignment Deny by default, deny wins Delivery Ed25519-signed model manifest Prompts Versions and labels, rendered by the gateway Reporting Metadata only, pseudonymised by default Overview Models and prompts is where you decide what the AI Gateway may serve. Platform teams connect providers, enter models and their prices, and assign them to the organisation, teams and projects. Applications reference prompts from a versioned library instead of carrying them in code. Insights reports who uses which model, MCP server, skill and harness pack, and what it costs, from usage metadata only. [What it does ↓](https://neuralinverse.com/#capabilities)[How it works ↓](https://neuralinverse.com/#workflow)[Enforced and recorded ↓](https://neuralinverse.com/#enforcement)[Where it runs ↓](https://neuralinverse.com/#where)[Get started ↓](https://neuralinverse.com/#get-started) What it does ## What models and prompts covers. The catalog and who may use it, the prompts that run against it, and what that use amounts to. - **Provider connections:** Anthropic, OpenAI, Google, Azure OpenAI, Amazon Bedrock, Vertex AI, and self-hosted OpenAI-compatible or Ollama servers. Keys are write-only, held in Govern's vault, and handled by a permission separate from the one that configures the connection. - **Your own catalog:** Each model is entered with its provider model id, uses, region, residency, the strictest classification it may serve, zero-retention flag, prices and limits. Govern does not discover models from providers, so the catalog works air-gapped. - **Deny-by-default assignment:** A model is allowed or denied for the organisation, a team or a project. It is usable only when allowed at a scope that applies to the person and denied at none. Leaving out the project never loosens a project's rules. - **Classification and regions:** Rules per data classification require any model, a zero-retention model or a self-hosted one, optionally in listed regions. Restricted work defaults to self-hosted or zero-retention models. - **Fallback chains:** Up to twenty fallbacks per model. Each fallback is decided again from scratch, so it never reaches a model the caller could not use directly. - **Defaults per use:** A default model for chat, agent, completion and embedding work at the organisation, team or project. The most specific scope wins, and a default the person may not use is skipped. - **Signed model manifest:** The Neural Inverse apps receive an Ed25519-signed list of what the person may use. It stays valid offline for a period you set, 24 hours by default and at most seven days. - **Personal provider keys:** When you allow it, people store their own Anthropic, OpenAI or Google key. It is used only through the gateway, only for models you allowed, and only up to a classification you set. - **Provider health:** Probe a connection on demand or on a schedule, and see the last probes, latency and circuit state of its models, without a provider's error bodies. - **Prompt library:** Versioned prompt templates with variables and organisation-wide values. Test, pin, fork and deprecate templates, and collect run statistics and feedback. - **Prompt labels:** Applications call a template by label, such as production, and the gateway renders it in OpenAI or Anthropic format. Moving a label promotes or rolls back a prompt without a client change. - **Prompt runs:** Every request made from a template is recorded with its version, label, the model that answered, measured tokens and cost, duration and outcome. Templates are also available to agents as an MCP tool. - **Compare models:** A playground sends one request as the signed-in person to up to four models or routes side by side. Evaluation datasets sampled from sealed request logs score models and routes with exact, contains, regex, JSON schema and model-graded evaluators. - **Model Passport:** A short-lived, Ed25519-signed attestation that binds an agent, and optionally its session and action, to the provider, model, version and hash it used, with a human-in-the-loop flag. Anyone with its id can verify it. - **Adoption and cost insights:** Summaries, time series and breakdowns by model, team, harness pack, MCP server and skill, with budgets and outcome signals such as changes kept, edited or discarded. - **Metadata only:** Usage events carry identifiers, counts and outcomes, never prompts or code. Per-person views are pseudonymised by default, and exports of raw events are audited. Bedrock models other than Anthropic models, and Gemini's native API, are not supported; Google and Vertex Gemini models are reached through their OpenAI-compatible endpoints. Spend on a personal key is not counted against spend budgets; its tokens are. How it works ## From a provider key to a model on someone's screen. 1. Connect Add a provider connection and set its key, which nobody can read back. 2. Catalog Enter each model with its prices, limits and the strictest classification it may serve. 3. Assign Allow models for the organisation, teams or projects. Nothing is usable until you do. 4. Deliver The apps fetch the signed manifest of what each person may use. 5. Serve The AI Gateway decides every request against the same rules, rendering prompts by label. 6. Measure Usage, cost and outcomes arrive in Insights, without prompt content. Who uses it ## Built for every role that answers for AI. - **Platform and AI enablement teams:** Connect providers, curate the catalog and its prices, set defaults and fallbacks, and assign models. - **Key custodians:** Set and rotate provider keys under their own permission, without being able to change routing policy. - **Application developers:** Publish prompt templates, move labels to promote or roll back, and compare models on their own traffic. - **Engineering and finance leads:** Read adoption and cost by team, model and tool, and export metadata for chargeback. Enforced and recorded ## Decided on the server, recorded with the change. Assignments, classification rules and regions are enforced by the AI Gateway on every request. The manifest only tells the apps what the gateway will allow. Enforced - **Deny wins:** A deny at any applicable scope removes the model, for the requested model, every fallback and every route target. - **Classification:** A request takes the strictest classification of its project, team, department and organisation. A client may raise it, never lower it. - **Keys stay inside:** Provider keys are never returned. Changing a connection's address, region or settings drops its stored key, so nobody can redirect a key to a host they control. - **Outbound guard:** Calls to providers refuse private, loopback, link-local and cloud metadata addresses unless your operator opens networks for self-hosted model servers. Recorded - **Configuration:** Every change to connections, catalog, assignments, defaults and policy, in its own transaction. Key changes record the new version and the last four characters, never the key. - **Prompt runs:** Each gateway request made from a template, with its version, label, model, tokens and cost. - **Passports:** Every issued passport is stored and listed with a verification verdict. Where it runs ## With your providers or your own models. [Deployment options](https://neuralinverse.com/deployment/) - **Self-hosted and in your cloud:** Provider keys stay in the vault of your installation. Your operator decides which private networks count as self-hosted. - **Air-gapped:** With local models only: register on-premises inference servers and approve local models per data class. The catalog and prices are yours. - **Mixed:** Restricted work on self-hosted models, everything else on hosted providers, decided by classification rules. - **Hosted by us:** We run it for you, with the same controls and audit record. Get started ## Set it up with the documentation. - [Model access](https://neuralinverse.com/docs/govern/model-access/) - [AI Gateway](https://neuralinverse.com/docs/govern/ai-gateway/) - [Budgets and rate limits](https://neuralinverse.com/docs/govern/budgets-rate-limits/) - [Routing and caching](https://neuralinverse.com/docs/govern/routing-caching/) - [Request logs and observability](https://neuralinverse.com/docs/govern/request-logs/) What's next ## Being built now. These are in development and not part of the product today. - **Model registry:** Register your own models and their versions, promote them through a lifecycle and record deployments. - **Model safety evaluations:** Evaluation suites and test cases scored per model, with comparisons, a leaderboard and stored red-team scenarios. - **Golden sets and drift:** Golden question sets per project, run through a model against a baseline, to detect and attribute drift. - **Passport revocation:** Revoke an issued passport, and keep a list of models approved for passport issuance. Related [AI Gateway → Approved models, DLP, guardrails, budgets and rate limits for every model request.](https://neuralinverse.com/govern/ai-gateway/)[Agents → Agent identities, consent from the people they act for, delegation limits and governed calls to remote agents.](https://neuralinverse.com/govern/agents/)[Audit and evidence → A hash-chained audit log you can verify offline, and evidence toward your frameworks.](https://neuralinverse.com/govern/audit/) ![](/photos/team.jpg) ## Talk to our team. Neural Inverse is available by request. We work with your engineering, security and procurement teams from the first conversation. [Request access](https://neuralinverse.com/contact/?topic=access)[Contact us](https://neuralinverse.com/contact/)