Skip to content
EdgeLex

AI & Intelligence · AI Governance

Your firm — not an AI vendor — controls the models, the data access, the tools, and the approvals.

Built into EdgeLex

app.edgelex.com — AI Model GovernanceMC

AI Model Governance

Control which AI models the Lex Runtime can use, set defaults, and monitor usage.

+ Add Provider

🛡 Runtime Governance Active authority

The Lex Runtime checks firm policy in the database before any model call. Browser clients cannot override this policy.

Allowed models25Default modelFirm default · pinnedExternal runtime authorityNo
Providers & ModelsProvider KeysFirm PolicyUsage & AccountingIntent Classifier
AnthropicFrontieractiveRuntime governed2/25 models enabled
OpenAIFrontieractiveRuntime governed11/59 models enabled
xAIFrontieractiveRuntime governed5/5 models enabled
Local GPU — GovernedLocalactiveRuntime governed6/8 models enabled
NVIDIAFrontieractiveRuntime governed0/130 models enabled

The problem

Most legal AI governance is a policy PDF and a prompt asking the model to be careful. When the model is wrong, you find out after the answer — with no record of what it was allowed to see or do.

How model policy actually works

Allowed. Enforced. Keyed. Metered. Attributed.

Follow one firm’s model policy through the system — every screen below is the real product.

01 · Allowed

Every model is a deliberate decision.

Provider catalogs arrive with every model disabled. Each one is allowed or denied by the firm — with its capabilities, context window, and price on the row. Refreshing a catalog never changes firm policy.

Provider catalog — every model allowed or denied, deliberately

Official provider pricing · View source

New catalog models are added disabled. Refreshing prices never changes firm model policy.

gpt-4.1chat · vision · 1.05M ctx · $2/$8 MTok in/outAllowed
gpt-4.1-minichat · vision · 1.05M ctx · $0.4/$1.6 MTok in/outAllowed
gpt-4chat · 7K ctx · $30/$60 MTok in/outDenied
gpt-4o-minichat · 128K ctx · $0.15/$0.6 MTok in/outAllowed
gpt-4o-realtime-previewchat · 127K ctx · $0.15/$0.6 MTok in/outDenied
gpt-4o-search-previewchat · vision · 127K ctx · $2.5/$10 MTok in/outDenied

…59 models in this catalog · 11 enabled by firm policy

02 · Enforced

The effective policy is one honest list.

25 allowed. 214 denied — each with its reason, per realm. This is what the runtime will actually run, and the list includes your own fine-tuned firm model alongside frontier and local options.

Effective Policy Summary — what the runtime will actually run

✓ Allowed Models (25)

GPT-4.1(openai)

GPT-4o Mini(openai)

Claude Haiku 4.5(anthropic)

Claude Sonnet 5(anthropic)

Grok 4.3(xai)

Llama 3.1 8B(local)

DeepSeek R1 14B(local)

Qwen3 14B(local)

Harborview Firm Model v2(local · fine-tuned)yours

…16 more

⊘ Denied Models (214)

gpt-4o Model denied for realm harborview

o3-deep-research Model denied for realm harborview

mistralai/mixtral-8x22b Model denied for realm harborview

nvidia/cosmos-reason2-8b Model denied for realm harborview

claude-3-5-haiku Model not activated for this realm

moonshotai/kimi-k2-instruct Model denied for realm harborview

…208 more, each with its reason

03 · Keyed

Your keys, your billing relationship.

Bring your own provider credentials, realm-scoped, validated on demand, revocable in one click. Frontier AI under the firm's own accounts — never a black-box pass-through.

Provider Keys — tenant BYOK, realm-scoped
Providers & ModelsProvider KeysFirm PolicyUsage & AccountingIntent Classifier

Tenant provider keys · 2 active

Store realm-scoped provider credentials for tenant BYOK routing.

Anthropic ▾mchen@chenokafor.com••••••••☐ Validate🔑 Save Key
ProviderScopeStatus · KeyActions
Anthropicmchen@chenokafor.com · All provider models
validated 5/23/2026
active · valid
…k4Tz · a41c9e02d7b8
ValidateDelete
OpenAIsmoke credential · All provider models
5/23/2026
disabled
…xxxx · 08f2d1c39aa4
ValidateDelete
xAIfirm API · All provider models
validated 6/12/2026
active · valid
…mQ2w · 5b7e88f01d23
ValidateDelete

04 · Metered

Every token lands on a ledger you can check.

Requests, tokens, cost, and monthly projection — plus provider-side reconciliation that fetches the organization's usage straight from the source, so the firm's ledger can be audited against the provider's.

Usage & Accounting — every token on the ledger
Providers & ModelsProvider KeysFirm PolicyUsage & AccountingIntent Classifier
Provider reconciliation — fetches organization usage directly from the provider, separate from EdgeLex’s local usage ledger. Runs only when you press the button.Fetch provider usage

TOTAL REQUESTS

10,786

INPUT TOKENS

305,944,215

OUTPUT TOKENS

7,698,068

EST. COST

$975.41

PROJECTED MONTHLY

$254.45

Cost by provider · all recorded usage

anthropic2,524 req · 51,054,819 tok · $595.38 · 61%

openai5,402 req · 148,640,487 tok · $275.44 · 28%

zai1,688 req · 64,350,721 tok · $94.82 · 10%

local (firm GPU)950 req · 4,762,581 tok · $0.00 · 0%

05 · Attributed

Cost has a client, a matter, and a feature.

Spend breaks down by credential source, by feature, by user, and by client and matter — flowing through the same expense pipeline as every other cost in the practice. AI time becomes billable truth, not overhead mystery.

Attribution — credential, feature, user, and matter

Cost by credential source

Platform Keys87.2%

Tenant BYOK12.8%

Cost by feature

legal_graph58.1%

lex_chat25.9%

lex_tool15.8%

lex_summarization0.2%

Cost by client / matter

Harborview HOA
Hale v. Northstar Logistics — breach of contract
119 req$9.97
Harborview HOA
Harborview — bylaw revision
110 req$5.90
Delgado Foods, Inc.
In re Delgado — Chapter 11
73 req$3.66

Every run bills to a matter or is absorbed knowingly — the same expense pipeline the rest of the firm uses.

The difference

Policy lives in the database, not the browser.

The runtime checks firm policy before any model call. A client application cannot override it, a clever prompt cannot route around it, and a new model in a vendor catalog arrives disabled until the firm says otherwise. Governance isn’t a settings page — it’s the authority layer everything runs under.

The architecture underneath →

Runtime authority

Checked in the database before every model call — clients cannot override it.

Default-deny

214 models denied with reasons; new catalog arrivals start disabled.

Any model, governed

Frontier under your keys, local on your GPUs, your own fine-tune — one policy.

Capabilities

What it does

Default-deny model governance

Three layers of policy — platform, firm, user — decide which models may run at all. No model runs unless your firm allows it — frontier, local open-source, or the firm's own fine-tuned model, all under the same policy.

The task is classified before the model runs

Each request is classified into a governed task type first, producing a contract for the turn: what evidence is required, which tools are allowed, whether the model may answer at all.

Capability binding

Only the tools a task actually needs are bound for that turn. The model can't call what it was never given.

Typed evidence, not vibes

Every claim's basis is recorded — a rules-engine packet, a document span, an email span, a billing ledger, a court order's own words, an approval artifact — and verified against a typed evidence ledger. Ungrounded legal claims are blocked.

Approval-gated actions

Actions that change the world — send, save, update, delete — require an approval artifact. Proposed and completed actions are never conflated.

Model routing with teeth

A router scores models per task and structurally refuses to let underpowered models perform destructive actions.

Real-time cost accounting, down to the matter

Every request is metered at the runtime with registry rate cards: cost by provider, by model, by user — and by client matter, so AI spend maps to the file and can be billed, absorbed, or examined deliberately. Local models run at zero marginal token cost.

Audit without leakage

Every governance decision is logged in one event taxonomy — and prompts, documents, and privileged content are redacted from the logs themselves.

In your control

Governance is architecture, not policy prose: the deny happens before the model runs, the evidence check happens before the answer renders, and the audit trail is written either way.

See EdgeLex on your own terms.

We'll walk through self-hosting, model control, and your firm's workflows.