P402
P402.io·Meter
DocsPricingDashboard
> _ AI TOKEN USAGE DASHBOARD

AI token usage
dashboard.

P402 Monitor records every AI call with owner, workflow, model, vendor, tokens, cost, and outcome. The dashboard groups token usage by any dimension.

See dashboardRead docs

Built on the P402 Monitor surface. Parent product page: /monitor.

The problem

Token usage scattered across provider consoles.

Each provider console shows tokens per API key on that provider. Nothing shows tokens per customer, per feature, per workflow, per department across every provider at once. An AI token usage dashboard needs one ledger and one owner taxonomy.

What this dashboard shows
Owner
Customer, feature, workflow, department, employee, or API key.
Workflow
The task or process the call served, tokens rolled up per workflow.
Model
Requested and used. Tokens per model, provider, and version.
Vendor
Share of tokens per vendor, with single-vendor concentration flagged.
Tokens
Input, output, and total token counts, per event and aggregated.
Cost
Direct cost in USD next to token counts. Retry and context waste flagged.
Budget
Budget the event drew from and remaining balance per owner.
Outcome
Accepted, rejected, revised, escalated, or failed, alongside token usage.
Evidence
Receipt and evidence bundle status per event for audit and finance review.
How it works
  1. 01
    Create a P402 key.
    Sign in, generate a key. The key is returned once. P402 stores only a hash.
  2. 02
    Route AI calls through P402 or report meter-only events.
    Use the OpenAI-compatible endpoint, or post metadata-only events from your backend. Both produce token counts in the dashboard.
  3. 03
    Attach owner, workflow, vendor, and customer metadata.
    Events are tagged under the taxonomy your organization already uses. Tokens roll up per owner without rebuilding a billing pipeline.
  4. 04
    Read tokens by any dimension.
    The Monitor surface groups tokens by team, workflow, model, vendor, customer, budget, outcome, and evidence status. Drill from a roll-up into the underlying event.
Privacy

Meter economics, not content.

The token usage dashboard reads token counts, owners, models, and outcomes. Prompt and response storage are off by default. Privacy modes are selectable per workflow.

  • metadata_onlyOwner, cost, tokens, budget, policy, outcome, and evidence status. No prompts. No responses. Default.
  • fingerprint_onlyAdds a hash fingerprint of prompt and response for dedup and replay protection. Content stays out.
  • redacted_tracePrompt and response retained after a redaction pass for fields the tenant policy allows.
  • private_gatewayYour environment hosts the inference, P402 records the economic event over a signed channel.
  • full_traceOpt-in. Prompts and responses retained verbatim with the event. Requires explicit tenant policy.
Read the trust posture
Proof

Same metering layer, four shipped workflows.

Each vertical demo is a working surface on the same metering layer. Use them to see how tokens roll up under owner, workflow, model, and outcome against a concrete workflow.

Healthcare
Medicaid prior authorization with HIPAA-aligned demo mode and human review gate.
Legal
M&A contract due diligence across an 8-document synthetic data room.
Real estate
Tenant application screening with fraud scoring and HUD fair-housing audit trail.
Enterprise
Department, employee, model, and workflow attribution across one organization.
For developers

Know tokens per feature without rebuilding billing.

Wrap AI calls once. The dashboard groups tokens by customer, feature, workflow, model, and outcome. Retry waste and context waste are flagged so engineering can act on real numbers.

Start free
For enterprise

Token usage rolled up for finance.

Tokens and cost grouped by department, employee, vendor, and budget at event time. Outcome and evidence status attached. Finance, engineering, and audit read the same record.

Run AI Spend Audit
FAQ
What dimensions does the AI token usage dashboard group by?+

Owner (customer, feature, department, employee, API key), workflow, model, vendor, budget, policy result, outcome, and evidence status. Token usage is recorded per event and rolled up under any of these dimensions.

Does the dashboard require storing prompts?+

No. Default privacy mode is metadata-only. The dashboard reads owner, model, tokens, cost, budget, policy result, outcome, and evidence status. Prompt and response content stay out unless tenant policy opts in.

Which providers feed the dashboard?+

OpenAI, Anthropic, Gemini, Bedrock, OpenRouter, and any HTTP-callable model. Calls routed through P402 and calls reported as meter-only events from your backend both land in the same ledger.

How does this differ from a provider-side usage dashboard?+

Provider dashboards show usage per API key on that provider. The P402 token usage dashboard shows tokens across every provider under one owner taxonomy, with budget, policy result, outcome, and evidence already attached.

What is the first integration step?+

Create a P402 key, then either route an existing OpenAI-compatible request through P402 or send a meter-only event from your backend. The first event lands in the ledger and the token usage dashboard renders with real data.

Can engineers and finance read the same dashboard?+

Yes. Engineering reads tokens by feature, workflow, and model. Finance reads tokens and cost by department, employee, vendor, and budget. The same metering events drive both views.

Get started

One ledger for every token your organization spends.

Start with the Monitor surface, or sign in to send the first metered event. Tokens roll up under any owner you supply.

See monitorSign in