Organization-Wide Analytics
Every project, every member, one page
Per-project analytics answers "where did this project's spend go?" — Organization Analytics does the rollup for the whole org. One page totals cost, requests, and tokens across every project for any date range, and a single group-by control pivots the cost-over-time and ranking charts by canonical model, project, or API key. Enterprise organizations also get usage broken down by person: a per-member table sorted by spend, and a detail view per member with summary cards, their top model, provider, and app, and cost-by-model breakdowns. Usage is attributed by who created each API key, every chart respects the shared date-range picker, and daily buckets follow your own timezone rather than UTC midnight. It all reads from the same pre-aggregated hourly rollups the rest of the dashboard uses — no scans over raw request logs — so it stays fast on windows up to a year.
In the dashboard
The real UI, with sample data
The same components your team gets in the dashboard — switch the Cost / Requests / Tokens tabs below. Numbers are illustrative.
Total spend
$7,828.80
Requests
3,288,112
Tokens
1,017,747,604
Why teams turn it on
Org-wide rollups
Spend, requests, and tokens totaled across every project in the organization — no more opening projects one by one and adding the numbers up yourself.
Pivot three ways
Group the same charts by canonical model, project, or API key, each with Cost / Requests / Tokens tabs on the shared date-range picker.
Per-member attribution
See cost, tokens, requests, error rate, and key count per person, with a detail view of their top models, providers, and apps. Spend lands on whoever owns the key.
Fast on any window
Reads pre-aggregated hourly rollups instead of raw request logs, and buckets days in your own timezone — charts line up with your wall clock.
How it works
From decision to deployed in three short steps
- 01
Open Organization → Analytics
Summary cards total spend, requests, and tokens for the selected range across all projects.
- 02
Pick a breakdown
Switch the group-by between model, project, and API key. Every view keeps the Cost / Requests / Tokens tabs.
- 03
Drill into people and keys
Open the Members table for per-person spend, or any API key's statistics page for cost, tokens, requests, and error rate scoped to that key.
bash
Daily series with a project breakdown
GET /analytics/activity?organizationId=org_123\
&groupBy=project\
&from=2026-06-01&to=2026-06-30\
&timezone=Europe/ParisReal-world use cases
Why customers actually adopt this
Which team drives the bill
Group by project to see which team or workload is behind this month's invoice — before finance asks.
Chargeback and showback
Attribute spend to members and API keys for internal cost allocation, straight from the dashboard or the API.
Spotting expensive outliers
Rank models by cost across the whole org to catch the experiment quietly burning budget on a frontier model.
Frequently asked
- Who can access organization analytics?
- Organization owners and admins on the Enterprise plan. Non-enterprise orgs see an upgrade card, and enterprise-gated entries are marked in the sidebar so members can tell before clicking through.
- How is member usage attributed?
- By who created each API key — spend lands on the member who owns the key. Member analytics are exposed through GET /analytics/members and GET /analytics/members/{userId}.
- Does it scan my request logs?
- No. The page reads the same pre-aggregated hourly rollups the rest of the dashboard uses, so it stays fast across any range up to a year. Every analytics endpoint also accepts an IANA timezone parameter so daily buckets follow your local day.
More enterprise capabilities
The rest of the enterprise stack
Per-Member Budgets & Developer Role
Per-member spend caps enforced at request time, org-wide default developer limits, and a project-scoped Developer role. An over-budget request is rejected before it ever reaches a provider.
Enterprise Audit Logs
Tamper-evident audit trails for SOC 2, HIPAA, ISO 27001, and internal investigations. Every config change, key rotation, and admin action — captured, attributed, exportable.
Per-Project Routing Overrides
Override global routing rules at the project level — region, provider order, fallback chain, and cost ceilings. Production stays pinned; experimental teams stay flexible.
Enterprise Guardrails
Server-side detection for prompt injection, PII, secrets, and policy violations. Configured centrally, enforced at the gateway, auditable per-request.
Discord & Slack Alerts
Native webhook integrations for Discord and Slack. Get the enterprise contact-sales form, billing events, guardrail trips, and SLA breaches in the channels your team already monitors.
Single Sign-On (SAML / OIDC)
SAML 2.0 and OIDC SSO with SCIM provisioning, group-based role mapping, and enforced-only access. No local credentials, no shared passkeys, no off-boarding gaps.
White-Label Chat & Playground
Embed or stand up a fully white-labeled chat app and playground under your own domain. Customize branding, default models, system prompts, and feature toggles.
Provider Compliance Policies
Define the certifications and data policies your providers must meet — SOC 2, ISO 27001, GDPR, no prompt training, no prompt logging — and the gateway refuses to route to anything that doesn't qualify.
See organization-wide analytics on your real workloads
Bring a sample workload to a 30-minute call. We'll wire it up live and show you the actual experience your team will get.