Passer au contenu
DeepTokenSuite créative IA
AccueilTableau de bordModèlesInvitesTableau de classementDocumentationTarifsEntreprisesBlog
    Observability

    Observability & Audit

    Per-request logs, provider health, and audit trail for every change

    Inspect latency, success rate, token counts, and provider behavior per request. Every routing, key, and billing change is recorded for compliance and post-mortem.

    Open ObservabilityView Pricing
    Per-request visibilityProvider health boardAuditable change log

    Aperçu des capacités

    real-time

    request log stream

    live

    provider health board

    audit-ready

    change audit trail

    Avantages clés

    Points de valeur clés liés aux workflows de production pratiques.

    Avantage

    01

    Per-request visibility

    Latency, retries, fallback hops, token counts, and error categories are recorded for every request.

    Avantage

    02

    Provider health board

    Track success rate, latency percentiles, and rate limit events per provider over rolling windows.

    Avantage

    03

    Auditable change log

    Routing, key, member, and billing changes are stored in an append-only audit trail with actor and timestamp.

    Workflow recommandé

    Un parcours simple en 3 étapes pour intégrer cette capacité aux appels de passerelle, politiques de routage et contrôles de facturation.

    Étape 1

    Stream request logs

    Open the live log view to follow active traffic and recent errors in real time.

    1

    Étape 2

    Inspect provider health

    Drill into each provider for latency, success rate, and rate limit pressure.

    2

    Étape 3

    Review audit trail

    Filter the audit log by actor, resource, and action to investigate incidents and reconcile changes.

    3

    FAQ

    How long are request logs retained?

    Retention is plan-dependent and ranges from 7 days on Free up to 90 days on Pro. Enterprise plans support longer retention.

    Are request payloads stored?

    Metadata is always stored. Full payload storage is opt-in per organization and respects provider data policies.

    Étape suivante

    Prêt à mettre cette fonctionnalité en production ?

    Commencez depuis la documentation, le catalogue de modèles ou le tableau de bord et validez cette capacité avec du trafic de production réel.

    Open ObservabilityRetour aux fonctionnalités