MODELS & PROVIDERS
Every model. Every provider.
One control plane.
Discover models, manage provider credentials, monitor real-time health and control access across environments — all from a single, unified control plane.
01MODEL CATALOG
A single source of truth
for your model catalog
Explore every model across OpenAI, Anthropic, Google and more. View identity, capabilities, technical metadata, pricing and real-time operational metrics — all in one place.
- Unified model catalog across providers
- Model identity, context window and capabilities
- Pricing, usage and latency metrics
- Governance, access control and routing policies
ModelsLIVE
GPT-5, Claude, and Gemini usage across OpenAI, Anthropic, and Google.
| MODEL | PROVIDER | REQUESTS | TOKENS | COST | AVG LATENCY | ERROR RATE | USAGE | STATUS |
|---|---|---|---|---|---|---|---|---|
| GPT-5 | OpenAI | 75,627 | 19.8M | $166.44 | 743 ms | 1.6% | 61% | Healthy |
| Claude | Anthropic | 29,755 | 7.8M | $85.48 | 698 ms | 1.5% | 24% | Healthy |
| Gemini | 18,587 | 4.9M | $40.93 | 802 ms | 1.9% | 15% | Healthy |
- Overview
- Usage & Cost
- Models
- Gateways
- Alerts
- Policies
- Teams
- Applications
- Audit Logs
Overview
Healthy
OpenAI61% of requests
Current metrics
Trends
Breakdown
02MODEL INSIGHTS
See the model
beyond the name
Go deeper into each model with detailed insights — usage trends, latency, error rates, pricing, context window, provider health and more.
- Real-time operational metrics
- Pricing breakdown and usage share
- Context window and technical metadata
- Related gateway and provider health
- Access, routing and guardrails at a glance
03PROVIDER HEALTH
Manage provider health
before it becomes an incident
Monitor provider performance across all your models. Track availability, latency, error rates, rate limits and quota utilization — and get ahead of issues before they impact your applications.
- Real-time provider health and availability
- Latency, error rate and rate limit tracking
- Quota and token utilization
- Visual alerts for degraded or unavailable providers
ProvidersLIVE
Monitor provider health and performance across all models.
| PROVIDER | MODELS | REQUESTS | COST | P95 LATENCY | ERROR RATE | HEALTH |
|---|---|---|---|---|---|---|
| OpenAI | 8 | 130,942 | $288.18 | 723 ms | 1.7% | Healthy |
| Anthropic | 8 | 45,210 | $142.36 | 698 ms | 1.5% | Healthy |
| 9 | 28,991 | $93.21 | 812 ms | 1.9% | Degraded | |
| AWS | 6 | 12,431 | $41.12 | 920 ms | 2.6% | Degraded |
| Azure | 4 | 8,221 | $28.40 | 1.2 s | 3.1% | Unhealthy |
04PROVIDER CREDENTIALS
Credentials, controlled
from one plane
Manage provider credentials securely across environments. Use masked keys, rotate credentials, test connections and control access by team, application and environment.
- Secure credential profiles with masked keys
- Environment-based configuration
- Test connection and health checks
- Credential rotation and lifecycle management
- Access control by team and application
sk-••••••••••••••••7F2AValidsk-ant-•••••••••••••1C9DValid••••••••••••••••••9K2LExpiring05INTEGRATIONS
Connect the stack
you already use
Works with your existing gateways and infrastructure. Connect LiteLLM, Portkey, TrueFoundry, OpenRouter or any custom gateway, and manage all your models and providers from one unified control plane.
- Pre-built connectors for major gateways
- Model and provider sync
- Unified monitoring and governance
- Works with self-hosted models and custom endpoints
06GOVERNANCE & CONTROL
From models to policy to production
Model and provider data is deeply integrated with your governance stack — teams, policies, routing, alerts and audit logs — so you stay in control at scale.
- Teams & RBACControl access across environments
- PoliciesDefine guardrails and usage rules
- RoutingRoute requests intelligently
- AlertsSet thresholds and respond faster
- Audit LogsTraceable activity and compliance
Connect the AI infrastructure you already have.
Control it from one place.
Discover, monitor and govern every model and provider — with .