Unified telemetry
Metrics, logs and traces for every workload, correlated automatically.
Platform · Observability
See everything. Fix anything faster.
Metrics, logs, traces, CPU and GPU telemetry and spend in one place, with anomaly detection and an AI copilot that explains what changed and why.
$600 in launch credit + 20M free inference tokens. No commitment.
Engineered for
- 13 global regions
- CPU & GPU compute
- Self-healing orchestration
- Zero-trust security
- OpenAI-compatible API
- Sovereign & air-gapped options
Observability
Why teams choose it.
Metrics, logs, traces, CPU and GPU telemetry and spend in one place, with AI-powered anomaly detection.
Anomaly detection
Catch regressions in latency, errors and utilization before users do.
Cost clarity
See spend by project, workload and key, down to the second.
Capabilities
One pane of glass for your entire AI estate.
Every capability is available through the dashboard, the API and the AI ops copilot.
CPU and GPU telemetry
Utilization, memory and throughput for every CPU instance, plus temperature for every accelerator, so you can right-size workloads and never pay for idle silicon.
Centralized logs
Search logs across every service and region.
Distributed traces
Follow requests across services and models.
Smart alerts
Alert on symptoms, not noise, with routing to your tools.
Spend analytics
Per-second cost attribution by project and key.
Copilot explanations
Ask why latency spiked or spend jumped, and get an answer with the evidence attached.
- Telemetry
- Real-time
- Metering granularity
- 1s
- Regions in one view
- 13
- Anomaly detection
- 24/7
Figures describe platform capabilities and service-level targets. Contracted commitments are set out in our Service Level Agreement.
Global cloud fabric
Observability, everywhere you operate.
Available across 13 regions on six continents, connected by a private, encrypted fabric with automatic failover and per-region data residency.
- US East · Ashburn
- US West · Hillsboro
- Canada Central · Montréal
- South America · São Paulo
- EU West · Dublin
- EU Central · Frankfurt
- EU North · Stockholm
- Middle East · Dubai
- Africa South · Johannesburg
- Asia South · Mumbai
- Asia Southeast · Singapore
- Asia Northeast · Tokyo
- Australia East · Sydney
Use cases
What teams build with Observability.
Starting points that deliver value in days.
Inference performance
Track latency and throughput per model and endpoint.
Compute utilization
Find idle CPU instances and accelerators, and right-size every workload.
Cost optimization
Attribute spend and spot waste instantly.
Incident response
Correlate signals to find root causes faster.
Per-tenant analytics
Understand usage by customer for SaaS products.
Compliance evidence
Retain and export logs for audits.
Security & compliance
Secure at every layer.
Zero-trust access, encryption everywhere and immutable audit trails are standard on every product, on every plan.
- Telemetry is access-controlled per project and retained according to your policies.
- Encryption at rest and in transit, with customer-managed keys available.
- SSO, role-based access control and scoped API keys.
- Your data is never used to train shared models.
- Built to align with SOC 2, ISO 27001, HIPAA and FedRAMP-moderate control frameworks.
Zero-trust by default
Every request authenticated, authorised and encrypted.
Built to align with control frameworks
- SOC 2
- ISO 27001
- HIPAA
- GDPR
- FedRAMP Moderate
- PCI DSS
AES-256
at rest
TLS 1.3
in transit
Immutable
audit trail
FAQ
Frequently asked questions
Straight answers from the team that runs the fabric. Still curious? Our architects reply fast.
Is observability included?
Core metrics, logs and spend analytics are included for every workload. Extended retention is available on Scale and Sovereign plans.
Can I export telemetry to my existing tools?
Yes. Export metrics and logs through standard formats and APIs.
How does anomaly detection work for me?
It learns the normal behavior of your workloads and alerts you when something meaningfully changes.
Can I see cost in real time?
Yes. Spend updates continuously with per-second metering, and invoices are invoiced every 30 days.
Know more. Guess less.
Start with $600 in launch credit and 20M free inference tokens, double the typical big-cloud free trial. No commitment, live in minutes.
Double the typical big-cloud free trial · Per-second metering · Live in minutes