Skip to content
Sign inRequest access

Products

GPU CloudAMD MI325X and NVIDIA H200 by the hour or on reservation.
Dedicated ClustersPreviewPrivate, interconnected GPU clusters for sustained workloads.
SandboxesPreviewIsolated, short-lived environments for developers and AI agents.
Serverless GPUPreviewGPU containers that scale with requests, down to zero.
Serverless InferenceOpen models behind one OpenAI-compatible endpoint.
Dedicated EndpointsReserved serving capacity for one model, billed per GPU-hour.
PlaygroundSend a prompt to any model your workspace can reach.
Model DeploymentsPreviewImmutable deployments with instant promote and rollback.
Fine-tuningLoRA fine-tunes on the open models in our catalog.
Model TrainingPreviewFoundation-model training runs, managed end to end.
EvaluationsPreviewBenchmark suites and model comparisons you can rerun.
DatasetsManaged and synthetic training data, versioned and ready to use.
Data ManagementPreviewDatasets, connections and storage, with lineage across the platform.
PipelinesPreviewVersioned DAGs that automate data, training and deployment.
Data RoomsPreviewSecure document sharing with guests, NDAs and an audit trail.
NokuvaPreviewThe AI-native design editor.
TavocPreviewA Rust-native code platform: IDE and desktop apps.
FoltracComing soonMulti-cloud deployment with autonomous operations.
W0rkTreeComing soonVersion control for agent fleets.
Identity & AccessMembers, roles, policies, SSO and audit for every workspace.
Billing & CostUsage, invoices, credits and budgets in one place.
Logs & MonitoringRequest logs, latency and error rates across services.
Project CanvasPreviewSee and change a project's resources on one live canvas.

Pages

Home/
Platform/platform
All products/products
Pricing/pricing
GPU pricing/pricing#compute
Inference services/services/inference
Model training services/services/model-training
Protocol design/services/protocol-design
Research partnerships/services/research-partnerships
Protocols/protocols
Datasets/datasets
Documentationdocs.legionedge.ai
Changelog/changelog
News/news
Research/research
Blog/blog
Articles/articles
Events/events
Startup Program/programs/startup
Ambassador Program/programs/ambassador
Partner Program/programs/partner
Event Program/programs/events
Company/company
Careers/careers
Partners/partners
Contact/contact
Statusstatus.legionedge.ai
Terms of Service/legal/terms
Privacy Policy/legal/privacy

Logs & Monitoring

Available

When an endpoint misbehaves, see why.

Every inference request, training job and endpoint event in one searchable log, with dashboards for latency, tokens and errors.

Request accessView pricing
Pricing
Included
Layer
Management & governance
Collects from
Serverless inference, Dedicated endpoints, Model deployments, Training jobs, GPU instances

Why Logs & Monitoring

Built into the request path, not bolted on.

Every inference request, training job and endpoint event lands in one searchable log. Tokens, latency and errors are recorded as requests are served, with log streams and traces at the endpoint level and dashboards across services.

  • Request logs

    Every call with its model, status, key, latency and tokens. Filter by any of them, or switch on live tail.

  • Dashboards

    Latency, throughput and error rates across services, broken down by deployment, region and key.

  • Limits & quotas

    See the limits on your workspace and how close you are to each, and ask to raise one before you reach it.

How it works

Request logs, latency and error rates across services.

  1. Requests are logged

    Each call records its model, status, key, latency and tokens as it is served. There is nothing to install.

  2. Search and filter

    Narrow the log by model, status, key and latency, or follow requests as they arrive with live tail.

  3. Read the dashboards

    Watch latency percentiles, time to first token, tokens and error rates, by deployment, region and key.

  4. Stay inside your limits

    See IAM limits, compute quotas and API quotas side by side, and request more before a limit stops you.

In the console

Everything in one place.

Logs & Monitoring lives in the LegionEdge cloud console, next to every other service in the workspace, under one account and one identity.

  • Request logs

    Every request is inspectable, from the list to the detail.

    • Sampled, searchable logs with live tail
    • Log streams and traces per endpoint
    • Prompt and response logging off by default

  • Dashboards

    Time series for the numbers that tell you whether a model is healthy.

    • Latency percentiles and time to first token
    • Tokens in and out, and errors by code
    • Broken down by deployment, region and key

  • Alerts and uptime

    Monitoring for the services you run, next to their metrics and logs.

    • Alerts
    • Uptime
    • Service level objectives

  • Limits & quotas

    Every limit on your workspace, in one place.

    • IAM limits, compute quotas and API quotas
    • Usage shown against each limit
    • Request an increase from the same page

Pricing

Included

Logs & Monitoring is included in every workspace, on every plan.

Full pricing
  • Prompts and responses are kept only when you turn payload logging on for a project, with a retention setting.

Related products

Pairs well with Logs & Monitoring

Get started

Start with a workload.

Connect to the platform directly, or work with our team on a specific technical challenge.

Self-service

LegionEdge Cloud

Create a workspace, explore the available models, and connect your application. The documentation takes you through your first request.

  • Turn on only the services you need
  • Pay per token or per GPU-hour
  • One account, one bill
Create a workspaceRead the docs

Custom engagements

Work with our team

Bring your data requirements, model goals, or infrastructure constraints. We'll define the scope, deliverables, and next steps together.

  • Scoped with an evaluation baseline
  • Dedicated clusters and reserved GPUs
  • A named engineer from day one
Discuss your projectsales@legionedge.ai