AI platform teams
Give every team models, without building the plumbing
Offer one endpoint to every product team. UnitVane AI routes their requests across providers, keeps each team within its budget and rate limit, and reports what every app spends per 1M tokens.
What UnitVane brings to this job
Every model request routed, metered and kept within budget
LLM gateway
An OpenAI-compatible endpoint in front of Azure OpenAI, Amazon Bedrock, Google Vertex AI, OpenAI and Anthropic. Routing, fallback, PTU-first spillover, team keys, budgets and per-request cost, without running any of it yourself.
Explore LLM gatewayProvisioned throughput sized from what you use each minute
Provisioned capacity
Size Azure OpenAI PTUs, Bedrock provisioned throughput and Vertex AI provisioned throughput from per-minute telemetry, see reservation coverage by pool, and approve purchases and renewals before they happen.
Explore Provisioned capacityWhat a million tokens really costs you, by model and team
Tokenomics
Billing joined to token telemetry for every deployment: input, output and cached tokens, PayGo, PTU and reservation cost, and an all-in cost per 1M tokens that you can compare across models and clouds.
Explore TokenomicsThe problem
Why it is hard today
One gateway and one cost model for every model your teams call
Every team wires its own client:
Retries, fallback and keys are rebuilt in each service, each slightly differently.Capacity is bought blind:
PTU and provisioned throughput are sized from guesses, then sit idle or throttle.Nobody sees cost per app:
The bill shows deployments; product managers want to know what their feature costs.
How UnitVane handles it
What you get
Managed routing
PTU first, spillover, fallback, all in route configuration.
Team keys
Routes, budgets and rate limits per team or app.
Capacity sizing
Provisioned throughput sized from per-minute use.
Cost per 1M tokens
Per app, model and cloud, including commitments.
Email, phone and card masking
Email addresses, phone numbers and card numbers masked before a provider sees them.
Every provider
Azure OpenAI, Bedrock, Vertex AI, OpenAI and Anthropic.
Outcomes
What changes for your team
A platform, not a library
Teams call one endpoint; routing changes never need an app deploy.
Capacity you can defend
Each PTU purchase comes with the utilization that justifies it.
Your first weeks
What you see, and when
From the first provider connection to capacity you can size and commit.
01
When you connect a provider
Billing and token telemetry are read for each deployment, read-only. Effective cost per 1M tokens appears for every period whose billing has arrived, with nothing routed through the gateway.02
From the first gateway request
Each routed request is metered as it is served: tokens, route, target, latency and cost, attributed to the team key that sent it.03
After 7 days of utilization
Provisioned deployments have enough per-minute data to be sized to the percentile you choose.04
After 14 days
Deployments count toward reservation coverage, so over-reserved and uncovered capacity are reported per pool.
UnitVane works with your technology
Every major cloud, any Kubernetes, and the tools and model providers your teams already use.
Clouds and Kubernetes: AWS, Microsoft Azure, Google Cloud, Oracle Cloud, Kubernetes, Red Hat OpenShift, Rancher, VMware Tanzu, k3s
Your tools and model providers: Helm, Terraform, Argo CD, Flux, Prometheus, OpenTelemetry, Okta, Slack, Microsoft Teams, OpenAI, Anthropic, Mistral AI
Your questions answered
Keep reading
Expert guides and related solutions
See your AI spend per team, model and request
A 30-minute walkthrough on your own Azure OpenAI, Bedrock or Vertex AI usage.