UnitVane AI
Know what every model call costs, and route it well
UnitVane AI measures cost per 1M tokens across every provider, sizes your provisioned throughput, and runs a managed LLM gateway so your teams do not have to build routing, fallback or budgets themselves.
The economics of AI, in one place
Every executive now asks which models the company uses, on whose infrastructure and at what cost. UnitVane AI answers with one cost model across providers, and one gateway that routes, meters and limits every call.
From your app to a cost per 1M tokens
Your apps and teams
- Your applicationsOne OpenAI-compatible endpoint
- Team keysAllowed models and a monthly budget
Provider billingRead-only cost and token metrics
UnitVane AI
Routes, meters and limits every call
- 1Check the key and budget
- 2Route to the right model
- 3Fall back if a model fails
- 4Record tokens and cost
What you get
Your model providersBilled to you directly- Smaller model when it fitsWith what the largest would have cost
- Budgets that stop callsPer team, per month
- Cost per 1M tokensComparable across every provider
The problem
AI spend grows faster than anyone can explain it
The bill stops at the deployment
Invoices show a cost per deployment or model, not which product, team or customer spent it.
Three ways to pay for one model
Pay-as-you-go, PTU by the hour and reservations land in different meters, and some are recorded in the wrong one.
Provisioned capacity sits idle
PTUs are paid every hour, while traffic still goes to pay-as-you-go because nothing routes it.
Every team builds its own client
Retries, fallback, keys and rate limits are reimplemented in each service, and none of them know the budget.
Two ways to start
Read-only on day one, the gateway when you are ready
Read-only
Connect billing and telemetry. Nothing in your traffic changes.
- Cost, tokens and requests per deployment
- PTU sizing and reservation coverage
- Budgets and alerts by product, team and tenant
Through the gateway
Change the base URL. UnitVane AI routes and meters every request.
- Exact tokens and cost per request, key and route
- PTU-first spillover and fallback across providers
- Budgets that stop at 100%, rate limits, cache, and redaction of emails, phone and card numbers
UnitVane AI modules
One portfolio, every layer of AI cost
Four areas, one AI cost model
One endpoint that routes, meters and controls every model call
Effective cost per 1M tokens by model, team and cloud
PTU and provisioned throughput sized from per-minute usage
Budgets, alerts, chargeback and reports for AI spend
LLM gateway
Change one URL and stop managing routing
Apps call a route such as chat-default. The gateway sends it to your PTU deployment until it is busy, spills over to pay-as-you-go, falls back to another provider when one throttles, and records the cost of every request against the team's key.
- OpenAI and Anthropic compatible
- Budgets and rate limits per key
- Fully managed by UnitVane
import osfrom openai import OpenAIclient = OpenAI( base_url="https://gateway.unitvane.com/v1", api_key=os.environ["KUBEON_AI_KEY"], # a team key, not a provider key)resp = client.chat.completions.create( model="chat-default", # a route name, not a vendor model messages=[{"role": "user", "content": "Summarize this ticket in two lines."}],)print(resp.choices[0].message.content)Tokenomics
Cost per 1M tokens that includes your commitments
PTU hours and reservations are allocated to the deployments and models that used them, so pay-as-you-go and provisioned capacity can be compared on the same number, by model, team and cloud.
- Input, output and cached tokens
- Past PTU billing corrected in place
- Model-mix savings from observed cost
Providers
Every model provider your teams use
Hosted APIs, cloud model platforms and models you run yourself, in one cost model.
- Azure OpenAI
- Azure AI Foundry
- Amazon Bedrock
- Amazon SageMaker
- Google Vertex AI
- OpenAI API
- Anthropic API
- Mistral
- Self-hosted models on your GPUs
Data handling
What the gateway sees, and what it keeps
No prompt logging by default
Bodies are read in memory to route each request. Only metadata is recorded unless you turn logging on for a route.
Email, phone and card masking
Email addresses, phone numbers and card numbers masked before a request leaves the gateway. Names and free text are not detected.
Your provider credentials
Stored encrypted and used only to call your provider. Never in app code.
Region pinning
Routes, fallback included, can be held to the regions you choose for data residency.
Why AI spend needs an owner
UnitVane AI: your questions answered
The UnitVane platform
Learn more about UnitVane AI
See your AI spend per team, model and request.
A 30-minute walkthrough on your own Azure OpenAI, Bedrock or Vertex AI usage.