Every team buys its own AI
Duplicate contracts, duplicate integrations and no shared view of cost.
Enterprise
Inference for every team, governed from one place
Give every product team, business unit and internal tool access to the whole model catalog through one endpoint, with keys, limits, history and spend you can see.
One front door
for every team's AI usage
Price per call
easy to allocate across teams
Built-in resilience
routing and fail-over
The problem
What is slowing you down today
Governance after the fact
Security finds out about a new AI tool when it is already in production.
Fragile integrations
Each team hard-codes a model and handles failure differently.
Capabilities
Everything you need, nothing you don't
Named keys per team
Give every team or service its own key and revoke any one without touching the others.
Rate limits
Requests-per-minute ceilings protect budgets and shared capacity.
Request history
A record of every call with model, tokens, latency and price.
Capability routing
Teams ask for what they need and get the lowest-priced enabled fit.
Automatic fail-over
Busy models do not become outages for your users.
Clear pricing
Per-token prices listed per model, with exact price on every response.
Use cases
What teams run on it
01
Internal AI platform
One endpoint every team builds on.
02
Customer-facing features
Resilient AI features across product lines.
03
Shared services
Document processing for finance, HR and operations.
04
Developer productivity
Code-capable models for internal tools.
How it works
From sign-up to production
- 1
Talk to our team
Tell us about your teams, workloads and volumes.
- 2
Pilot with one team
Start on the free allowance with named keys.
- 3
Expand with visibility
Add teams and track usage in the dashboards.
Control
Built so you stay in charge
Keys you control
API keys are shown once at creation and stored only as a hash. Revoke any key instantly from Settings.
Spend you can see
Every request carries its own receipt: tokens in, tokens out, latency and price. Nothing is billed that you cannot trace.
Limits you set
Per-account rate limits and a free monthly allowance keep experiments safe before they become production.
Data you decide on
You choose exactly what you send. Repeat prompts can be served from your cache, and cache hits are never billed.
For developers
One endpoint. Every model.
Send a prompt and a capability, or name a model. One bearer key, one small JSON body, and a full receipt on every response.
curl https://YOUR-DOMAIN/api/ainf/inference \
-H "Authorization: Bearer $AI_INFERENCE_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: order-1042" \
-d '{"prompt":"Summarise this ticket in one line","capability":"chat"}'Questions, answered
Can we attribute usage to teams?
Every response returns its tokens and exact price, so each team's integration can log its own spend. Account totals live in the usage dashboard.
Do you support single sign-on?
Contact our team to discuss sign-in options for your organisation.
Can we run it in our own environment?
AI Inference is a hosted service. It is not available as a self-managed deployment.
How do we get started?
Sign up and pilot on the free allowance, or reach our team through the contact page.
Bring every team onto one endpoint
Talk to our team, or start a pilot today.