A new stack per client
Every engagement should not start with a fresh model integration.
Partners
Build with us, grow with us
Agencies, consultancies and software platforms use one endpoint to deliver AI features to their own clients. If that sounds like you, our team would love to talk.
One integration
for every client project
Clear unit cost
price on every call
Direct line
to our team
The problem
What is slowing you down today
Costs you cannot quote
Clients want a fixed proposal. You need a predictable unit cost.
No one to call
When a client project matters, you want a real conversation, not a ticket queue.
Capabilities
Everything you need, nothing you don't
One endpoint for every project
Reuse your integration across clients and use cases.
Separate keys per client
Create a key per client project and revoke any one independently.
Per-call pricing
Tokens and price on every response make it easy to estimate and report costs.
Capability routing
Deliver chat, code, vision and reasoning features without separate integrations.
Resilience built in
Automatic fail-over keeps client features running.
A console to show clients
Playground and usage dashboards make demos and reviews easy.
Use cases
What teams run on it
01
Digital agencies
AI features for client websites and apps.
02
Consultancies
Automation projects built on a reliable endpoint.
03
Software platforms
AI features embedded in your own product.
04
Systems integrators
Inference wired into client workflows and tools.
How it works
From sign-up to production
- 1
Email our team
Tell us about your clients and what you build.
- 2
Prototype together
Build a first project on the free allowance.
- 3
Grow the relationship
Expand as your client work grows.
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
How do I become a partner?
Email our team with a short description of your business and the projects you have in mind.
Can I use one account for several clients?
Yes. Create a separate key for each client project so you can revoke them independently.
Can my clients see the console?
Your account and console are yours. Share results and usage with clients as you see fit.
Is there a cost to start?
No. Every account includes a free monthly token allowance.
Let's build for your clients together
Email our team and tell us what you are working on.