Contact forms into the void
You should know your message reached someone who can help.
Contact
Talk to a real person
Whether you are sizing a rollout, stuck on an integration or curious about partnering, email our team. We read every message and reply as quickly as we can.
Real people
not a bot queue
One inbox
for every question
Helpful answers
from the team that builds it
The problem
What is slowing you down today
Sales calls for simple questions
Sometimes you just need a straight answer about pricing or limits.
Support that does not know the product
Questions about the API deserve answers from people who know it.
Capabilities
Everything you need, nothing you don't
Sales and enterprise
Rollouts across teams, volumes and account setup.
Developer help
Integration questions, errors and best practices.
Billing
Invoices, payment and your free allowance.
Security
Report a concern or ask about account controls.
Partnerships
Agencies, consultancies and platforms building on AI Inference.
Press and general
Anything else, we are happy to hear from you.
Use cases
What teams run on it
01
Planning a rollout
Tell us about your workloads and we will help you plan.
02
Debugging a request
Include the request id from the response so we can find it.
03
Questions about an invoice
Include the billing period you are asking about.
04
Reporting an issue
Tell us what you saw and when.
How it works
From sign-up to production
- 1
Email our team
Describe what you need, with any request ids or details.
- 2
We reply
A person on our team will get back to you.
- 3
Keep building
Meanwhile, the quickstart and playground are always open.
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 reach you?
Email our team. We read every message.
What should I include for a technical question?
The request id from the response, the HTTP status and the error message if there was one. Never send your API key.
Can I get help without talking to sales?
Absolutely. Ask your question directly and we will answer it.
Is there self-serve documentation?
Yes. Start with the quickstart, API reference and help center.
We would love to hear from you
Email our team, or start building now on the free allowance.