Azure OpenAI · Model provider
Can we use Azure OpenAI models and still control keys, cost and what is sent?
Yes. You add your Azure OpenAI resource to the Katonic AI Gateway, and agents call its models through the gateway. The model runs in your own Azure subscription, and prompts and responses go to that resource. The gateway holds the key, decides which teams may call which model, applies rate limits and budgets, checks each turn against your guardrail profile and records usage and cost.
Where the model runs.
In your cloud account.
How it is connected
- 01Your Azure OpenAI resource name. The address is built from it.
- 02An API key, sent in Azure's api-key header.
- 03The deployment and API version for a model.
In your own Azure subscription, in the region of your Azure OpenAI resource.
What leaves your environment
The prompt and the response.The prompt and the response go to your Azure OpenAI resource. Katonic controls which teams and models may do that, checks the turn against your guardrail profile and records it. In an install flagged as air-gapped, hosted providers start disabled.
Keys
Your key is kept encrypted and decrypted only for the call. It is not stored or cached in plain text.
Model access
A policy for each tenant and an entitlement for each team decide which models may be called.
Rate limits
Requests and tokens per minute, for each user, tenant and model.
Budgets
Checked before the call, at three levels: warn, soft and hard. A hard budget blocks the call.
Guardrails
The input and output of a chat turn are checked against your guardrail profile.
Failover
Health is tracked for each provider and model, with a circuit breaker. A call can move to the next member of its tier.
Cost and usage
Each call is priced when it is recorded, and usage and cost can be queried.
Who paid
Each usage record says whose credential paid for the call.
Air gap
In an install flagged as air-gapped, hosted providers start disabled.
A model you serve on your own GPUs keeps the prompt and the response on your infrastructure. The gateway does the same work in front of it.
Where do prompts go?
To your Azure OpenAI resource, in your Azure subscription. They do not go to Katonic.
Who holds the Azure key?
You do. It is kept encrypted in your Katonic install and decrypted only for the call.
Can we block it for some teams?
Yes. A policy for each tenant and an entitlement for each team decide which models may be called.