InferenceAbout made. ↗
An open resource by made.

Australian inference.
The details matter.

Find LLM APIs for Australian workloads. Compare where inference runs, how you pay, and what the evidence actually says.

7service profiles
5major platforms
2smaller providers under review
Initial research · 09 Nov 2026

Explore the directory

Suggest an update ↗
Research preview. These are service profiles, not verified model configurations. Exact model availability, prices and contractual conditions are still being reviewed. See coverage progress.
7 service profiles

Azure

Service profile
Foundry · Standard

Model/version selection pending

Configuration dependent

Geography-based processing with usage billing. The exact model and deployment type matter.

Watch for: An Australian resource using Global Standard or an APAC Data Zone is not an Australia-only configuration.

Pay per token

DocumentationRead profile & sources →

AWS

Service profile
Bedrock · on-demand

Model/profile selection pending

Configuration dependent

Model access through Bedrock, with processing boundaries that depend on the invocation route.

Watch for: An Australian source region does not prove Australian inference. Inspect every destination in the selected inference profile.

On-demand usage

DocumentationRead profile & sources →

Google Cloud

Service profile
Managed generative AI APIs

Model/endpoint selection pending

AU processing unverified

Evaluate the model’s processing commitment separately from its endpoint location.

Watch for: A regional endpoint alone does not guarantee in-region ML processing.

Model-specific; pricing review pending

DocumentationRead profile & sources →

OpenAI

Service profile
API · Australian data residency

Eligible models and endpoints only

May process offshore

Australian storage for eligible API projects, without an Australian inference processing guarantee.

Watch for: Australian storage is not Australian inference. The documented Australian region does not support regional processing.

Usage billing; residency pricing conditions apply

DocumentationRead profile & sources →

Databricks

Service profile
Foundation Model APIs

Model/workspace selection pending

Configuration dependent

Managed model APIs with processing rules that depend on the model and workspace.

Watch for: An Australian workspace does not establish an Australia-only processing boundary.

Pay-per-token option

DocumentationRead profile & sources →

ToothFairyAI

Service profile
Sovereign LLM API · AU

AU catalogue verification pending

AU processing unverified

A smaller provider advertising Australian regional inference and OpenAI-compatible APIs.

Watch for: Australian processing and zero retention are provider claims; contractual scope and routing remain to be verified.

Published per-token rates advertised

Provider claimRead profile & sources →

Xinference

Service profile
Model API · Australia

Hosted catalogue verification pending

AU processing unverified

A hosted model API advertised as running in Australian data centres.

Watch for: The shared Model API must be reviewed separately from dedicated and self-hosted offerings.

Pay per token advertised

Provider claimRead profile & sources →

Understand the trade-offs

All guides →