You control which LLM provider families and model IDs are available in your organisation. Fontana ships 600+ supported models across leading providers: frontier chat and reasoning models, open-weight endpoints, and domain-specific hosts, all routed through your approved gateways and BYOK keys (see Gateways). Usage stays aligned with your contracts, compliance posture, and budget because inference never runs through a shared Fontana-operated model account.
A model you have imported into your own AWS account through Bedrock Custom Model Import is listed alongside the standard ones, named Imported: <your model name>. Choose it anywhere a model is chosen. Fontana reads it with your own AWS credentials, so the model and everything sent to it stay in your account.
Imported models show no per-token price, because Bedrock charges for them by the time the model is loaded and by storage rather than by tokens. Your AWS bill is the figure to read.
The list appears once your AWS credentials allow Fontana to read it. If your imported models are missing while the standard models are listed, the credentials are working and the permission to list imported models is not.
If your preferred provider or model is not listed above, or you run internal inference endpoints, contact the Fontana Engineering team. We can add support for custom gateways, private hosts, or enterprise-only model access to match your deployment boundary.
We use essential cookies so this site works. With your agreement we also use optional analytics cookies. That optional use is based on your consent under the GDPR. You can withdraw it in your browser settings or by writing to us.
