Aptos
Content is processed only in encrypted TEE memory and is not logged. GPU memory is protected by hardware isolation, not encryption; NVLink traffic is unencrypted. This route does not support Private Mode.
Privacy can differ by model. See each model’s label.
Models served by Aptos
No models from Aptos are available right now.
Prices are per million tokens. TTFT is the observed time to first token. Selectable routes include the applicable provider-selection markup; fixed routes show the standard model price. Availability and pricing refresh continuously; each model page shows the live provider comparison.
Using Aptos via the API
Call a model served by Aptos using its displayed model ID, including the provider suffix when selection is supported.
No Aptos models are currently available for explicit selection, so requests pinning this provider will fail until availability returns.
For models with provider selection, append :aptos to the model ID, set "provider": "aptos" in the request body, or send an X-Provider: aptos header. Explicit provider selection adds a route-specific markup over that provider's base price; the prices in the table above already include it. Models without provider selection use the displayed model ID without a provider suffix or selection surcharge.
See the API documentation for provider preferences, price-aware routing, and error behavior.