Llama 3.3 70B served inside a Tinfoil verified confidential-compute enclave.
Modalities
In / out price
$0.20 / $0.60
per 1M
Context
131K
Max output
16K
Released
–
Updated
Aug 13, 2026
Providers
1 routeThe same model can have different pricing and privacy guarantees depending on who serves it. The model's headline privacy uses the strongest available route below.
| Provider | Privacy | Input / 1M | Output / 1M | Cache read / 1M | Context | Max output | Uptime | Latency | Throughput |
|---|---|---|---|---|---|---|---|---|---|
| TEE | $0.20 | $0.60 | — | 131K | 16K | — | — | — |
Privacy
3 / 4Hardware-isolated routing
TEE tier
- Anonymous
- Private
- TEE
- E2EE
Inference runs inside a hardware-isolated, attestable environment. TEE protects processing, but does not by itself mean the client encrypted the request end to end.
Features
3Streaming
Tool calling
JSON/schema