Tinfoil

inference provider · 5 models

Access 5 models served through Tinfoil on AnonRouter's privacy-first gateway, including Gemma 4 31B, Llama 3.3 70B, and Kimi K3. Tinfoil serves every route inside a verified AMD SEV-SNP enclave with remote attestation. AnonRouter pins each inference TLS connection to the key carried in the verified hardware report.

Models

Modalities

Text, Embeddings

From (input)

$0.05

per 1M tokens

Max context

262K

Private routes

5 / 5

not anonymous-only

Catalog by modality

5 routes

Text4Embeddings1

Tinfoil models5

Gemma 4 31B

google/gemma-4-31b-instruct

TinfoilTEE

Gemma 4 31B served in a Tinfoil verified confidential enclave.

TEE|262K context|$0.40/M input|$1.00/M output

Llama 3.3 70B

meta-llama/llama-3.3-70b

TinfoilTEE

Llama 3.3 70B served in a Tinfoil verified confidential enclave.

TEE|131K context|$1.75/M input|$2.75/M output

Kimi K3

moonshotai/kimi-k3

TinfoilTEE

Kimi K3 served in a Tinfoil verified confidential enclave.

TEE|262K context|$4.00/M input|$20.00/M output

OpenAI GPT OSS 120B

openai/gpt-oss-120b

TinfoilTEE

OpenAI GPT OSS 120B served in a Tinfoil verified confidential enclave.

TEE|131K context|$0.15/M input|$0.60/M output

Nomic Embed Text

nomic-ai/nomic-embed-text

TinfoilTEE

Nomic Embed Text served in a Tinfoil verified confidential enclave.

TEE|8K context|$0.05/M input|Verify/M output

Provider documentation2 sources

Tinfoil attestation architecture Tinfoil models