All Providers

Chutes

TEE-only Gateway

Decentralized confidential inference on Bittensor with TEE

Chutes is a decentralized AI compute marketplace built on the Bittensor network. TEE-tagged models run inside AMD SEV-SNP and Intel TDX enclaves, providing verifiable privacy on community-run hardware. Offers the widest selection of open-source models with hardware-attested confidentiality.

Models 12
From $0.02/M input tokens
Trust Tier TEE-only Gateway

API Features

OpenAI Compatible
Streaming
Function Calling
Batch Inference
Vision
Embeddings

Models & Pricing

Model Family Context Max Out Input /M Output /M Free
Qwen3 32B Qwen 40K 40K $0.10 $0.42
Gemma 4 31B Google Gemma 128K 64K $0.15 $0.42
GLM 5.1 ZhipuAI GLM 198K 64K $1.20 $4.00
Kimi K2.5 Moonshot AI 256K 64K $0.44 $2.00
Qwen3.5 397B A17B Qwen 256K 64K $0.45 $3.00
DeepSeek V3.2 DeepSeek 128K 64K $0.28 $0.42
GLM 5 ZhipuAI GLM 198K 64K $0.95 $2.55
MiniMax M2.5 MiniMax 192K 64K $0.15 $1.20
Kimi K2.6 Moonshot AI 256K 64K $0.74 $3.50
Qwen3.6 27B Qwen 256K 64K $0.30 $2.00
Qwen3 235B A22B Thinking Qwen 256K 256K $0.30 $1.20
Mistral Nemo 2407 Mistral 128K $0.02 $0.10