Chutes
TEE-only GatewayDecentralized 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.
API Features
OpenAI Compatible ✓
Streaming ✓
Function Calling —
Batch Inference —
Vision —
Embeddings —
Attestation Status
View full details →Last checked: Aug 7, 2026, 11:00 AM
Model coverage: 13/13 current catalog models have an explicit check.
Incomplete evidence Hardware and TCB passed, but one or more later evidence gates are not proven.
0 verified 12 partial 0 failed 1 unavailable
Hardware 1 warning TCB policy 1 warning Freshness 1 warning Channel binding 1 warning Workload identity 13 warning Source provenance 13 warning Request route 13 warning Availability 1 warning
Workload identity not proven 12 Source provenance not proven 12 Request route not proven 12 Endpoint unavailable 1
Deepseek Ai/DeepSeek V3.2 TEE (TEE) Intel TDX Attested E2EE Chutes · corroborated Details Deepseek Ai/DeepSeek V4 Flash 0731 TEE (TEE) Intel TDX Attested E2EE Chutes · corroborated Details Google/gemma 4 31B Turbo TEE (TEE) Intel TDX Attested E2EE Chutes · corroborated Details Moonshotai/Kimi K2.6 TEE (TEE) Intel TDX Attested E2EE Chutes · corroborated Details Moonshotai/Kimi K3 TEE (TEE) Intel TDX Attested E2EE Chutes · corroborated Details Nemotron 3 Nano Omni 30B TEE (TEE) Intel TDX Attested E2EE Chutes · corroborated Details Qwen/Qwen3 235B A22B Thinking 2507 TEE (TEE) Chutes · declared Details Qwen/Qwen3 32B TEE (TEE) Intel TDX Attested E2EE Chutes · corroborated Details Qwen/Qwen3.5 397B A17B TEE (TEE) Intel TDX Attested E2EE Chutes · corroborated Details Qwen/Qwen3.6 27B TEE (TEE) Intel TDX Attested E2EE Chutes · corroborated Details Unsloth/Mistral Nemo Instruct 2407 TEE (TEE) Intel TDX Attested E2EE Chutes · corroborated Details Zai Org/GLM 5.1 TEE (TEE) Intel TDX Attested E2EE Chutes · corroborated Details Zai Org/GLM 5.2 TEE (TEE) Intel TDX Attested E2EE Chutes · corroborated Details
Get notified when this provider's attestation verdict changes:
Alerts RSS
Models & Pricing
| Model | Family | Context | Max Out | Input /M | Output /M | Free | Attestation | Observed route |
|---|---|---|---|---|---|---|---|---|
| Qwen3 32B | Qwen | 40K | 40K | $0.10 | $0.42 | — | partial | Chutes corroborated · route not bound |
| Qwen3.5 397B A17B | Qwen | 256K | 64K | $0.45 | $3.00 | — | partial | Chutes corroborated · route not bound |
| Gemma 4 31B | Google Gemma | 128K | 64K | $0.12 | $0.37 | — | partial | Chutes corroborated · route not bound |
| Kimi K2.6 | Moonshot AI | 256K | 64K | $0.58 | $3.40 | — | partial | Chutes corroborated · route not bound |
| DeepSeek V3.2 | DeepSeek | 128K | 64K | $1.00 | $1.00 | — | partial | Chutes corroborated · route not bound |
| GLM 5.1 | ZhipuAI GLM | 198K | 64K | $0.98 | $3.08 | — | partial | Chutes corroborated · route not bound |
| Qwen3.6 27B | Qwen | 256K | 64K | $0.30 | $2.00 | — | partial | Chutes corroborated · route not bound |
| Kimi K3 | Moonshot AI | 1024K | 64K | $3.00 | $15.00 | — | partial | Chutes corroborated · route not bound |
| DeepSeek V4 Flash 0731 | DeepSeek | 1024K | 128K | $0.14 | $0.28 | — | partial | Chutes corroborated · route not bound |
| Qwen3 235B A22B Thinking | Qwen | 256K | 256K | $0.30 | $1.20 | — | unreachable | Chutes declared · route not bound |
| GLM 5.2 | ZhipuAI GLM | 1024K | 64K | $1.25 | $3.95 | — | partial | Chutes corroborated · route not bound |
| Mistral Nemo 2407 | Mistral | 128K | — | $0.02 | $0.10 | — | partial | Chutes corroborated · route not bound |
| Nemotron 3 Nano Omni 30B | Unknown | 128K | — | $0.02 | $0.10 | — | partial | Chutes corroborated · route not bound |