Venice.ai
Attested E2EEEnd-to-end encrypted private AI with TEE attestation
Venice.ai is a privacy-first AI platform that combines end-to-end encryption with Trusted Execution Environment attestation. Conversations and model weights are protected through hardware-level confidential computing — Venice cannot access your prompts, and TEE attestation lets you verify this cryptographically. The E2EE private tier covers a curated set of open-source models with per-model pricing.
API Features
OpenAI Compatible ✓
Streaming ✓
Function Calling ✓
Batch Inference —
Vision ✓
Embeddings —
Attestation Status
View full details →Last checked: Aug 26, 2026, 2:00 AM
Model coverage: 13/13 current catalog models have an explicit check.
Explicit trust failures At least one check has an explicit mismatch or policy rejection; other evidence layers may still have passed.
0 verified 5 partial 4 failed 4 unavailable
Hardware 4 warning TCB policy 4 warning Freshness 4 warning Channel binding 4 warning Workload identity 4 bad Source provenance 13 warning Request route 13 warning Availability 4 warning
Workload identity failed 4 Source provenance not proven 9 Request route not proven 9 Endpoint unavailable 4
E2ee Deepseek V4 Flash (TEE) Intel TDX Attested E2EE Phala/dstack · corroborated Details E2ee Gemma 4 26b A4b Uncensored P (TEE) Details E2ee Glm 5 2 P (TEE) Details E2ee Qwen3 6 27b (TEE) Intel TDX Attested E2EE Phala/dstack · corroborated Details E2ee Qwen3 6 35b A3b Uncensored P (TEE) Details Gemma 3 27B (TEE) Intel TDX phala · inferred Details Gemma 4 31B (TEE) Intel TDX Attested E2EE Phala/dstack · corroborated Details GLM 5.1 (TEE) Intel TDX Attested E2EE Phala/dstack · corroborated Details GPT-OSS 120B (TEE) Intel TDX phala · inferred Details GPT-OSS 20B (TEE) Intel TDX phala · inferred Details Qwen 2.5 7B (TEE) Intel TDX phala · inferred Details Qwen3 35B (TEE) Intel TDX Attested E2EE Phala/dstack · corroborated Details Qwen3-VL 30B (TEE) 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 |
|---|---|---|---|---|---|---|---|---|
| Gemma 3 27B | Google Gemma | 39K | 4K | $0.14 | $0.50 | — | failed | phala inferred · route not bound |
| Gemma 4 26B A4B Uncensored | Google Gemma | 63K | 4K | $0.19 | $0.88 | — | unreachable | Not identified |
| GLM 5.2 | ZhipuAI GLM | 512K | 32K | $1.75 | $5.75 | — | unreachable | Not identified |
| GPT-OSS 20B | OpenAI GPT | 125K | 32K | $0.05 | $0.19 | — | failed | phala inferred · route not bound |
| GPT-OSS 120B | OpenAI GPT | 125K | 32K | $0.13 | $0.65 | — | failed | phala inferred · route not bound |
| Qwen2.5 7B | Qwen | 31K | 4K | $0.05 | $0.13 | — | failed | phala inferred · route not bound |
| Qwen3.6 35B A3B Uncensored | Qwen | 125K | 4K | $0.38 | $1.88 | — | unreachable | Not identified |
| Qwen3-VL 30B A3B | Qwen | 125K | 4K | $0.25 | $0.90 | — | unreachable | Not identified |
| GLM 5.1 | ZhipuAI GLM | 195K | 32K | $1.10 | $4.15 | — | partial | Phala/dstack corroborated · route not bound |
| Qwen3.6 35B A3B | Qwen | 31K | 4K | $0.18 | $1.18 | — | partial | Phala/dstack corroborated · route not bound |
| Qwen3.6 27B | Qwen | 250K | 32K | $0.35 | $3.46 | — | partial | Phala/dstack corroborated · route not bound |
| Gemma 4 31B | Google Gemma | 31K | 4K | $0.14 | $0.43 | — | partial | Phala/dstack corroborated · route not bound |
| DeepSeek V4 Flash | DeepSeek | 977K | 8K | $0.18 | $0.37 | — | partial | Phala/dstack corroborated · route not bound |