Redpill
Attested E2EEOpenAI-compatible confidential inference on Phala GPU TEE
Redpill by Phala Network offers confidential AI inference running on Phala's decentralized GPU TEE infrastructure. Models execute inside Intel TDX enclaves with NVIDIA H100 Confidential Computing, providing cryptographic proof that inference is private. Fully OpenAI-compatible API with transparent on-chain attestation.
API Features
OpenAI Compatible ✓
Streaming ✓
Function Calling ✓
Batch Inference —
Vision ✓
Embeddings ✓
Attestation Status
View full details →Last checked: Jun 18, 2026, 11:05 AM
Critical trust failures At least one check failed a quote, freshness, key-binding, measurement, or policy gate.
7 verified 14 partial 3 failed 2 unavailable
Hardware 24/26 good Freshness 3 bad Key binding 3 bad Workload 10 bad Provenance 17 warning Availability 2 warning
Measurement mismatch 3 Signer not bound 3 Nonce not bound 3 Image provenance incomplete 17
DeepSeek V3.2 (TEE) Intel TDX Attested E2EE Details Gemma 4 31B (TEE) Details GLM 4.7 (TEE) Intel TDX Attested E2EE Details GLM 5.1 (TEE) Intel TDX Attested E2EE Details GPT-OSS 120B (TEE) Intel TDX Attested E2EE Details GPT-OSS 20B (TEE) Intel TDX Attested E2EE Details Kimi K2.5 (TEE) Intel TDX Attested E2EE Details Kimi K2.6 (TEE) Intel TDX Details Phala/deepseek Chat V3.1 (TEE) Intel TDX Attested E2EE Details Phala/deepseek V4 Flash (TEE) Intel TDX Attested E2EE Details Phala/gemma 3 27b It (TEE) Details Phala/gemma 4 26b A4b Uncensored (TEE) Intel TDX Attested E2EE Details Phala/glm 4.7 Flash (TEE) Intel TDX Attested E2EE Details Phala/glm 5 (TEE) Intel TDX Attested E2EE Details Phala/glm 5.2 (TEE) Intel TDX Attested E2EE Details Phala/minimax M2.5 (TEE) Intel TDX Attested E2EE Details Phala/qwen2.5 Vl 72b Instruct (TEE) Intel TDX Details Phala/qwen3.5 27b (TEE) Intel TDX Attested E2EE Details Phala/qwen3.6 27b (TEE) Intel TDX Attested E2EE Details Phala/qwen3.6 35b A3b (TEE) Intel TDX Attested E2EE Details Phala/qwen3.6 35b A3b Uncensored (TEE) Intel TDX Attested E2EE Details Phala/uncensored 24b (TEE) Intel TDX Attested E2EE Details Qwen 2.5 7B (TEE) Intel TDX Attested E2EE Details Qwen3 30B (TEE) Intel TDX Attested E2EE Details Qwen3-VL 30B (TEE) Intel TDX Details Qwen3.5 397B (TEE) Intel TDX Attested E2EE Details
Models & Pricing
| Model | Family | Context | Max Out | Input /M | Output /M | Free |
|---|---|---|---|---|---|---|
| DeepSeek V3.2 | DeepSeek | 160K | — | $0.32 | $0.48 | — |
| Gemma 3 27B | Google Gemma | 52K | — | $0.11 | $0.40 | — |
| GPT-OSS 20B | OpenAI GPT | 128K | — | $0.04 | $0.15 | — |
| DeepSeek V3.1 | DeepSeek | 160K | — | $1.05 | $3.10 | — |
| Qwen3 30B A3B | Qwen | 256K | — | $0.15 | $0.55 | — |
| Qwen3-VL 30B A3B | Qwen | 128K | — | $0.20 | $0.70 | — |
| Qwen2.5-VL 72B | Qwen | 64K | — | $0.20 | $0.70 | — |
| GLM 4.7 | ZhipuAI GLM | 128K | — | $0.85 | $3.30 | — |
| Venice Uncensored 24B | Custom | 32K | — | $0.20 | $0.90 | — |
| GLM 5 | ZhipuAI GLM | 198K | — | $1.20 | $3.50 | — |
| GLM 5.1 | ZhipuAI GLM | 198K | — | $1.21 | $4.20 | — |
| Qwen3.5 27B | Qwen | 256K | — | $0.30 | $2.40 | — |
| Kimi K2.5 | Moonshot AI | 256K | — | $0.60 | $3.00 | — |
| MiniMax M2.5 | MiniMax | 192K | — | $0.20 | $1.38 | — |
| GLM 4.7 Flash | ZhipuAI GLM | 198K | — | $0.10 | $0.43 | — |
| Qwen3.6 27B | Qwen | 256K | — | $0.32 | $2.70 | — |
| Qwen3.6 35B A3B Uncensored | Qwen | 128K | — | $0.30 | $1.50 | — |
| GPT-OSS 120B | OpenAI GPT | 128K | — | $0.15 | $0.60 | — |
| Gemma 4 26B A4B Uncensored | Google Gemma | 64K | — | $0.15 | $0.70 | — |
| Qwen2.5 7B | Qwen | 32K | — | $0.04 | $0.10 | — |
| Kimi K2.6 | Moonshot AI | 256K | — | $1.09 | $4.60 | — |
| Qwen3.5 397B A17B | Qwen | 256K | — | $0.55 | $3.50 | — |
| Gemma 4 31B | Google Gemma | 256K | — | $0.15 | $0.46 | — |