Phala

Congratulations to the Proofable team on the launch! As AI agents take on more responsibility, verifying who they represent and what they’re authorized to do becomes essential. Proud to support this work alongside the Proofable ecosystem.

Phala Confidential AI: 186.42 billion tokens over the past 24 hours. Top models: GLM-5.3 Flash 69.41% deepseek-v4.1-flash-1017 7.61% xing4.0-29b-a4b 5.50% https://lnkd.in/gEVMa8Fn TEE-backed AI infrastructure.

Phala Confidential AI: 186.26 billion tokens over the past 24 hours. Top models: GLM-5.3 Flash 59.87% Kimi K3 13.74% DeepSeek V4.1 Flash 9.13% https://lnkd.in/gEVMa8Fn TEE-backed AI infrastructure.

Phala Confidential AI: 105.50 billion tokens over the past 24 hours. Top models: GLM-5.3 Flash 43.47% DeepSeek V4.1 Flash 23.98% xing4.0-29b-a4b 7.70% https://lnkd.in/gEVMa8Fn TEE-backed AI infrastructure.

DeepSeek V4.1 Flash 1017 is live on Phala—served inside a TDX-attested GPU TEE. Private, verifiable inference for long-horizon agents, visual understanding, reasoning. https://lnkd.in/ge8ArCkx 1M context. Tool use, structured outputs. $0.75/M input · $1.6/M output. https://lnkd.in/e4yu_p_C

Phala Confidential AI: 81.33 billion tokens over the past 24 hours. Top models: DeepSeek V4.1 Flash 56.30% xing4.0-29b-a4b 12.22% qwen3.8-27b 9.39% https://lnkd.in/g8Zgbf8Z TEE-backed AI infrastructure.

Phala Confidential AI: 57.82 billion tokens over the past 24 hours. Top models: DeepSeek V4 Flash 0731 24.69% GLM-5.3 Flash 24.69% Kimi K3 14.28% https://lnkd.in/gYKNW_Ex TEE-backed AI infrastructure.

Agents can generate language. Production workflows also need bounded decisions that software can threshold, route, and log. Kev-4B is now live in beta on Phala. It turns shared application state into typed probability distributions for yes/no, choice, and score questions through TypeSafe’s System One API. Agent use cases from the Kev-4B model card: • classification, routing, and triage • extraction choices • policy and eligibility checks • judging a proposed answer against stated criteria • confidence-based handoff to human review Selected model-card benchmarks (self-reported, fp32): • 83.8% accuracy on the transfer-v4 locked out-of-domain test (656 questions) • 90.3% accuracy on the documents-v1 test (936 questions) • 70.1% coverage at an error rate of 5% or less on transfer-v4 locked These results measure specific evaluation suites. Validate thresholds on labeled examples from your target workload. On Phala, Kev-4B runs with NVIDIA Confidential Computing, an 8,192-token validated context, and catalog pricing of $0.04 per 1M input tokens with free output. Read the launch article: https://lnkd.in/gjPTbrCE Try the model: https://lnkd.in/gi-PJqsr Benchmark methodology: https://lnkd.in/gy93aeDf #AIAgents #DecisionModels #ConfidentialAI

Phala Confidential AI: 85.07 billion tokens over the past 24 hours. Top models: DeepSeek V4.1 Flash 51.54% GLM-5.3 Flash 25.82% Kimi K3 5.22% https://lnkd.in/g8Zgbf8Z TEE-backed AI infrastructure.

Phala Confidential AI: 34.61 billion tokens over the past 24 hours. Top models: GLM-5.3 Flash 23.97% DeepSeek V4.1 Flash 23.09% GLM-5.3 14.66% https://lnkd.in/gEVMa8Fn TEE-backed AI infrastructure.