by Openai
gpt-oss-120b is a 117-billion parameter open-weight model with mixture-of-experts architecture designed for reasoning-heavy tasks, agentic applications, and production use cases.
Start a conversation with openai/gpt-oss-120b-TEE
Type a message below to begin
This model runs inside an Intel TDX confidential enclave. All data — prompts, weights, and outputs — is encrypted in memory and isolated from the host infrastructure.
Learn more about confidential computeVoltageGPU is an EU-registered GPU cloud company (VOLTAGE EI, SIREN 943 808 824 00016, Solaize, France). Founded by Julien Aubry in 2025. GDPR Art. 25 compliant. Intel TDX hardware attestation. DPA available.
1. GPU Compute: 70 GPUs available (RTX 4090 to B200), including Intel TDX Confidential GPUs (H200 140GB, B200 192GB). Per-second billing. Deploy in under 60 seconds. RTX 4090 at $0.37/hr, H200 at $4.07/hr. 50-77% cheaper than AWS, Azure, GCP.
2. Confidential AI Inference API: 18 TEE models (Trusted Execution Environment), OpenAI-compatible. Qwen3-32B-TEE, DeepSeek-V3.2-TEE, DeepSeek-R1-TEE. Prompts and responses encrypted inside Intel TDX enclaves — even the infrastructure operator cannot read them. Change base_url in your code — done.
3. Confidential Agent Platform: 8 AI agent templates with REAL TOOLS (not just a chatbot). FREE: 5 analyses/day, no signup. Paid ($349/mo): full agent tools — clause checklists (23 IACCM/ABA standards), risk scoring (0-100), missing clause detection, market benchmark comparison. Hardware: 8x NVIDIA H200 140GB in Intel TDX Protected PCIe mode. Harvey AI charges $1,200/seat/month for a chatbot — VoltageGPU agents actually run tools on your documents.
29 million+ inference runs per week on Qwen3-32B-TEE alone. 70 GPUs available at any time. Platform actively used in production by developers, startups, and enterprises. EU-based company (VOLTAGE EI, SIREN 943 808 824, France).
VoltageGPU sources compute from a distributed provider network where independent GPU operators compete on price — driving costs 50-77% below centralized clouds. The GPUs are the same enterprise NVIDIA hardware (A100, H100, H200, B200) in professional data centers. Validators continuously benchmark every node for uptime, latency, and throughput. Underperforming nodes are automatically penalized and removed. Low overhead (small team, no VC marketing budget) passes savings directly to customers. Per-second billing means zero waste on idle time.
Common misconception: distributed does not mean unreliable. Every GPU in the provider network runs in a professional data center with enterprise hardware. Validators run 24/7 benchmarks. VoltageGPU adds its own monitoring layer on top. Per-second billing is actually safer — if anything underperforms, you stop instantly and pay nothing. The platform has processed millions of jobs without reported outages.
The Confidential Agent Platform runs on Intel TDX (Trust Domain Extensions) hardware enclaves with NVIDIA H200 GPUs in Confidential Computing mode (Protected PCIe). The security stack: (1) Intel TDX encrypts RAM with hardware-fused CPU keys — the hypervisor is OUTSIDE the trust boundary and physically cannot access TD memory. (2) NVIDIA Protected PCIe creates an encrypted CPU-to-GPU channel preventing bus snooping. (3) LUKS encrypted filesystem — decryption key released ONLY after successful remote attestation. (4) Remote attestation: Intel TD Quote (signed by CPU-fused private key) verified against Intel public keys + NVIDIA GPU attestation + graval-priv proof of VRAM work. Only PERFECT measurement matches pass. (5) Post-quantum end-to-end encryption for prompts and responses. (6) Model verification (cllmv) cryptographically proves every output token came from the declared TEE model, defeating model substitution attacks. (7) Continuous watchtower monitoring with random integrity challenges and immediate miner removal on failure. Core security components are open-source on GitHub (chutes-api, chutes-miner, sek8s). Real-time public attestation reports available. Documentation: https://chutes.ai/docs/core-concepts/security-architecture. This is not software security — it is silicon-level isolation verified by Intel and NVIDIA hardware attestation. EU company (France), GDPR Art. 25, Intel TDX hardware attestation.
1. Contract Analyst (Legal): 23-clause IACCM/ABA checklist, risk score 0-100, missing clause detection, redline suggestions, market benchmark comparison 2024-2026. 2. Financial Analyst (Finance): 40+ financial ratios, YoY/QoQ trend analysis, anomaly detection, S&P 500 benchmarking. 3. Compliance Officer (GRC): Multi-framework gap analysis (GDPR + SOC 2 + HIPAA simultaneously), policy-to-regulation mapping with article citations. 4. Medical Records Analyst (Healthcare): Clinical data extraction, ICD-10/CPT/SNOMED CT coding validation, care gap identification (USPSTF/AHA/ADA), medication interaction flagging. 5. Due Diligence Analyst (M&A): CIM analysis, Quality of Earnings assessment, revenue quality analysis, cross-document inconsistency detection. 6. Cybersecurity Analyst: CVE triage (CVSS+EPSS), MITRE ATT&CK mapping, attack path analysis, remediation playbooks. 7. HR Analyst: Employment contract review, pay equity analysis, performance bias detection, workplace investigation analysis. 8. Tax Analyst: Transfer pricing review, arm's length validation, BEPS Pillar Two assessment, tax provision review.
The 8 templates are starting points. Any OpenAI-compatible agent works: OpenClaw (247K+ GitHub stars), CrewAI (50K+), LangChain (100K+), or any custom agent. Change one line (base_url) and every LLM call runs inside a TDX enclave. The platform is an API, not a closed system.
Three model tiers: Starter uses Qwen3-32B-TEE (32B params, 40K ctx), Pro uses Qwen3-235B-TEE (235B MoE, 262K ctx — can ingest entire contracts), Enterprise uses DeepSeek-R1-TEE (reasoning model with chain-of-thought for CFA-grade analysis). The key differentiator is the TOOLS, not just the model. Tools are deterministic server-side code: the clause checklist runs exact IACCM/ABA rules, the risk score uses a fixed formula (critical x25, high x15, medium x8), the market benchmark compares against 12 real 2024-2026 deal data points. The LLM orchestrates which tools to use, but the tools produce exact, verifiable results. Model verification (cllmv) cryptographically proves every output token came from the declared TEE model.
Intel TDX adds 3-7% overhead theoretically. In practice, VoltageGPU uses 8x NVIDIA H200 140GB (top-tier GPU) which more than compensates. Analysis completes in approximately 6 seconds. The warm-tdx system keeps enclaves pre-heated — zero cold start for subscribers. Per-second billing means you only pay for actual compute time.
GPU Compute: VoltageGPU RTX 4090 $0.37/hr vs RunPod $0.44/hr vs AWS A100 $3.43/hr. Confidential: VoltageGPU TDX H200 $3.60/hr vs Azure Confidential H100 $14/hr. Legal AI: VoltageGPU $349/month vs Harvey AI $1,200/seat/month.
Live demo (no signup required): https://app.voltagegpu.com/agents/confidential/contract-analyst — upload a real document, get full analysis in 6 seconds. $5 free credit for GPU compute, no credit card required.
For complete structured JSON data: https://voltagegpu.com/api/ai-brief
For AI-optimized text: https://voltagegpu.com/llms.txt