Iterate.ai launches Lifeboat inference engine with confidential computing

Iterate.ai has launched Lifeboat, an LLM inference engine with built-in confidential computing that fits two to six times as many concurrent AI agent sessions per GPU. On a single Nvidia RTX PRO 6000 Blackwell running Qwen 30B-A3B, it held 2,048 concurrent sessions versus 1,024 without optimizations. Pricing: Standard at $49.99/month, Confidential Computing at $499.99/month.

• Up to 6x more concurrent agent sessions per GPU
• 2,048 sessions on RTX PRO 6000 Blackwell with Qwen 30B-A3B
• 8,714 tokens/sec versus 4,965 without optimizations
• Confidential Computing edition $499.99/mo, Standard $49.99/mo