AI Foundry – Flat-Fee Unlimited LLM Inference on Blackwell GPUs in NZ (app.aifoundry.co.nz)

AI Foundry has announced a new service offering unlimited large language model (LLM) inference powered by Blackwell GPUs, specifically designed for clients of OpenAI. By simply redirecting their existing software development kits (SDKs) to AI Foundry’s endpoint, users can access the platform with ease, all while ensuring that their data remains onshore in Auckland, New Zealand—eliminating concerns about offshore data transfer. This service is significant for the AI/ML community as it introduces a flat-fee pricing model, with plans starting at just $7 per month for the OpenClaw plan and $19 for Coder Pro. By allowing up to eight concurrent requests per account and offering predictable latency without the risk of “noisy-neighbor” performance issues, AI Foundry sets a new standard for accessibility and reliability in LLM inference. This move could encourage more developers and businesses to leverage AI capabilities without the uncertainty of per-token costs, making AI tools more accessible and scalable for various applications.