Lambda, a San Francisco-based technology company, has introduced a new AI inference API service that promises the lowest costs in the industry. According to VentureBeat reporter Carl Franzen, the service allows enterprises to deploy AI models without managing computing infrastructure. The API supports various advanced models including Meta’s Llama 3.3 and Alibaba’s Qwen 2.5, with prices starting at $0.02 per million tokens for smaller models. Lambda’s Vice President Robert Brooks emphasized that their platform can offer significant cost savings compared to competitors due to their extensive GPU infrastructure built over 12 years. The pay-as-you-go service requires no subscriptions or rate limits, and developers can begin using it within minutes. The company plans to expand into multimodal applications, including video and image generation capabilities.