Comparison

Voice agents fail on latency long before they fail on intelligence. Time to first token is the metric most teams use to choose an inference API, and it is the right starting point and the wrong stopping point. This benchmark works through every layer of the voice stack — LLM, speech-to-text, text-to-speech, and speech-to-speech — using figures verified against primary sources on August 30, 2026, with each number labeled as independently measured, vendor-published, or vendor-measured on its own product.

Z.ai and Qwen independently shipped near-identical architectures: 3:1 linear hybrids, compressed indexers, gated residuals, and Muon training.

Every agent that writes code needs somewhere to run it, and no two vendors quote the same units. This comparison measures burst cold start across E2B, Daytona, Modal, Cloudflare, and Vercel, normalizes per-second rates to cost per 1,000 executions, and maps filesystem persistence, idle billing, and egress policy against primary sources verified August 27, 2026.