Retell AI, a voice AI platform for contact center operations, now serves more than 4,000 businesses with monthly call volume exceeding 100 million as of September 2026, according to OpenAI. The platform grew from 30 million monthly calls in early 2026.
OpenAI models generate responses for 80% of calls on Retell’s platform, with customers achieving resolution rates above 80%. The company has consumed more than 1 trillion tokens across OpenAI models.
Retell built its vCX benchmark to compare models using multi-turn conversations from production scenarios, testing instruction following, grounding, tool calling and conversational language. In Retell’s October 13, 2026 benchmark, GPT-6 Astra ranked first for instruction following at 89.7%.
Retell also reported evaluations conducted before GPT-6 Astra’s launch showing GPT-5.5 with reasoning enabled ranked highest among tested models on non-hallucination rate at 88.0% and tool-call correctness at 88.3%, outperforming Gemini-3.1-Pro and Claude-4.6 on both measures.
The platform allows contact center teams to define agents’ business context, goals and rules, while developers configure workflows and integrations. Customers have access to OpenAI Realtime models through the Realtime API and OpenAI text-to-speech. Retell makes new OpenAI models available on their launch day.
“We choose models the way our customers choose vendors: on real calls, not demos. OpenAI keeps earning its spot,” said Bing Wu, co-founder and CEO of Retell AI.