Retell AI 用 OpenAI 模型支撑每月 1 亿通电话
OpenAI 表示，语音 AI 平台 Retell AI 已服务超过 4000 家企业，月通话量从 2026 年初的 3000 万通增长到 9 月的逾 1 亿通，其中 80% 的通话响应由 OpenAI 模型生成。Retell 称客户解决率超过 80%，并举例称 Anker 报告 80.4% 的工单解决率与 63 的 NPS，Pine Park Health 的预约智能体达到 55.7% 的预约率。在其 10 月 13 日的 vCX 基准测试中，GPT-6 Astra 以 89.7% 的指令遵循率排名第一，其工程师则使用 Codex 做代码调研、功能开发与调试，并用 GPT-6 Astra 的 computer use 测试前端界面。
该报道记录了 OpenAI 模型在客服语音智能体中的大规模生产部署，包括每月 1 亿通电话、跨 OpenAI 模型累计消耗超 1 万亿 token 以及基于 Codex 的工程流程，但采用率与绩效数据均来自供应商陈述。
Retell AI(opens in a new window) is a voice AI platform for contact center operations, helping businesses build agents that can answer questions, take action, and connect a caller with a person when needed. Its platform now serves more than 4,000 businesses, with monthly call volume growing from 30 million in early 2026 to more than 100 million by September.
As Retell serves more enterprises with complex workflows, it uses OpenAI models to keep call quality and reliability high. Today, OpenAI models generate responses for 80% of calls on Retell, with customers achieving resolution rates above 80%. Retell has also surpassed 1 trillion tokens consumed across OpenAI models, reflecting the scale of that adoption.
Retell’s engineers use Codex throughout development, from researching unfamiliar code to building features and debugging issues, and GPT‑6 Astra to test front-end interfaces.
“We choose models the way our customers choose vendors: on real calls, not demos. OpenAI keeps earning its spot.”
—Bing Wu, Co-founder and CEO, Retell AI
Choosing OpenAI models for the demands of a live call
Enterprise voice agents need to follow company policies and stay within their assigned roles, even as conversations change. Retell built its vCX benchmark to compare dozens of models using difficult, multi-turn conversations drawn from real production scenarios.
#Retell AI#OpenAI#Codex#GPT-6 Astra#GPT-6.1 Sol#GPT-5.5#GPT-5.6 Terra#GPT-5.6 Luna#Anker#Pine Park Health#Gemini-3.1-Pro#Claude-4.6