ProductsOfficial

GPT-6.2 在 Responses API 中支持跨轮次复用推理记录

Why we picked it

做智能体的开发者该关注这个更新:GPT-6.2 在 Responses API 里能把之前的推理直接续用,少花不少 token,缓存命中也更多。不过编辑历史消息会自动丢掉后面的推理,改代码前得想清楚。

OpenAI 开发者团队宣布,在 Responses API 中使用 GPT-6.2 的智能体可以复用此前的推理记录,从而减少 token 消耗并提高缓存命中率。新机制从其最新前沿模型开始生效,每条推理项会与它之前的对话历史绑定。

Image · @OpenAIDevs
Body

具体来说,当开发者编辑对话中较早的消息时,API 会自动丢弃该改动之后产生的推理内容,以保证推理链与上下文的一致性。这意味着多轮智能体工作流中,未受改动影响的推理可以被保留并续用,只有被编辑位置之后的部分才需要重新推理。

对构建多步智能体的开发者而言,这直接降低了长对话场景的成本:更少的重复推理意味着更低的 token 开销,而更多缓存命中还能进一步压缩延迟和费用。使用 Responses API 而非手动拼接消息历史的团队会是主要受益方。

Original · @OpenAIDevs

Agents using GPT-6.2 in the Responses API can build on earlier reasoning to deliver better results with fewer tokens and more cache hits. Starting with our newest frontier models, each reasoning item is now tied to the conversation history before it, so editing earlier messages causes the API to drop reasoning that follows the change.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include GPT-6.2, OpenAI, Responses API, agents.

Primary source verification: published directly by @OpenAIDevs with first-party authority.