OpenAI updates Responses API so agents can build on earlier reasoning with fewer tokens
OpenAIDevs · x · 2026-11-20
OpenAI's developer account announced that agents using GPT-6.2 in the Responses API can now build on earlier reasoning, delivering better results with fewer tokens and more cache hits.
Starting with the newest frontier models, each reasoning item is tied to the conversation history before it — editing earlier messages causes the API to drop all reasoning that follows the change. Developers should keep history unchanged and append new turns instead.
Related event: OpenAI Responses API Lets Agents Reuse Reasoning History to Cut Tokens(3 posts)→
More from coding & agent
- Vercel CEO: outcome-oriented engineers are now 1000x, and coding is AI's #1 killer app — tlakomy · 2026-11-20
- AssemblyAI Adds Circuit Breaker to LLM Gateway: Skip Degraded Models Before Your Request Fails — AssemblyAI · 2026-11-20
- LangChain Celebrates Fundraise With Mini Launch Week: Trace Governance, Tool Gateway, LangSmith for Coding Agents — hwchase17 · 2026-11-20
- Techtree Packages Skills, Evals and Training Envs to Provably Upgrade Business Agents — seanwbren · 2026-11-20
- Open-source F1 MCP Server: telemetry, tire wear and Monte Carlo strategy — modelcontextprotocol · 2026-11-20
- Maindex Smart Memory Service gives agents memory via four explicit tools — modelcontextprotocol · 2026-11-20