OpenAI launches WebSocket mode for the Responses API
OpenAI added WebSocket mode to its Responses API, enabling persistent bidirectional connections for API consumers. This is an infrastructure-level capability update that allows lower-latency, streaming-friendly integrations compared to standard HTTP request-response patterns. The change is relevant for developers building real-time or agentic applications on top of OpenAI's API.
Related guides (3)
Related events (8)
New Tools and Features in the Responses API
OpenAI announced new tools and features for its Responses API, expanding the capabilities available to developers building on the platform. The update likely includes additional built-in tools, improved function calling, or new modalities accessible through the API. As a Tier 1 source announcement, this represents a meaningful expansion of OpenAI's developer-facing infrastructure. Specific details were not available in the body text provided.
Speeding up agentic workflows with WebSockets in the Responses API
OpenAI published a technical deep dive into the Codex agent loop, detailing how WebSockets and connection-scoped caching were used to reduce API overhead and improve model latency. The post focuses on infrastructure optimizations within the Responses API for agentic workflows. These changes are relevant to developers building multi-step agent pipelines that rely on repeated API calls.
OpenAI launches server-side compaction in the Responses API
OpenAI has shipped server-side compaction to its Responses API, a feature that manages context window usage automatically on the server side. This reduces the burden on developers to manually truncate or summarize conversation history when building long-running or agentic applications. The release is a quality-of-life infrastructure improvement for API consumers.
OpenAI announces Open Responses: open-source spec for multi-provider LLM interfaces
OpenAI announced Open Responses, an open-source specification for multi-provider, interoperable LLM interfaces derived from the original OpenAI Responses API. The specification aims to standardize how applications interact with LLMs across different providers. This is a potential standardization move that could shape how the broader ecosystem builds on top of LLM APIs.
OpenAI launches Skills support in the Responses API with local and hosted execution
OpenAI added Skills support to its Responses API, enabling both local execution and hosted container-based execution modes. Skills appear to be a new capability primitive within the Responses API ecosystem, extending what developers can build with the API. The announcement is brief and lacks detail on the specific capabilities or use cases Skills enable.
OpenAI models now available in Amazon Bedrock via Responses API
OpenAI has made its models available through Amazon Bedrock using an OpenAI-compatible Responses API endpoint. Supported models and features vary by AWS Region. This expands OpenAI's distribution reach into AWS's managed AI infrastructure, giving enterprise customers access to OpenAI models within the Bedrock ecosystem.
OpenAI adds image results to web search in the Responses API
OpenAI's Responses API web search tool now returns image results alongside text results. The feature targets use cases requiring web-grounded visuals such as product photos, landmarks, events, and visual references. This expands the multimodal utility of the Responses API for developers building search-augmented applications.
From model to agent: Equipping the Responses API with a computer environment
OpenAI describes how it built an agent runtime by combining the Responses API with a shell tool and hosted containers, enabling agents to operate with persistent files, tools, and state. The architecture supports secure, scalable execution of agentic workflows. This represents a concrete infrastructure layer for deploying agents in production environments.