4OpenAI Release Notes·
OpenAI adds phase labeling to Responses API
OpenAI released a 'phase' field to the Responses API that labels assistant messages as either intermediate commentary or a final answer. This allows developers to distinguish reasoning steps from terminal outputs in API responses. The feature is a targeted ergonomic improvement for agentic and multi-step workflows.
Related guides (2)
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.
OpenAI adds inline moderation scores to Responses API and Chat Completions API
OpenAI has added moderation scoring directly to the Responses API and Chat Completions API, allowing developers to receive moderation results for both inputs and outputs in a single API call. Previously, moderation required a separate API request. This reduces latency and integration complexity for applications that need content safety checks.
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.
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 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.
Open Responses: What you need to know
Hugging Face published a blog post titled 'Open Responses' covering what appears to be an open-source or open-weights initiative related to response generation or an API-compatible service. The post is positioned as an informational overview for the community. As a tier-2 source with commentary depth, this likely addresses ecosystem tooling or model serving developments relevant to the open AI/ML community.
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 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.