Releases

OpenAI is scheduled to shut down the v1/prompts API and reusable prompt objects on November 30, 2026. The migration path is to keep prompt content in application code.

OpenAI is scheduled to shut down the Evals dashboard and API on November 30, 2026, after making existing evals read-only on October 31.

OpenAI says existing content on the deprecated Evals platform becomes read-only on October 31, 2026, ahead of the platform shutdown on November 30.

Databricks released a command-line workflow for developing agents integrated with Unity Gateway, Agent Bricks Runtime and MLflow tracing.

Perplexity added reusable agent profiles, skills and managed versioned connectors to Agent API.

CoreWeave made its hosted read-only Mission Control MCP server generally available for querying metrics, logs, dashboards, alerts, documentation, and resource state.

Databricks introduced Genie One MCP to provide trusted governed business context to external AI agents and cowork tools.

Hugging Face released Tokenizers v1, a major milestone for its Rust-based tokenization stack.

Modal updated its JavaScript and Go SDKs to the 0.10 generation.

OpenAI released the Agents API as a unified platform interface for building and operating agentic applications.

Oracle expanded its Responses API to work with imported models and agentic tooling.

DeepSeek released an updated agent harness with support for V4 Flash Vision.

DeepSeek added native Responses API support and low, high and max thinking effort controls.

Perplexity expanded Agent API into a unified interface for language models, real-time web retrieval and managed agents.

Perplexity launched secure isolated sandboxes for agent code execution and tool use.

Meta launched an API for developers to access and build with Muse Spark 1.1.

SpaceXAI made Grok 4.5 available through the API for coding, agentic tasks and knowledge work.

SpaceXAI made its fast agentic coding model available through the API in public beta.

Perplexity added structured financial search and retrieval to the Agent API.

The efficient V4 Flash preview became available through DeepSeek's API.

The V4 Pro preview became available through OpenAI- and Anthropic-compatible interfaces.

SpaceXAI announced its speech-to-text and text-to-speech APIs with multilingual support and developer pricing.

SpaceXAI launched batch and streaming speech transcription in 25 languages.

Modal opened a beta filesystem API for programmatic sandbox file operations.

Microsoft makes MAI-Voice-1 available to developers in Microsoft Foundry with custom-voice support and safety controls.

Mistral AI released a command-line interface for managing Spaces and developer workflows.

AWS released developer tooling for building customized Nova-based frontier models.

SpaceXAI made its natural-sounding text-to-speech API generally available.

Perplexity launched Sandbox API for isolated code execution by AI agents.

Perplexity upgraded Search API with improved extraction and dynamic evaluation benchmarks.

Perplexity launched Agent API as a managed runtime for agentic workflows.

xAI launched next-generation image and video generation through the Grok Imagine API, alongside a Batch API for high-volume workloads.

xAI launched an expanded production Collections API for retrieval-augmented generation directly within the Grok API.

xAI launched its Voice Agent API for developers building real-time conversational voice systems.

Transformers v5 entered release candidate with simplified model definitions, standardized attention interfaces, and support for more than 400 architectures.

The core Hugging Face Hub Python client reached v1.0 with a redesigned hf CLI, httpx networking, and Xet-based file transfers.

Anthropic introduced reusable Skills across Claude apps, Claude Code, and the API.

xAI made web search, X search and code execution tools generally available through its API.

OpenAI released the Apps SDK preview for developers to build interactive applications inside ChatGPT.

Modal released a beta Go SDK.

Modal released a beta JavaScript and TypeScript SDK.

Microsoft introduces the open-source Microsoft Agent Framework, unifying agent-development concepts from Semantic Kernel and AutoGen.

Anthropic released an SDK exposing the agent-building infrastructure used by Claude Code.

Perplexity launched a developer Search API exposing its real-time web index, retrieval and content extraction.

xAI made its stateful Responses API generally available.

Mistral AI introduced persistent memory capabilities for agents and applications.

xAI released the Collections API for file upload, embeddings and retrieval-augmented inference.

xAI released a Management API for programmatic API-key administration.

Mistral AI launched the Agents API with persistent agents, tools, orchestration, conversations and built-in connectors.

OpenAI added remote MCP server support, image generation, Code Interpreter, and background mode to the Responses API.

xAI added live search over supported data sources to API completions.

Microsoft launches NLWeb, an open MCP-compatible project for adding conversational and agent-accessible interfaces to websites.

AWS open-sourced a model-driven SDK for building AI agents.

Anthropic released a web search tool for developers building Claude-powered applications.

Modal released the 1.0 generation of its Python client and SDK.

Google introduces the open Agent2Agent protocol with more than 50 partners to enable interoperable agent collaboration.

Google Cloud releases the open-source Agent Development Kit for building and orchestrating multi-agent systems.

xAI made Grok 3 flagship models generally available through its API.

xAI made its image-generation model available through the developer API.

NVIDIA launched Dynamo to orchestrate and scale distributed generative AI inference.

Anthropic released API features designed to reduce token use and improve long-running agent workflows.

Databricks released APIs for embedding Genie conversational analytics into applications, Teams, Slack and SharePoint.

OpenAI released the open-source Agents SDK for orchestrating single- and multi-agent workflows.

OpenAI launched the Responses API as a new foundation for building agentic applications with built-in tools.

Hugging Face launched a unified inference layer that lets developers call models across multiple providers through one API and billing experience.

Perplexity launched Sonar and made Sonar Pro generally available through its API platform for cited real-time answers.

Hugging Face released smolagents, a lightweight open-source framework for tool-using and code-executing AI agents.

Anthropic introduced and open-sourced MCP, its specification, SDKs, local Claude Desktop support, and reference servers.

Mistral AI launched a moderation API for safety classification and content policy enforcement.

Mistral AI launched an asynchronous Batch API for high-volume model inference.

xAI opened public API access to Grok foundation models with OpenAI- and Anthropic-compatible interfaces.

Gradio 5 introduced redesigned application theming, stronger security defaults, and improved AI app development workflows.

Anthropic launched computer use in public beta, allowing developers to direct Claude to operate graphical computer interfaces.

Anthropic launched asynchronous batch processing for large volumes of Claude API requests.

OpenAI launched the Realtime API public beta for low-latency multimodal experiences.

Anthropic introduced Contextual Retrieval, combining contextual embeddings and BM25 to improve retrieval-augmented generation.

La Plateforme added support for Pixtral and expanded developer tooling for multimodal applications.

Accelerate reached its 1.0 release-candidate milestone after becoming a core distributed-compute layer in the Hugging Face ecosystem.

Anthropic launched prompt caching to reduce latency and cost for repeated long-context prompts.

DeepSeek introduced disk-based context caching to reduce repeated-token costs.

The API gained JSON mode, function calling, chat-prefix completion and fill-in-the-middle completion.

Mistral AI introduced self-service fine-tuning through La Plateforme and released customization tooling.

Anthropic made tool use generally available across the Claude API, Amazon Bedrock, and Google Vertex AI.

Hugging Face launched LeRobot to bring open models, datasets, policies, and reproducible tooling to real-world robotics.

DeepSeek opened an OpenAI-compatible API for its chat and coding models.

Cohere added function calling and tool-use capabilities for building grounded enterprise agents.

Anthropic expanded commercial legal protections and improved API access and enterprise terms.

Google releases the Gemini API through Google AI Studio and Vertex AI, giving developers access to Gemini Pro.

Baidu fully opened ERNIE APIs to enterprise customers through AI Cloud.

xAI began early API access for Grok developers ahead of the later public beta.

OpenAI launched the Assistants API beta with Code Interpreter, Retrieval, and function calling.

Moonshot introduced developer API access to its language models.

Hugging Face released a production-grade server for serving text embedding and reranking models.

Meta introduced ExecuTorch, an open-source framework for efficient on-device PyTorch inference.

NVIDIA publicly released its open-source TensorRT-LLM library for optimized large-model inference.

HTTP endpoints backed by autoscaling Modal functions became generally available.

Modal's Python-first SDK and developer workflow reached general availability.

Perplexity launched pplx-api with hosted access to its PPLX chat models.

Microsoft Research releases AutoGen, a framework for building applications with conversing and collaborating AI agents.

Databricks introduced pay-per-token APIs and provisioned throughput for serving curated open foundation models.