APIs and SDKs provide the programming interfaces and software kits developers use to integrate artificial intelligence models into applications. Truncated covers new interface releases, protocol updates, developer tools and integration standards.
AI-generated summary OpenAI introduced Private Safety Processing to review related API requests for safety without retaining your prompts or responses. OpenAI states that records stay in your environment where an automated safety agent reviews them without personnel accessing the content.
AI-generated summary Perplexity says it is integrating Fast Search into the Perplexity Decisions API to enable batch-mode decisions with factual grounding from the web. Perplexity says search costs $0.001 per request and the Decisions API costs $0.02 per 1M input tokens.
AI-generated summary Simon Willison has released datasette-llm 0.1a10 with a bug fix. The update resolves an issue that affected the agent.datasette.io demo site regarding model restrictions.
AI-generated summary Cisco says over 16,000 customers have deployed Cisco IQ since its general availability in Apr 2026. Cisco says the platform provides production REST APIs and a Model Context Protocol server for operational intelligence.
AI-generated summary Runway states that Runway Dev is now on Claude Code to bring AI video, image, and audio capabilities to applications. Runway states that the Runway Dev plugin enables Claude Code to build Runway's API into applications by writing the integration.
AI-generated summary Cohere announces that Embed 5 and Rerank 5 are now live on OpenRouter for retrieval applications. Cohere says users can access the two models through a single API in Pro and Fast tiers.
AI-generated summary The author made available a custom workflow created with n8n and GPT-5.4 mini to automate their morning routine. The automation tool compiles schedule details and messages from Gmail, Google Calendar, Asana, and Slack into a single daily briefing email.
AI-generated summary Strands releases expanded built-in tools support within the Strands Harness SDK for both Python and TypeScript. Strands says developers can add the capabilities to custom agents without building and maintaining each tool individually.
AI-generated summary @OpenAIDevs makes GPT-Image-2.6 available today in Codex and through the API for developers. @OpenAIDevs says Image-2.6 Flare and Sunburst are two new API image models that generate images 50 percent faster than before.
AI-generated summary Apple released the first Xcode 27.3 beta with three new features on Tuesday. The software includes GitHub Copilot support, Siri AI integration testing, and additional APIs for upcoming MacBook Pro models.
AI-generated summary NVIDIA releases NVIDIA CUDA 13.5 to deliver general availability for NVIDIA Vera Rubin support across major new platforms. NVIDIA says the update provides innovations across libraries, compilers, NVIDIA CUDA Tile, and developer tools to improve scheduling and performance.
AI-generated summary OpenAI rolls out an update to ChatGPT that lets users generate animated GIFs directly from a prompt or an uploaded photo. The new update also enables faster image generation across ChatGPT and its API alongside additional tools for developers.
AI-generated summary Coinbase launched the x402 open payment standard in May 2025 with partners including AWS, Anthropic, Circle and NEAR to let AI agents and apps pay for services in stablecoins. The Linux Foundation subsequently announced the creation of the x402 Foundation on April 2, 2026, to steward the protocol under vendor-neutral governance.
AI-generated summary Sinch has launched the Sinch plugin, available now through the Cursor Marketplace, to provide developers and AI coding agents with direct access to Sinch API knowledge and tools. Sinch states that the integration brings enterprise-grade communications infrastructure into Grok Build workflows so developers can build applications that enable AI agents to handle customer enquiries and automate routine interactions.
AI-generated summary @ArtificialAnlys announced that it will make the CritPt v2 grading server available to the community via its API tomorrow. @ArtificialAnlys stated that it regraded every model and observed small score increases for most models while frontier model rankings remain unchanged.
AI-generated summary Apple is testing a new Siri AI initiative in developer beta that allows third-party developers to create advanced app skills for the first time. The new features allow apps to teach Siri how to coordinate complicated multi-step actions across different platforms.
AI-generated summary LangChain has made LangSmith Bring Your Own Cloud available to run on AWS, Azure, and Google Cloud. LangChain says the offering keeps sensitive data in customer cloud accounts while the company manages the data plane for orchestration and scaling.
AI-generated summary Anthropic has released a public beta for message threads in its Messages API to speed up long-running Claude Code sessions. Anthropic says the feature reduces median time to first token by approximately 35% for requests containing between 500,000 and 1 million tokens.
AI-generated summary OpenAI released Pando as a new backend for Git repositories to power development in its monorepo. OpenAI says Pando cut median push latency by nearly 5x and now delivers nearly a petabyte of Git data per day.
AI-generated summary Simon Willison has released llm 0.37 with a Python library and CLI tool update containing accumulated features and fixes. The updated tool includes new gpt-6.1-sol and gpt-6.1-terra models along with a new llm openai endpoint add command for configuration.
The top AI news in your email delivered each morning. Choose categories