We use cookies to measure how the site is used and how our ads perform (Google Analytics and Ads, Microsoft Clarity, and the Meta, OpenAI and X ad pixels). “Essentials only” turns off advertising cookies everywhere, and analytics too in the EEA, UK and Switzerland. Privacy Policy
Tool Retrieval is in preview in the Gemini Interactions API: add a tool_search tool, set defer_loading on the long tail, and the server loads parameter schemas on demand. What that changes for tokens, prefix caching, MCP catalogs and debugging — and where the saving does not show up.
Job listings spotted by Bloomberg show Apple building an autonomous agent that browses, codes, controls apps and coordinates sub-agents — the last major platform holder to enter the computer-use race.
Mistral launches the API preview for Mistral Large 4, a 1-trillion parameter multimodal model with strong performance in cybersecurity and agentic coding. Open weights drop soon.
Qwen Code Desktop v0.25.0 and SDK TypeScript v0.1.18 landed 5 October with a native advisor tool, a v2 Managed Runtime execute/status/cancel contract, review verdicts that survive a rebase, and a claimed 2x faster fresh startup with 60 percent lower memory.
AWS made GLM 5.3 generally available on Amazon Bedrock on October 5, 2026 — managed APIs, cross-Region inference, prompt caching, and $1.68 per 1M input tokens for eligible enterprise customers. What shipped, what it costs, and how to call it.