After 100-plus hours testing both coding agents, Pi's context overhead is under 1,000 tokens per request versus OpenCode's roughly 6,900 tokens, a 7x difference that can waste thousands of dollars in …
Vercel's AI Gateway now offers Fish Audio's four audio models for free through September 18, including text-to-speech and speech-to-text, with standard pricing resuming after the period unless models …
Vercel's AI SDK harness layer now supports Cline, an AI coding agent, through the official adapter @ai-sdk/harness-cline, developed with the Cline team. Cline runs fully in the host process, using the…
Google's Gemini 3.7 Flash is now available on AI Gateway via the AI SDK at half price through December 31, 2026, with improved agent reliability and reduced tool-calling loop failures. The developer a…
Google's Gemini 3.7 Flash model cuts inference costs by half while improving code generation accuracy, with FrontierCode scores rising from 34.4% to 43.6%. Z.ai's GLM 5.2, a 1M-token open-weights mode…
Vercel has made its v0 API generally available, giving developers programmatic access to its AI-powered application-building agent. The API supports synchronous, asynchronous, and streaming requests, …
A developer detailed an adapter pattern for unified tracing across AI SDK, LangChain.js, OpenAI Agents SDK, and direct model clients. The approach normalizes framework-specific lifecycles into a commo…
Vercel's AI Gateway now offers Google's Gemini 3.7 Flash model at a 50% discount until December 31, 2026. The model improves software engineering and agentic tasks, resolving issues more reliably and …
Vercel's AI SDK harness layer now supports any Agent Client Protocol (ACP)-compatible harness through the new @ai-sdk/harness-acp package, which wraps the protocol as a meta adapter instead of a singl…
Vercel released a minimal chatbot template built with Next.js, the AI SDK, shadcn/ui, shadcn/react, shadcn/typeset, and the Vercel AI Gateway, featuring streaming chat with markdown rendering, tool ca…
DeepSeek V4 Pro now runs on updated weights on Vercel's AI Gateway, with the new version accessible via the model ID `deepseek/deepseek-v4-pro-0813` in the AI SDK. Existing requests using `deepseek/de…
Vercel's AI SDK, an open-source project with over 20 million weekly npm downloads and 26,000 GitHub stars, faced a backlog of over 1,000 open issues and nearly 800 pull requests by late June. To addre…
SpaceXAI's Grok 4.6 is now available on Vercel's AI Gateway, featuring a 500K token context window, text and image inputs, and reasoning levels from low to xhigh, defaulting to high. Developers can us…
Vercel's AI SDK harness layer now supports Grok Build, an official adapter that runs through the same HarnessAgent interface as other coding-agent runtimes, allowing developers to switch runtimes with…
Vercel's AI Gateway now supports xAI's Grok Imagine Image 2.0 Preview, a model that follows detailed instructions, plans typography and layout, and supports image editing. Developers can use it via th…
ByteDance's Seedance 2.5 video generation model is now available on Vercel's AI Gateway, enabling single-clip generation of up to 30 seconds with consistent camera movement and continuity, plus local …
Vercel's AI Gateway now offers Ling 3.0 Tiny from ANT Group, a free-to-use model with 7.9B total parameters and about 1.3B active per token, a 256K token context window, and up to 32K output tokens, a…
Meta's Muse Spark 1.2 is now available on Vercel AI Gateway, featuring improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows. The model is desi…
Cloudflare has launched Cloudflare Agents, a unified platform for deploying and managing hosted agents, starting with agent tracing for observability. The new agent tracing feature, available today fo…
A developer shares a simple prompt-engineering trick: wrapping prompt sections in XML tags like <instructions> and <context> measurably improves output consistency from large language models such as C…