DeepSeek released deepseek-v4-flash-vision-exp, an experimental multimodal variant of its V4-Flash model, on August 21, 2026, matching text-only capabilities while accepting images at the same per-tok…
Aivo released a command-line tool that lets developers launch coding agents such as Claude Code, Codex, and Pi with any model from providers including OpenRouter, Vercel AI Gateway, DeepSeek, Cloudfla…
Vercel Labs open-sourced fx, a coding agent CLI written in Zig that ships as a 7.8 MiB binary, cold-starts in 10 microseconds, and requires no runtime to install. The tool, currently at v0.0.4, is des…
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…
Vercel's open-source security review harness deepsec now supports one-command setup, allowing users to configure a repository and run its first security review with a single `npx deepsec init` command…
Vercel AI Gateway and Vercel Sandbox are now available on Hermes Agent, enabling access to 200+ models at no markup on tokens and isolated cloud microVM execution for agent commands. The integration a…
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 …
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…
In 60 coding-agent runs across three inference routes, patch footprint—the number of files a change touches—was the strongest predictor of success, beating every model-side variable measured. Local De…
Conductor 0.79.0, a cloud-focused update to the AI coding agent, introduces simplified onboarding, Vercel AI Gateway API key support, and an experimental Pierre editor for direct file editing in diffs…
A 60-run evaluation of coding agents found no quality winner among local DeepSeek V4 Flash, hosted DeepSeek via Vercel AI Gateway, and Claude Sonnet 5, with strict acceptance at 8/20, 9/20, and 5/20 r…
FLock has added DeepSeek V4 Flash to its OpenAI-compatible API Platform, offering developers access to a 284-billion-parameter mixture-of-experts model with a 1-million-token context window at discoun…
Vercel AI Gateway charges zero markup on provider list prices, while OpenRouter adds a 5.5% fee on credit purchases, but OpenRouter offers broader model coverage and more provider redundancy, accordin…
Thinking Machines' Inkling, a 975B total / 41B active MoE model with Apache 2.0 license and 1M context, is being trialed via a bash wrapper alias 'claude-inkling' that bridges Anthropic's CLI to the O…
A developer's two-week experiment with an M5 Max MacBook Pro with 128 GB of unified memory found that DeepSeek V4 Flash weights ran at 6 tokens per second under mainline llama.cpp but 30 to 40 tokens …
A developer evaluating AI gateways for multi-model routing found that per-call cost visibility is more important than model count. Direct provider SDKs require hardcoded prices that rot, while gateway…
A developer benchmarked time-to-first-token (TTFT) across AI gateways, finding LLM Gateway delivered the first content token 35% faster cold (906ms vs 1392ms) and 34% faster warm (814ms vs 1232ms) tha…
Ramp opened a closed beta for Ramp Router on July 20th, a gateway that directs AI requests across approved models and tracks costs, which the company says cut its internal large language model costs b…
Inkling, a decoder-only mixture-of-experts model with 1 trillion total parameters and 40 billion active per token, launched on Together Serverless, supporting native multimodal I/O and a reasoning_eff…
Hayden Bleasel, an expert developer from OpenAI, released Blume, an open-source, zero-config documentation framework that ships AI-ready docs from a Markdown folder. Blume version 1.0.3 is available o…