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…
Vercel and Herdr have launched a plugin that lets terminal coding agents like Claude Code, Codex, and OpenCode run in isolated Vercel Sandboxes, orchestrated from Herdr's tmux-style manager. The plugi…
Agent Plugins 1.0.0, an open, vendor-neutral standard for plugins that extend AI agents, is now publicly available. The format, initiated by Vercel and refined with AWS, Anysphere, GitHub, Microsoft, …
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…
Agent Plugins 1.0.0, an open, vendor-neutral standard for packaging Agent Skills and MCP servers into portable plugins, is now available, supported by ChatGPT, Codex, Cursor, GitHub Copilot, Kiro, and…
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 Marketplace integrations now automatically install provider agent skills from skills.sh when installed via the Vercel CLI, enabling agents to use the integrated services. The update also intr…
Vercel's AI Gateway now generates an OpenTelemetry trace for every request, allowing Pro and Enterprise teams to export traces via Vercel Drains to OTLP/HTTP-compatible endpoints such as Braintrust, D…
AI Gateway, a product by Vercel, is now available on AWS Marketplace, allowing teams to procure it through their existing AWS account and consolidate inference spend onto their AWS bill. Purchases are…
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…
Vercel has made all Sandbox firewall features available on its free Hobby plan, enabling developers to control outbound network traffic with allow-all, deny-all, or custom policies based on domain, IP…
Vercel has launched a new feature allowing users to search for and purchase domains directly from its dashboard, with automatic nameserver configuration for projects. The feature is accessible via the…
Vercel Sandbox now supports Devin Outposts, allowing each Devin session to execute in an isolated Sandbox microVM with session orchestration and command execution running in the user's Vercel project.…
Vercel's AI Gateway is offering DeepSeek V4 Flash at a 90% discount through Novita for Vercel Pro customers until August 11, with the model accessible via the identifiers deepseek/deepseek-v4-flash or…
Vercel WAF for Blob is now generally available and supported for production use on all plans, with existing beta rules carrying over unchanged. The firewall protects Blob stores with custom rules that…
Factory, an AI-powered software development platform, runs its entire cloud backend on Vercel's Next.js, handling tens of millions of daily API requests with a p95 response time of 350ms or below, wit…
Factory, an AI-powered software development platform, scaled its cloud backend on Vercel to serve one billion daily API requests with a p95 response time of 350ms or below, without a dedicated infrast…
Vercel's AI Gateway now supports Qwen 3.8 Max, a 2.4-trillion-parameter model handling text and vision tasks with a 1-million-token context window. The model, accessed via model ID alibaba/qwen3.8-max…
Vercel's AI Gateway now supports spend budgets scoped to teams, projects, or API keys, allowing dollar limits that halt requests when exceeded. Budgets can be set via the dashboard or CLI, with option…
Vercel's AI Gateway now serves DeepSeek V4 Flash with updated weights by default, boosting its Terminal-Bench score to 82.7, up 25.8 points from 56.9 in the April preview. Requests to `deepseek/deepse…