MiniMax M3 on AI Gateway
MiniMax M3, the company's first model with a 1M-token context window and native multimodality, is now available on Vercel AI Gateway. The model, built around MiniMax Sparse Attention, improves softwar…
MiniMax M3, the company's first model with a 1M-token context window and native multimodality, is now available on Vercel AI Gateway. The model, built around MiniMax Sparse Attention, improves softwar…
Vercel launched BotID, a tool that verifies requests to AI endpoints come from real browsers before inference runs, using an invisible CAPTCHA and server-side classification to block automated clients…
Inference theft attacks on AI endpoints are surging, with attackers using residential proxies and adapters to steal expensive model calls for resale at a fraction of the cost. Vercel reported a single…
Vercel detected a surge in unauthorized AI inference usage on April 12, 2026, when traffic to its docs AI chat endpoint spiked to roughly ten times normal volume, reaching 1,300 requests per minute an…
Vercel Sandbox now supports installing and running Docker inside a sandbox, enabling agents to build containers, install system packages, and modify files without affecting the host system. This featu…
Claude Opus 4.8 is now available on Vercel AI Gateway, designed for long-horizon agentic execution and complex multi-step coding tasks. The model handles refactors that previously required human corre…
AI Gateway has launched a team-wide provider allowlist that restricts which AI providers can serve requests, enforcing approved-vendor routing at the gateway level for all traffic including BYOK. The …
Conductor, a multi-agent IDE startup founded by former Vercel employee Charlie Holtz, launched Cloud Workspaces built on Vercel Sandboxes to enable developers to run multiple parallel coding agents re…
Firecrawl has joined the Vercel Marketplace, enabling Vercel teams to integrate structured web data into AI agents and applications without managing crawling infrastructure. The integration allows dev…
Vercel released a new CLI command, `vercel alerts`, enabling users to list and view details of anomaly alerts for a team or project directly from the terminal. The command displays each alert's start …
Alibaba's Qwen 3.7 Max model is now available on Vercel AI Gateway, offering capabilities in coding, office workflow automation, and long-horizon autonomous execution. The model features improvements …
Grok Build 0.1, a beta coding model trained for agentic coding, is now available on Vercel AI Gateway in early access. The model powers the Grok Build CLI app and can be accessed by setting the model …
Chat SDK now includes a built-in AI SDK toolset accessible via the new `chat/ai` subpath, enabling developers to integrate read and write actions into their agents with a single `createChatTools(chat)…
Vercel released an AI Gateway plugin for WordPress that provides access to hundreds of AI models from over 40 providers through a single API key. The plugin integrates with the new WordPress AI Client…
The Nuxt MCP Toolkit now supports MCP apps, enabling agent tools to return interactive HTML responses rendered inline by clients like Claude and ChatGPT instead of plain text. Developers can declare t…
Vercel has added Gemini 3.5 Flash to its AI Gateway, offering developers access to the model with improved coding proficiency, reasoning, and multi-turn coherence. The model defaults to a medium think…
Anthropic and Vercel launched a new integration allowing developers to run Claude Managed Agents within Vercel Sandbox, providing isolated execution environments for AI agent tool calls. The setup run…
Vercel has added a new sorting feature to AI Gateway that allows developers to rank model providers by cost, latency (time to first token), or throughput (tokens per second). The sorting is computed a…
Vercel has introduced natural language support for its Firewall, allowing users to create WAF custom rules by describing the desired behavior in plain text. The feature generates rules that can log, b…
Vercel has released fast mode for Claude Opus 4.7 on AI Gateway in research preview, delivering approximately 2.5 times faster output token generation while maintaining full Opus 4.7 intelligence. The…