AI Briefing#vercel
The latest AI and developer news about #vercel, with the original source and a short summary.
The latest AI and developer news about #vercel, with the original source and a short summary.
The platform uses Vercel Fluid compute for scalable backend processing and AI Gateway to route traffic across multiple model providers to ensure reliability.
The new Managed API Key option lets Vercel generate and store scoped credentials, eliminating the need to paste secrets and allowing rotation without redeployment.
The system requires users to approve a specific plan and its requested scopes before the agent gains write access to production resources.
Temporary deployments use the tmp.now domain and require claiming within one hour to keep the project live.
A survey of over 1,000 SaaS vendors found only 8.4% support secure authentication, prompting Vercel to enforce OIDC standards to replace static credentials.
The eligible TLD count for the one-year free domain offer has increased to sixteen, including .co, .studio, .company, .info, .pro, .live, .digital, and .agency.
The middleware runs as a separate ASGI or WSGI app before requests reach the application, allowing developers to rewrite, redirect, or answer them.
Vercel now excludes automatically skipped monorepo deployments from rate limits, allowing teams to run more deployments within the same quota.
The feature handles 15 million connections daily for AI chat and streaming apps, with CPU billed only for active processing time.
The new form factor supports Express, Hono, Fastify, and Next.js apps, handling up to 128 concurrent requests per environment with CPU-based billing.
The open-source package extends durability to Pi, OpenCode, Codex, and Claude Code by logging every step to a durable backend, ensuring agents resume from the exact point of failure without repeating completed model calls.
The update clarifies that plan-included credits expire at the end of the subscription term while purchased credits expire one year after purchase, and grants UK and EU consumers the right to cancel free of charge if service changes have a more than minor negative impact.
The model uses diffusion for parallel text refinement and supports a 1M-token context window for latency-sensitive workloads.
The open-weight multimodal model features a 1M-token context window and improved performance in coding and agentic tasks.
The new model snapshot improves reasoning, coding, and agentic tasks while reducing output tokens and task completion time.
The model accepts images and video to track objects and interpret spatial relationships, accessible via the model name elorian/glimpse.
Beam is a low-latency open-weight reasoning model with a 1M-token context window and Apache 2.0 license.
The open-source template integrates Shopify’s rebuilt Hydrogen SDK and the Universal Commerce Protocol to let AI agents read product data and build carts directly.
The open-weight reasoning model supports text and image input with a 1M-token context window for coding and agentic workflows.
Connectors can now use dedicated static IPs to reach providers like Salesforce and Snowflake that enforce IP allowlists.
Cat Jam is free to use during its stealth period and supports function calling and structured outputs for agentic tasks.
Open-weight model spend share more than quadrupled since June, while overall gateway spend grew 13x and average token prices fell 47%.
The update enables apps and agents to subscribe to webhook events from compatible MCP servers with automatic subscription renewal.
Pro teams can subscribe for $30 per month to receive $80 in shared credit for coding agents using GLM 5.3 and Kimi K3.