AI BriefingVercel Blog news
The latest AI and developer news from Vercel Blog, with short summaries.
Visit website →Vercel Routing Middleware Adds Python Support for FastAPI, Flask, and Django
The middleware runs as a separate ASGI or WSGI app before requests reach the application, allowing developers to rewrite, redirect, or answer them.
Vercel Excludes Skipped Monorepo Deployments from Rate Limits
Vercel now excludes automatically skipped monorepo deployments from rate limits, allowing teams to run more deployments within the same quota.
Token Pass Adds DeepSeek V4.1 Flash, Kimi K3, and GLM 5.3 via AI Gateway
The $30/month subscription grants $80 in monthly credit and supports coding agents like fx, Pi, and Cline with Zero Data Retention enabled by default.
Vercel Functions WebSocket support reaches general availability
The feature handles 15 million connections daily for AI chat and streaming apps, with CPU billed only for active processing time.
Vercel introduces durable-harness to make coding agents crash-resistant
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.
Vercel Updates Hobby and Pro Terms of Service Effective October 19, 2026
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.
Inception Mercury 3 Launches on AI Gateway with 50% Off Pricing
The model uses diffusion for parallel text refinement and supports a 1M-token context window for latency-sensitive workloads.
MiniMax M3.1 Flash available on AI Gateway for free until Oct 20
The open-weight multimodal model features a 1M-token context window and improved performance in coding and agentic tasks.
AI Gateway adds Sessions view to logs for tracking session affinity and cache efficiency
The new view groups requests by session to display cache hit rates, duration, and provider routing paths for coding agents like Claude Code and Codex.
DeepSeek V4.1 Flash 1017 now available on AI Gateway
The new model snapshot improves reasoning, coding, and agentic tasks while reducing output tokens and task completion time.
Elorian AI's Glimpse visual reasoning model now available on AI Gateway
The model accepts images and video to track objects and interpret spatial relationships, accessible via the model name elorian/glimpse.
Perplexity Decider V1.2 models now available on AI Gateway
The new multimodal decision models, Decider V1.2 27B and Decider Flash V1.2 4B, classify content and route requests via typed questions.
Reflection AI's Beam model now available on AI Gateway for free
Beam is a low-latency open-weight reasoning model with a 1M-token context window and Apache 2.0 license.
Vercel Shop GA: Open-source Next.js storefront for Shopify with agent-first shopping tools
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.
Liquid AI's d1-ultra decision model now available on AI Gateway
The multimodal model returns structured probabilities for classification and routing tasks rather than generating text.
Meta's Muse Spark Open now available on Vercel AI Gateway
The open-weight reasoning model supports text and image input with a 1M-token context window for coding and agentic workflows.
Vercel Connect adds Secure Compute routing for IP-allowlisted providers
Connectors can now use dedicated static IPs to reach providers like Salesforce and Snowflake that enforce IP allowlists.
Vercel AI Gateway adds Cat Jam reasoning model for coding in stealth
Cat Jam is free to use during its stealth period and supports function calling and structured outputs for agentic tasks.
Open-weight models process more than 70% of tokens and nearly one in four dollars in AI Gateway index
Open-weight model spend share more than quadrupled since June, while overall gateway spend grew 13x and average token prices fell 47%.
Vercel Connect adds MCP Events support in public beta
The update enables apps and agents to subscribe to webhook events from compatible MCP servers with automatic subscription renewal.