AI BriefingVercel Blog news
The latest AI and developer news from Vercel Blog, with short summaries.
Visit website →xAI's Grok Imagine Video 1.5 Lite Now Available on AI Gateway
The lightweight model generates 1-15 second video clips with native audio in resolutions up to 1080p.
Vercel Adds skipMiddlewareRequestBody to Reduce Routing Middleware Overhead
The new configuration option reduces Fast Origin Transfer usage and improves time to first byte by preventing request bodies from being sent to Routing Middleware.
Vercel Sandbox creation now returns a ready sandbox
Snapshot restoration time now counts toward creation, adding about 50 ms to p50 latency but eliminating wait times for the first operation.
Step 5 Preview now available on AI Gateway
StepFun's flagship model supports text and image input with a 1M-token context window for agentic coding and analysis.
Microfrontends Routing becomes free for WAF-mitigated traffic
The change applies automatically to every project using microfrontends, joining CDN Requests and Fast Data Transfer which were already free for this traffic.
OpenAI Decisions API now available on AI Gateway
The API supports decision models like GPT-6 Luna Decisions and requires OpenAI SDK 7.30.0+ (JS) or 3.26.0+ (Python).
Anthropic's Claude Haiku 5.5 Now Available on AI Gateway
The model introduces effort levels and adaptive thinking, supporting low to max settings to control token usage and reasoning depth.
Vercel AI Gateway Adds Glyph Cluster Reasoning Model for Free During Stealth Period
The model is free for Pro and Enterprise teams with purchased AI Gateway credits but lacks Zero Data Retention support.
Vercel Flags Adds Support for Timestamp Attributes in Entity Targeting
Developers can now configure timestamp attributes for entities to enable time-based targeting rules such as 'is after' or 'is before'.
AI Gateway adds confidence-based decision fallbacks
The new beta feature escalates requests to a fallback model when primary answers fail user-defined confidence thresholds, billing both stages.
Google's Nano Banana 2.1 now available on AI Gateway
The model offers Flash-tier latency and cost while improving image generation and editing capabilities.
Mistral Large 4 now available on AI Gateway
Users can access the open-weight, multimodal model via a single API key without a separate Mistral account.
FLUX 3 Image now available on AI Gateway
The model supports up to ten reference images for editing and five resolution tiers up to 4K.
OpenAI Ultrafast mode now available on AI Gateway
The service tier costs 6× the standard per-token rate and supports US and global processing.
Vercel Releases AI SDK for Python with Experimental Jev evaluate() API
The new SDK allows Python developers to use Jev, a universal classifier model, via the experimental evaluate() function.
Rogo ships agent-written code to production in 5 minutes on Vercel
The team now pushes more than 73,000 deployments a month using six production AI agents.
Speed Insights Deprecates First Input Delay on November 1st
The deprecation does not require user changes, affect scores, or block access to existing FID data.
Laya decision model available on AI Gateway, free through October 31
The Laya evaluation model from Convai Innovations is free to use via Boundless on AI Gateway until October 31, 2026.
Vercel AI Gateway adds Microsoft MAI voice and transcription models
The integration includes MAI-Voice-2.1, MAI-Voice-2.1-Flash, and MAI-Transcribe-2 Streaming with no platform fee or markup on inference.
Vercel Agent Supports Private Package Installation from npm and Custom Registries
Vercel Agent now supports installing private dependencies from npm and custom registries using credentials stored as shared environment variables.