← All sources

Vercel Blog news

The latest AI and developer news from Vercel Blog, with short summaries.

Visit website →

AI Gateway adds Browserbase Search and Fetch tools

The tools are available in AI SDK 7.0.116 and later, allowing models to access current web information via a single API key.

·2026.09.30 09:00

Vercel Renames Edge Requests to CDN Requests

Pricing, limits, and measurement methods remain unchanged despite the rebranding.

·2026.09.30 09:00

InclusionAI's Ling 3.1 Flash now available on AI Gateway

The model is free to use through October 13, 2026.

·2026.09.30 09:00

Vercel Sandbox Adds Secure Compute Support for Dedicated Network Connectivity

Vercel Sandbox now supports Secure Compute, enabling Enterprise teams to connect sandboxes to dedicated networks for private AWS VPC access via peering.

·2026.09.30 09:00

Vercel CDN Stops Caching Responses with Vary: Cookie

Responses with Vary: Cookie now return x-vercel-cache: MISS and vary_key_denied:cookie in logs.

·2026.09.30 09:00

Vercel Connect Now Accepts Service Submissions for Connector Directory

Developers can now submit their own services to the Vercel Connect directory via a four-step process involving OAuth or API key verification.

·2026.09.29 09:00

Vercel AI Gateway Adds OpenAI GPT-6.1 Sol for Coding and Agentic Workflows

GPT-6.1 Sol offers lower standard pricing than GPT-6 Astra and improved performance for complex document reading and multi-step workflows.

·2026.09.29 09:00

Vercel CLI adds terminal search for trace spans

The new vercel traces search command returns up to 100 spans from the last hour by default, supporting filters via KQL and JSON output for automation.

·2026.09.29 09:00

Vercel enables unauthenticated domain search and pricing checks via CLI and API

The Domains Registrar API allows checking up to 200 exact domain names for availability and pricing in a single request without authentication.

·2026.09.28 09:00

Anthropic's Claude Sonnet 5.5 Now Available on AI Gateway

The model supports Zero Data Retention and integrates with the AI SDK, OpenAI-compatible APIs, and Anthropic Messages API.

·2026.09.28 09:00

Fireworks Releases Ember-1 Reasoning Model on AI Gateway

Ember-1 is a research preview model built on Kimi K3 that reportedly generates 40% fewer tokens than its base model.

·2026.09.27 09:00

Vercel AI Gateway adds Pixel Canary model in stealth mode with free access

Pixel Canary matches GPT-6 Astra's 90.3% success rate on Next.js evals and is free for a limited time.

·2026.09.25 09:00

Vercel Container Registry Adds GitHub OIDC Login Action for Credential-Free Image Pushes

The new vercel/vcr-action/login action exchanges GitHub OIDC tokens for short-lived Vercel access tokens, eliminating the need for stored registry credentials.

·2026.09.25 09:00

Vercel Sandbox Adds Memory Observability to Dashboard and CLI

The new feature includes P75 and P95 memory metrics in the dashboard and exposes memoryUsedBytes data via the vercel metrics CLI command.

·2026.09.25 09:00

skills.sh Registry Hits One Million Agent Skills in Seven Months

The registry recorded nearly 280 million installs, with cross-industry skills accounting for 87.5% of all downloads.

·2026.09.25 09:00

Klaviyo Ships 356 Internal Apps in Two Weeks Using Vercel Platform

512 employees, including non-technical staff in legal and HR, deployed 356 apps, with 196 being full-stack applications connected to Klaviyo's databases.

·2026.09.24 09:00

Vercel Launches Unified Public Bug Bounty Program on HackerOne

The new program covers all Vercel products and open-source projects, consolidating previous private and OSS initiatives.

·2026.09.24 09:00

Vercel Connect Adds Support for TanStack AI

TanStack AI agents can now call OAuth-protected MCP servers without authentication via Vercel Connect.

·2026.09.24 08:00

AI Gateway Adds Two Gemini 3.8 TTS Models

Two models supporting over 100 languages and speaker control are now available via the unified API.

·2026.09.23 09:00

Vercel Removes Blob Store Creation Limits Across All Plans

Store creation costs $5 per million on the Pro plan, while the existing usage-based billing structure remains in place.

·2026.09.23 09:00