ElevenLabs on AI Gateway
Vercel’s AI Gateway now integrates 14 ElevenLabs audio models with a unified API, enabling real-time transcription, speech, music, and sound effects generation for applications.
SOURCE ARCHIVE · ORIGINAL LINKS INCLUDED
Vercel Blog coverage
Every ClipRaptor briefing sourced from Vercel Blog, with a direct link to the original publisher page. Page 1 of 6: briefings 1-30, published Oct 15, 2026 to Oct 27, 2026.
The fx adapter now runs the harness on the host
Vercel’s AI SDK fx adapter now executes the harness and model requests in the same process as the host application, improving efficiency while maintaining sandbox isolation for filesystem and shell operations.
Vercel Agent sessions now cost 67% less
Vercel reduced Agent session costs by 67% through token efficiency improvements in context management and prompt caching, now live without user action.
Deploy a container from a plain Dockerfile
Vercel now allows deploying a standalone Dockerfile or Containerfile without framework detection, routing traffic directly to the built image via the Container runtime in beta.
Discover 1000+ services on Vercel Connect from the CLI
Vercel’s CLI now lets users browse and search over 1,000 services in Vercel Connect directly from the terminal, with filtering and JSON output options.
Run Scale AI’s AgentEnv evals on Vercel Sandbox
Scale AI’s AgentEnv evaluation framework now integrates with Vercel Sandbox, enabling separate sandboxed execution of agents and tasks for improved testing and scoring.
Vercel Agent can now validate alerts before paging
Vercel Agent now validates alerts before sending them to paging systems, reducing noise by filtering only critical incidents for Pro and Enterprise users with Observability Plus.
Create custom monitors in Vercel Observability
Vercel introduces custom monitors in Observability to generate alerts based on specific query results, supporting metrics like AI Gateway costs and Core Web Vitals, with options for anomaly detection or fixed thresholds.
Customizable widgets for project cards
Vercel’s dashboard now allows teams to customize which metric appears on each project card, replacing the fixed Real Experience Score with selectable options like firewall activity or traffic.
GPT-6.1 Terra now available on AI Gateway
OpenAI’s GPT-6.1 Terra model is now accessible via Vercel’s AI Gateway, offering enhanced visual reasoning, coding, and document processing capabilities with broad API compatibility.
Vercel CLI adds Spend Management
Vercel CLI introduces Spend Management features, allowing teams to monitor budgets, view alerts, and pause deployments via command-line tools.
How Vercel Agent accesses production safely
Vercel Agent introduces a permission-first workflow for production actions, requiring users to approve proposed plans before granting access, reducing risk of unintended changes.
Deployments now show build cache size
Vercel deployments now display build cache size and usage limits in summaries, CLI, and API to help users monitor storage and billing.
Vercel Connect adds managed Stripe API keys
Vercel Connect now generates restricted Stripe API keys for each agent or task, replacing the need to use a single full-access key across projects.
How Interfaze serves 50 million requests a month on Vercel
Interfaze, a provider of deterministic AI models for document processing and classification, migrated its entire stack to Vercel to handle 50 million monthly requests, including API routing, sandbox execution, and...
Kimi K3.1 Pro and Kimi K3.1 Pro Highspeed are available now in AI Gateway
Vercel’s AI Gateway now hosts Moonshot AI’s Kimi K3.1 Pro and K3.1 Pro Highspeed models, expanding coding, finance, and agentic task capabilities with a 1M-token context window.
Death to long-lived static credentials
Vercel is phasing out long-lived static credentials in favor of short-lived OIDC tokens to reduce security risks from credential leaks and supply-chain attacks across its platform and Marketplace integrations.
Deploy without an account using Vercel CLI
Vercel has introduced a feature allowing users to deploy applications without an account via the Vercel CLI, enabling faster prototype sharing with temporary live URLs.
Routing Middleware now supports Python
Vercel now allows Python-based routing middleware for frameworks like FastAPI and Flask, enabling request rewrites, redirects, or responses before they reach the main application.
Baseten's Mammoth-1 and Elephant-1 now available on AI Gateway for free
Baseten’s Mammoth-1 and Elephant-1 decision models are available for free on AI Gateway through October 27, offering text classification and routing with 16k-token context windows.
Skipped monorepo deployments no longer count against limits
Vercel will no longer count automatically skipped monorepo deployments toward rate limits, increasing deployment capacity for teams using monorepos.
Mercury 3 now available on AI Gateway
Vercel’s AI Gateway now offers Mercury 3 from Inception at a 50% launch discount, featuring diffusion-based text generation with over 1,000 tokens per second and a 1M-token context window.
MiniMax M3.1 Flash now available on AI Gateway for free
Vercel’s AI Gateway now offers MiniMax M3.1 Flash at no cost until October 22, providing a 1M-token context window for coding and agentic tasks before reverting to standard pricing.
AI Gateway logs now show session affinity
Vercel’s AI Gateway now groups AI requests into sessions in logs, showing how session affinity routes each turn and improving cache efficiency for repeated prompts.
DeepSeek V4.1 Flash 1017 now available on AI Gateway
Vercel’s AI Gateway now offers DeepSeek V4.1 Flash 1017, an updated model improving reasoning, coding, agentic tasks, and image understanding with faster task completion and shorter outputs.
Vercel and Shopify make agents first-class shoppers
Vercel and Shopify launched Vercel Shop, an open-source Next.js storefront template for Shopify, enabling storefronts optimized for human, search engine, and agent interactions with machine-readable product data.
Elorian AI's Glimpse now available on AI Gateway
Elorian AI’s Glimpse visual reasoning model is now accessible via Vercel’s AI Gateway, enabling image and video analysis with object tracking and spatial reasoning.
Perplexity's Decider V1.2 models now available on AI Gateway
Perplexity’s Decider V1.2 models, including a 27B and a 4B variant, are now accessible via AI Gateway for decision-making tasks such as routing, scoring, and classification.
Reflection AI's Beam now available on AI Gateway for free
Reflection AI’s Beam reasoning model is now accessible for free via AI Gateway during its launch period, offering low-latency coding and agentic tasks with adjustable parameters.
Vercel Ship 2026 recap
Vercel Ship 2026 unveiled agent-focused infrastructure updates, including Python support, AI Gateway controls, and persistent agent workspaces, alongside BYOC on AWS and enterprise authorization features.