Backends on Vercel: Python, containers, and Daemons
Vercel expands backend support with Python general availability, containerized Functions, and Daemons for background workers, integrating with existing workflows and services.
SOURCE ARCHIVE · ORIGINAL LINKS INCLUDED
Vercel Blog coverage · page 2
Every ClipRaptor briefing sourced from Vercel Blog, with a direct link to the original publisher page. Page 2 of 6: briefings 31-60, published Oct 06, 2026 to Oct 15, 2026.
Vercel Daemons is now in public beta
Vercel has launched Vercel Daemons in public beta, enabling long-running background processes without HTTP servers, integrating with queues and CI systems while running on Fluid compute.
Vercel for Enterprise
Vercel launched Enterprise Apps and Agents to centralize governance for AI-powered development across engineers and citizen developers while maintaining security and compliance.
Introducing Vercel Drives: persistent storage for agents
Vercel introduces Vercel Drives, a persistent storage solution for agents that maintains file continuity across different execution environments in Vercel Sandbox.
Python on Vercel is now generally available
Vercel announced general availability of Python support, enabling developers to deploy Python applications with automatic framework detection and shared workflows for frontend-backend projects.
Findings from the $1M Vercel Sandbox challenge
Vercel’s $1M Sandbox challenge uncovered a Linux kernel zero-day allowing sandbox escapes, prompting immediate fixes and broader security upgrades across shared cloud infrastructure.
Amazon S3 joins the Vercel Marketplace
Vercel integrates Amazon S3 into its Marketplace, enabling direct resource creation and connection within Vercel projects using OIDC authentication and environment variables.
Nemotron 3.5 Lightning now available on AI Gateway for free
NVIDIA’s Nemotron 3.5 Lightning reasoning model is now freely accessible via Vercel’s AI Gateway, offering a 30B-parameter hybrid architecture with a 1M token context window and tool-calling support.
Drama 3 now available on AI Gateway
Vercel’s AI Gateway now offers Drama 3 from Fish Audio at an 80% discount for 30 days, enabling scripted voice direction via natural-language prompts for multi-speaker audio projects.
Gemini 4 Argon now available on AI Gateway
Vercel’s AI Gateway now supports Google’s Gemini 4 Argon model, expanding coding, agentic, and reasoning capabilities with a 1M token context window and multi-modal input support.
Repository checkout and Git LFS downloads are now faster
Vercel reports faster repository checkouts and Git LFS downloads, cutting average setup time by 20% overall and 54% for LFS projects, with no user action required.
Muse Wonder now available on AI Gateway
Meta’s Muse Wonder coding and agent model is now accessible via Vercel’s AI Gateway, enabling multi-step task execution and large-context processing without a separate Meta account.
Agents can now buy domains with the Vercel CLI
Vercel’s CLI now lets agents search, check, and buy domains while keeping final purchase approval with users, ensuring controlled spending.
Deployment Storage billing begins for existing Pro teams
Vercel will begin billing Pro teams for Deployment Storage and Functions Storage at $0.10 per GB-month, with a new 30-day retention window starting October 23.
New Pro teams now default to 30-day deployment retention
Vercel Pro teams now retain deployments for 30 days by default, reducing storage costs while keeping recent history accessible for inspection or rollback.
How Rillet ships 3× faster with AI agents on Vercel
Rillet, an AI-native ERP platform, accelerated software delivery threefold by deploying AI agents on Vercel, reducing customer request fulfillment from days to hours.
Liquid AI's d1 is available on AI Gateway
Vercel’s AI Gateway now supports Liquid AI’s d1 decision model for structured evaluations, including vision-based classification, via multiple API formats.
Skip sending request bodies to Routing Middleware
Vercel introduced a setting to skip sending request bodies to Routing Middleware, reducing Fast Origin Transfer usage and potentially improving response times for large payloads.
Vercel Sandbox creation now returns a ready sandbox
Vercel Sandbox creation now completes before commands or file operations begin, reducing initial wait time and surfacing startup errors immediately.
FLUX 3 Image now available on AI Gateway
Vercel’s AI Gateway now integrates Black Forest Labs’ FLUX 3 Image model, enabling text-to-image generation and image editing without requiring a separate account.
Grok Imagine Video 1.5 Lite on AI Gateway
xAI’s lightweight Grok Imagine Video 1.5 Lite model is now accessible via Vercel’s AI Gateway, enabling text-to-video and image-to-video generation with native audio in multiple resolutions and aspect ratios.
OpenAI Ultrafast mode now available on AI Gateway
Vercel’s AI Gateway now supports OpenAI’s Ultrafast tier for GPT 6 Astra and GPT 6.1 Sol, enabling faster responses for interactive and coding workflows with tiered billing.
Step 5 Preview now available on AI Gateway
Vercel’s AI Gateway now supports Step 5 Preview, StepFun’s model optimized for coding and analysis, with a 1M-token context window and no platform fees on inference.
Claude Haiku 5.5 now available on AI Gateway
Anthropic’s Claude Haiku 5.5 is now accessible via Vercel’s AI Gateway, offering faster, cost-efficient subagent capabilities with adjustable reasoning effort levels and zero data retention.
Glyph Cluster is now available in stealth for free on AI Gateway
Vercel’s AI Gateway now offers Glyph Cluster as a free stealth model for Pro and Enterprise teams, enabling advanced coding and reasoning tasks without image input or structured outputs.
OpenAI Decisions API now available on AI Gateway
OpenAI’s Decisions API is now accessible via AI Gateway’s OpenAI-compatible endpoint, enabling structured decision-making without text generation.
Timestamp attributes are now supported in Vercel Flags
Vercel Flags now allows targeting by date and time using timestamp attributes, enabling time-based campaign and user segmentation through dashboard or CLI configurations.
AI Gateway adds confidence-based decision fallbacks
Vercel’s AI Gateway now supports confidence-based fallback models to reroute requests when primary model responses fail preset confidence thresholds, with billing applying to both decision stages.
Mistral Large 4 now available on AI Gateway
Vercel’s AI Gateway now supports Mistral Large 4, enabling multimodal reasoning via a single API key without requiring a separate Mistral account.
Nano Banana 2.1 now available on AI Gateway
Google’s Nano Banana 2.1 image model is now accessible via Vercel’s AI Gateway, enhancing editing and generation with improved realism and precision.