Free
$0/mo
$5 credits
Vercel's AI development platform. Prompts produce production-grade React, Next.js, and Tailwind code using shadcn/ui — from a single component to a full-stack app. The 2026 v0.app rebrand added a VS Code-style editor, Git, database integrations, and agentic workflows.
+Pros
- Best-in-class React/Next.js/Tailwind/shadcn code quality out of the box
- Image-to-code and Figma-to-code for fast UI prototyping
- One-click deploy to Vercel with live preview
- Three model tiers (Mini, Pro, Max) for cost–quality trade-offs
- Full-stack sandbox with VS Code-style editor and Git integration
−Cons
- Tightly coupled to the Vercel/React ecosystem — not suitable for non-JS stacks
- Credit-based pricing can add up quickly for complex, iterative projects
- Less suitable for backend-heavy or non-UI tasks
- Enterprise plan required for SSO and advanced compliance features
Pricing
Premium
$20/mo
More credits, v0 Pro model
Team
$30/user/mo
Team features
Business
$100/user/mo
Advanced features, audit logs
Enterprise
Custom
SOC 2, SAML SSO
v0 is Vercel's AI development platform for the web. Originally launched at v0.dev as a text-to-component generator in late 2023, it was rebranded to v0.app and significantly expanded in 2026 — adding a VS Code-style editor, Git integration, database connectors, and full-stack sandbox workflows. UI generation remains its core strength: prompts produce production-grade React, Next.js, and Tailwind code using shadcn/ui.
Under the hood, v0 runs on three proprietary models — v0 Mini, Pro, and Max — fine-tuned for React and frontend code. Users can drop screenshots or Figma frames to convert designs to code, iterate visually, and deploy to Vercel with one click. The 2026 platform update also added agentic workflows for multi-step generation and refactoring.
Key Features
• Prompt-to-UI: React + Next.js + Tailwind + shadcn/ui out of the box
• Image-to-code: upload screenshots or Figma designs and get code back
• v0 Mini / Pro / Max: three proprietary model tiers with different cost–quality trade-offs
• Full-stack sandbox: Git panel, VS Code-style editor, database integrations
• Agentic workflows: multi-step generation, refactoring, and iteration
• One-click deploy to Vercel; available as an API ($3 in / $15 out per Mtok)
• Enterprise: SOC 2, SAML SSO, audit logs
Version History
Claude Opus 4.7 Fast model option (2.5x faster output), agent browser screenshots visible during preview, ZIP file drag-and-drop support.
Run terminal commands in chat with permission prompts, 50% faster sandbox startup, 500MB less storage per sandbox, OAuth MCP server support.
Support for .riv file uploads, element screenshot attachment in design mode, simplified PR menu for git sync.
Team skills linking to design systems, zebra loader animation for previews, Plan agent now supports image generation, improved sidebar design.
Signature Snippet
v0 prompt: "Pricing page for a SaaS with three tiers, a feature comparison table, a faq, and a sticky CTA bar."
→ v0 generates a Next.js page using shadcn/ui components and Tailwind, deploys a live preview, and lets you push to GitHub or one-click deploy to Vercel.More in this Space
Prime Agent (Prime Intellect)
Prime Agent is an open-source (MIT) self-improving coding and research harness by Prime Intellect, built on a Recursive Language Model that runs inside a persistent IPython REPL and a Continual Harness that refines its own state via /refine. It took the same frontier weights from 30.2% to 95.5% on ARC-AGI-3 RHAE Best@1, powered daemon-backed sessions, and ships no hosted offering.
OpenCodeReview (ocr)
OpenCodeReview (ocr) is Alibaba's open-source AI code-review CLI. It reads git diffs and drives an LLM agent through a hybrid architecture where deterministic pipelines handle file selection, rule matching, and comment positioning while the agent does the reasoning. Built on two years of internal use at Alibaba scale, it ships a multi-language ruleset and consumes roughly 1/9 of the tokens of general-purpose agents.
Delta (by Zed)
Multiplayer environment from Zed for coding with agents. Threads unify the agent conversation, the code edits, and human review in one shareable artifact, replacing the branch/PR loop. Built on DeltaDB, a CRDT-based version control layer that records every edit between commits alongside the prompts and reasoning that produced them.