v0 Mini
AI model · Language model (LLM) · Text → Text by v0
Lightning-fast speed with near-frontier intelligence for rapid web development.
v0 Mini is a lightning-fast AI model for web development, designed for rapid UI iterations and code fixes with near-frontier intelligence. It offers the most cost-effective entry point for developers using the v0 platform, with tiered pricing starting at $0.10 per million input tokens.
Model specs
The full spec card (context, pricing per token, modalities and more) on AntSpace. Sign up free to see the full spec card.
- Languages
- English
Category: Generative AI
- Sizes and variants
- v0 Mini, v0 Pro, v0 Max, v0 Max Fast
- Access
- v0 chat interface, iOS app, and Vercel platform
- Base Input Price
- $0.10 / 1M tokens
- Base Output Price
- $0.50 / 1M tokens
- Base Cache Write Price
- $0.125 / 1M tokens
- Base Cache Read Price
- $0.01 / 1M tokens
- Lightning-fast speed with near-frontier intelligence
- Input pricing from $0.10 per 1M tokens
- Output pricing from $0.50 per 1M tokens
- Integrated into v0 chat and iOS app for rapid UI iteration
Overview
v0 Mini is a high-speed language model developed by Vercel for the v0 platform, designed to serve as a collaborative AI assistant for designing and scaling full-stack web applications. It is optimized for rapid iterations, offering lightning-fast generation speeds with intelligence levels that approach frontier models. The model is particularly suited for quick edits, simple component generation, and users seeking a cost-effective way to build without the latency of larger models. v0 Mini is integrated into the v0 chat interface and the v0 iOS app, allowing developers to iterate on UI and code fixes on the go. It features a tiered pricing structure that rewards lower-volume usage with highly competitive token rates.
Performance and Integration
- Lightning-fast speed: The model is designed for lightning-fast generation speeds while maintaining intelligence levels approaching frontier models.
- Rapid iteration: It provides a cost-effective solution for rapid UI iterations and small code fixes.
- Chat integration: The model is integrated directly into the v0 chat interface for collaborative application design.
Standard Token Pricing
- Base input rate: Standard input is priced at $0.10 per 1 million tokens for the first 272,000 tokens.
- Base output rate: Standard output is priced at $0.50 per 1 million tokens for the first 272,000 tokens.
- Cache write pricing: Cache write operations are billed at $0.125 per 1 million tokens.
- Cache read pricing: Cache read operations are billed at $0.01 per 1 million tokens.
Volume Pricing Tier
- Tiered input rate: Input pricing adjusts to $0.20 per 1 million tokens for usage exceeding 272,000 input tokens.
- Tiered output rate: Output pricing adjusts to $0.75 per 1 million tokens for usage exceeding 272,000 tokens.
- Tiered cache write rate: Cache write pricing adjusts to $0.25 per 1 million tokens above the 272,000 token threshold.
- Tiered cache read rate: Cache read pricing adjusts to $0.02 per 1 million tokens above the 272,000 token threshold.
Use cases
- Developers use v0 Mini for rapid UI iterations to quickly visualize and adjust web components.
- Engineers perform small code fixes and edits using the model's high-speed generation capabilities.
- Mobile developers build on-the-go by accessing v0 Mini through the integrated iOS app.
- Users on the Free plan utilize v0 Mini as a cost-effective collaborative assistant for full-stack applications.
Pricing
- v0 Mini Input (up to 272K tokens)
- $0.10 per 1M tokens
- v0 Mini Output (up to 272K tokens)
- $0.50 per 1M tokens
- v0 Mini Input (above 272K tokens)
- $0.20 per 1M tokens
- v0 Mini Output (above 272K tokens)
- $0.75 per 1M tokens
Specifications
- Sizes and variants
- v0 Mini, v0 Pro, v0 Max, v0 Max Fast
- Access
- v0 chat interface, iOS app, and Vercel platform
- Base Input Price
- $0.10 / 1M tokens
- Base Output Price
- $0.50 / 1M tokens
- Base Cache Write Price
- $0.125 / 1M tokens
- Base Cache Read Price
- $0.01 / 1M tokens
- Volume Input Price (>272K)
- $0.20 / 1M tokens
- Volume Output Price (>272K)
- $0.75 / 1M tokens
- Volume Cache Write Price (>272K)
- $0.25 / 1M tokens
- Volume Cache Read Price (>272K)
- $0.02 / 1M tokens
FAQ
If I send a message, where does that usage come from?
Usage comes from included monthly credits ($30 for Plus/Business) or free daily credits ($2 on login). If these are exhausted, usage is billed based on the specific model's token rates.
How does the volume pricing for v0 Mini work?
v0 Mini pricing for the first 272K input tokens is $0.10 for input and $0.50 for output per 1M tokens. Above 272K, it increases to $0.20 for input and $0.75 for output.
Is there a free way to use v0 models?
Yes, v0 offers a Free plan with a 7 message per day limit, which includes access to the v0 model for deploying apps to Vercel and using Design Mode.
Added by AntSpace from public sources (v0.app).