About Venice

Welcome to Venice.ai’s API documentation! Our API enables you to harness the power of advanced AI models for text and image generation while maintaining the highest standards of privacy and performance.

​

Venice’s Values

• Privacy-First Architecture: Built from the ground up with user privacy as a core principle. Venice does not utilize or store user data for any purposes whatsoever.

• Open-Source: Venice only utilizes open-source models to ensure users have full transparency into the models they are interacting with.

• OpenAI API Compatible: Seamless integration with existing OpenAI clients using the Venice API base URL.

​

What Can I do with Venice API?

• Chat: Prompt any of the supported models directly for simple chat applications with custom parameters and configurations. Use default settings, or customize as deeply as you prefer.

• Generate Images: Use the image models to generate new images from a simple prompt, or modify images with “inpainting”.

• Assist with Coding: Prompt models for coding related outputs or integrate the Venice API into your preferred IDE or Visual Studio Code plugin.

• Transcribe Audio (BETA): Use Venice’s new Voice models to transcribe text into Voice using your preferred “speaker”.

• Analyze Documents: Send images or PDF documents for interpretation, analysis or summarization.

• Interact with Characters: Chat with your favoritate Venice characters through the API.

• Anything you can imagine: The Venice API has no bounds. Tie the API into your preferred integration using the API base URL and build anything you can imagine and code.

​

Accessing the API

Venice users can access the API in 3 ways:

1. Pro Account: Users with a PRO account will gain access to the Venice API within the “Explorer Tier”. This tier has lower rate-limits, and is intended for simple interaction with the API.

2. VCUs: With Venice’s launch of the VVV token, users who stake tokens within the Venice protocol gain access to a daily AI inference allocation (as well as ongoing staking yield). When staking, users receive VCUs, which represent a portion of the overall Venice compute capacity. You can stake VVV tokens and see your VCU allocation here. Users with positive VCU balance are entitled to “Paid Tier” rate limits.

3. USD: Users can also opt to deposit USD into their account to pay for API inference the same way that they would on other platforms, like OpenAI or Anthropic. Users with positive USD balance are entitled to “Paid Tier” rate limits.

​

API settings

Venice recognizes that users may be integrating with various applications and require API key separation and usage limitation. Venice now offers the following settings for API Keys:

1. Administrator Settings: Users can create new API keys directly through the API, reducing the need for UI interactions.

2. Expiration Time: Users can set a date for API keys expiration.

3. Usage Limits: Users can set daily VCU or USD limits per API key.

​

Resources

​

Start Building

These docs are open source and can be contributed to on Github by submitting a pull request. Here is a simple reference guide for “How to use Venice API”