Explorer Tier

Venice is pleased to offer trial API access to our Pro users free of charge with constrained rate limits, to support exploration of our services and testing of our API with their application.

Paid access to the Venice API can be obtained in two ways:

1

Purchased API Credits

Users can purchase API credits via the API Dashboard.

2

Stake VVV

Users can stake VVV which in return, provides you proportional access to Venice’s compute pool in “Venice Compute Units” or VCUs. The more you stake, the higher your VCU allocation, and they renew daily. You also earn staking rewards while staked. Visit the Token Dashboard to stake VVV and to see how much VCU you control.

Model Pricing

Chat Models

Chat models are priced per million tokens, with separate pricing for input and output tokens. While the price is per million tokens, you will only be charged for the tokens you use. You can estimate the token count of a chat request using this calculator.

ModelInput Tokens (per M.)Input Tokens (per M.)Output Tokens (per M.)Output Tokens (per M.)
Llama 3.2 3B
1.5 VCU$0.156 VCU$0.60
Qwen 2.5 Coder 32B
Qwen 2.5 QWQ 32B
Mistral Small 3.1 24B
5 VCU$0.5020 VCU$2.00
Llama 3.3 70B
Dolphin 72B
Deepseek R1 70B
Qwen 2.5 VL 72B
7 VCU$0.7028 VCU$2.80
Llama 3.1 405B
15 VCU$1.5060 VCU$6.00
DeepSeek R1 671B
35 VCU$3.50140 VCU$14.00

Image Models

All Venice Image models are currently priced at the following rates:

ModelOne 1024x1024 ImageOne 1024x1024 Image
All0.1 VCU$0.01 USD

Audio Models

All Venice Audio models are currently priced at the following rates:

ModelInput Characters (per M.)Input Characters (per M.)
All35 VCU$3.50 USD