Pricing
Explorer Tier
Venice is pleased to offer trial API access to our Pro users free of charge, initially, as users want to test the API with their application. Call limits are relatively low, but it’s free.
Paid Tier
If you pay directly for API usage (USD or crypto), or stake VVV you are entitled to a certain amount of inference on a daily basis (unified into one metric as Venice Compute Units or “VCU”). The more you stake, the higher your limits, 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.
See the section below for our preliminary VCU pricing. As our offering matures we will be releasing more details on different types of pricing and tiers.
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.
| Model | Input Tokens (/mil) | Input Tokens (/mil) | Output Tokens (/mil) | Output Tokens (/mil) |
|---|---|---|---|---|
| VCU | USD | VCU | USD | |
| Llama 3.2 3B | 2 VCU | $0.15 | 6 VCU | $0.60 |
| Qwen 2.5 Coder | 5 VCU | $0.50 | 20 VCU | $2.00 |
| Llama 3.3 70B Dolphin 72B Deepseek R1 70B Qwen 2.5 VL | 7 VCU | $0.70 | 28 VCU | $2.80 |
| Llama 3.1 405B | 15 VCU | $1.50 | 60 VCU | $6.00 |
| DeepSeek R1 671b | 35 VCU | $3.50 | 140 VCU | $14.00 |
Image models
Image models are priced per image. For the moment there is no per-model image pricing. This will change in a future price update.
| Image Model | One 1024x1024 Image* | One 1024x1024 Image* |
|---|---|---|
| All* | 0.1 VCU | $0.01 |
*High resolution images are metered as 2 images.