Configure your negotiated token costs for accurate cost reporting in AI evaluations and real-time logs. Custom token pricing ensures that displayed costs match your actual expenses based on special pricing agreements.

​
How it works

1

Define Token Costs

Enter your custom input and output token costs
2

Apply Pricing

Apply costs to model configs and log repositories
3

Cost Calculation

System calculates actual costs for each evaluation
4

Default Pricing

Standard pricing applies when no custom rates exist

​
Create custom pricing structures

  1. Navigate to Settings > Models > Pricing
  2. Enter a model name pattern (string or regex) that matches your model names
  3. Input your token usage cost (per 1000 tokens)
Interface for creating custom token pricing structures

​
Configure model pricing

  1. Go to Settings > Models > Model Configs
  2. Select a model config to edit
  3. Locate the Pricing structure section
  4. Choose your pricing structure from the dropdown
Custom pricing supports OpenAI, Microsoft Azure, Groq, HuggingFace, Together AI, Google Cloud, and Amazon Bedrock models.
Attach the pricing structure to model config

​
Set up pricing for log repository

  1. Open Logs from the sidebar
  2. Select the log repository you want to configure custom pricing for
  3. Find the Pricing structure section
  4. Choose your pricing structure from the dropdown
Attach pricing structure to log repository