Pricing Settings

Cost Calculation:Costs are calculated based on token usage and pricing rates. Each request's cost is determined by: (input_tokens × input_rate) + (output_tokens × output_rate) + (cached_tokens × cached_rate)

Pricing Format: All rates are in dollars per million tokens ($/1M tokens). Example: An input rate of 2.50 means $2.50 per 1,000,000 input tokens.

Token Types:

• Input: Standard prompt tokens
• Output: Completion/response tokens
• Cached: Cached input tokens (typically 50% of input rate)
• Reasoning: Special reasoning/thinking tokens (fallback to output rate)
• Cache Creation: Tokens used to create cache entries (fallback to input rate)

Custom Pricing: You can override default pricing for specific models. Reset to defaults anytime to restore standard rates.