Inference Cost Calculator
How much will your AI cost? Compare models at your exact volume.
Daily Token Volume
1.0M tokens/day
0.2M tokens/day
Select Models to Compare
Save $175/mo by choosing Gemini 2.0 Flash over Claude Sonnet 4
That's $2.10K/year at your current volume
Gemini 2.0 FlashGoogleCHEAPEST
$5/mo
via GCP Vertex AI
Direct API
$5/mo
GCP Vertex AI
$5/mo
GPT-4o MiniOpenAI
$8/mo
via Azure OpenAI
Direct API
$8/mo
Azure OpenAI
$8/mo
Claude 3.5 HaikuAnthropic
$48/mo
via GCP Vertex AI
Direct API
$48/mo
AWS Bedrock
$48/mo
GCP Vertex AI
$48/mo
Gemini 2.5 ProGoogle
$98/mo
via GCP Vertex AI
Direct API
$98/mo
GCP Vertex AI
$98/mo
GPT-4oOpenAI
$135/mo
via Azure OpenAI
Direct API
$135/mo
Azure OpenAI
$135/mo
Claude Sonnet 4Anthropic
$180/mo
via GCP Vertex AI
Direct API
$180/mo
AWS Bedrock
$180/mo
GCP Vertex AI
$180/mo
Calculations: (input tokens/day ÷ 1M × input price + output tokens/day ÷ 1M × output price) × 30 days. Prices from official API pricing pages, April 2026.