Inference Volume$52.1B+5.1%
Model Rankings165updated
AI Traffic624.8K+38.2%
Global Latency11msoptimal
API Calls102.4M+12.4%
Live Agents582,391+42.1%
AI Market Cap$58.2B+5.2%
GPU Nodes6,247+10.2%
Inference Volume$52.1B+5.1%
Model Rankings165updated
AI Traffic624.8K+38.2%
Global Latency11msoptimal
API Calls102.4M+12.4%
Live Agents582,391+42.1%
AI Market Cap$58.2B+5.2%
GPU Nodes6,247+10.2%

AI Cost Analytics

Real-time token pricing, API economics, GPU serving costs, inference economics

Cheapest Input
Free
Llama 3.1 405B
Most Expensive Input
$15.00/1M
Claude 3 Opus
Cheapest GPU Cloud
$0.15/hr
P100 on Vast.ai
Enterprise AI Spend
$6.9M/mo
Tracked enterprises

API Cost Comparison / 1M tokens

Sorted by input cost

ModelProviderInput/1MOutput/1MContextSpeedEfficiency
Llama 3.1 70BMetaFreeFree128K112ms
Llama 3.1 405BMetaFreeFree128K412ms
DeepSeek V3DeepSeek$0.27/1M$1.10/1M128K156ms
Gemini 2.0 FlashGoogle$0.35/1M$0.70/1M1M89ms
DeepSeek R1DeepSeek$0.55/1M$2.19/1M128K298ms
Mistral Large v2Mistral$2.00/1M$6.00/1M128K98ms
GPT-4oOpenAI$2.50/1M$10.00/1M128K142ms
Claude 3.5 SonnetAnthropic$3.00/1M$15.00/1M200K187ms
Gemini 1.5 ProGoogle$3.50/1M$10.50/1M2M165ms
Grok 2xAI$5.00/1M$15.00/1M131K134ms
GPT-4-turboOpenAI$10.00/1M$30.00/1M128K256ms
Claude 3 OpusAnthropic$15.00/1M$75.00/1M200K412ms