All Tools
G
llm

Groq

Groq

World's fastest AI inference — LPU chips delivering 500+ tokens/sec Groq offers ultra-fast inference for open-source LLMs (Llama 3, Mixtral, Gemma) using proprietary LPU hardware.

Visit Groq

Pricing

API / Token Pricing
Model / Plan
Price
Unit
Llama 4 Scout Input
$0.11
1M tokens (input)
Llama 4 Scout Output
$0.34
1M tokens (output)
Llama 4 Maverick Input
$0.5
1M tokens (input)
Llama 4 Maverick Output
$0.77
1M tokens (output)
Llama 3.3 70B Input
$0.59
1M tokens (input)
Llama 3.3 70B Output
$0.79
1M tokens (output)
Llama 3.1 8B Input
$0.05
1M tokens (input)
Llama 3.1 8B Output
$0.08
1M tokens (output)

Features

context window131072
api available✓
supports vision✓
function calling✓
open source✗
streaming✓
free tier✓

Links

Official WebsiteFull Changelog
Data Freshness
Pricing updated: 19m ago