Groq Pricing

Groq API Β· Ultra-fast LLM inference on custom LPU hardware.

Groq logo

Groq

βœ“ Verified Pricing LLM API
Groq API

Ultra-fast LLM inference on custom LPU hardware.

All Models & Pricing
Model Input / 1M tokCached / 1M tokOutput / 1M tok
GPT OSS 120B
OpenAI open-weight 120B on LPU
$0.150 - $0.600
GPT OSS 20B
OpenAI open-weight 20B on LPU
$0.075 - $0.300
Llama 4 Scout
17Bx16E MoE, 128K context
$0.110 - $0.340
Llama 3.3 70B Versatile
128K context
$0.590 - $0.790
Llama 3.1 8B Instant
Fastest, cheapest tier
$0.050 - $0.080
Qwen3 32B
131K context
$0.290 - $0.590
Qwen/Qwen3.8-27B $0.800 - $4.000
GPT OSS Safeguard 20B $0.075 - $0.300
Qwen3.8 27B $0.800 - $4.000
Safety GPT OSS 20B $0.075 - $0.300
Llama Prompt Guard 2 22M $0.030 - $0.030
Prompt Guard 2 86M $0.040 - $0.040
Price history

Tracked automatically on every price check.

Groq
Get started with Groq

Ultra-fast LLM inference on custom LPU hardware.

View official pricing β†’
Prices verified on official pricing page. Always confirm before purchase.
Details
Category
LLM API
Last checked
2026-11-11 21:01 EST
Last price change
2026-11-01 21:02 EST
Pricing status
βœ“ Verified
✦
CloudMart AI Compute
Answers from live pricing data
✦
What are you building?
Compare providers, estimate costs, or get a recommendation - answers come from CloudMart's live dataset, never made-up prices.
Enter to send Β· Shift+Enter for a new line
Compare:
Report a problem