Groq AI models — pricing & benchmarks

Official siteDocsPricingAPI

The Groq LPU delivers inference with the speed and cost developers need. Inference platform · OpenAI-compatible API · Fast Inference · Low Latency · Lpu · Open Weight

Intelligence vs Price

Best value among Groq models on this chart: GPT OSS 120B · GPT OSS 20B · Llama 3.1 8B Instruct. Hover any dot for full pricing, or click a creator in the legend to isolate.

Groq models

14 models, 11 with pricing

Model	Creator	Input Price, $	Output Price, $	Context	Max Output	Inference Providers	Intelligence	Coding
GPT OSS 120B	OpenAI	0.039	0.180	131K	131K	compare (20)	33.3#1	28.6#1
GPT OSS 20B	OpenAI	0.030	0.140	131K	131K	compare (15)	24.5#2	18.5#2
Llama 3.3 70B Instruct	Meta	0.100	0.200	131K	120K	compare (20)	14.5#3	10.7#3
Llama 3.1 8B Instruct	Meta	0.020	0.030	200K	128K	compare (20)	11.8#4	4.9#4
Gemma 7B IT	Google	0.050	0.080	8K	8K	compare (3)	N/A	N/A
GPT OSS 20B Safeguard	OpenAI	0.070	0.200	131K	66K	compare (5)	N/A	N/A
Kimi K2 Instruct	Moonshot AI (Kimi)	0.500	2.00	262K	33K	compare (9)	N/A	N/A
Llama 4 17B Maverick Instruct	Meta	0.050	0.100	1.0M	16K	compare (9)	N/A	N/A
Llama 4 17B Scout Instruct	Meta	0.050	0.100	10.0M	16K	compare (11)	N/A	N/A
LlamaGuard 4 12B	Meta	0.180	0.180	164K	16K	compare (4)	N/A	N/A
PlayAI TTS	PlayAI	N/A	N/A	10K	10K	compare (1)	N/A	N/A
Qwen3 32B	Alibaba	0.050	0.100	131K	41K	compare (15)	N/A	N/A
Whisper 3 Large	OpenAI	N/A	N/A	N/A	N/A	compare (1)	N/A	N/A
Whisper 3 Large Turbo	OpenAI	N/A	N/A	N/A	N/A	compare (2)	N/A	N/A