Groq
groq
Updated 23 minutes ago
Groq is an AI inference company that pioneered the LPU (Language Processing Unit) in 2016, the first chip purpose-built for AI inference. Their proprietary LPU inference engine delivers ultra-low latency AI inference, with benchmarks showing Llama 2 70B running at 300 tokens per second—reportedly 10x faster than NVIDIA H100 clusters and 18x faster on Anyscale's LLMPerf Leaderboard. Groq focuses on making AI inference fast and affordable at scale, offering both cloud services and on-premises deployment options, with a mission to enable real-time AI applications that were previously impossible due to latency constraints.
Browse 16 LLM models available from Groq. Compare prices and features.
Models (16)
| Organization | Model Name | Original Model | Input | Output | Free | |||
|---|---|---|---|---|---|---|---|---|
|
qwen | Qwen3.8-27B |
qwen/qwen3.8-27b
|
$0.80 | $4.00 | |||
|
Alibaba | Qwen3.6 27B |
qwen/qwen3.6-27b
|
$0.60 | $3.00 | |||
|
OpenAI | GPT OSS 120B |
openai/gpt-oss-120b
|
$0.15 | $0.60 |
|
||
|
|
OpenAI | GPT OSS 20B |
openai/gpt-oss-20b
|
$0.08 | $0.30 |
|
||
|
Nvidia | Whisper Large v3 |
whisper-large-v3
|
- | - | |||
|
Groq | Whisper Large v3 Turbo |
whisper-large-v3-turbo
|
- | - | |||
|
|
Groq | Orpheus V1 English |
canopylabs/orpheus-v1-english
|
- | - | |||
|
|
Groq | Orpheus Arabic Saudi |
canopylabs/orpheus-arabic-saudi
|
- | - | |||
|
|
OpenAI | gpt-oss-safeguard-20b |
openai/gpt-oss-safeguard-20b
|
$0.08 | $0.30 | |||
|
|
Groq | Compound |
groq/compound
|
- | - | |||
|
|
Groq | Compound Mini |
groq/compound-mini
|
- | - | |||
|
|
Groq | Llama Prompt Guard 2 22M |
meta-llama/llama-prompt-guard-2-22m
|
$0.03 | $0.03 | |||
|
|
Groq | Llama Prompt Guard 2 86M |
meta-llama/llama-prompt-guard-2-86m
|
$0.04 | $0.04 | |||
|
|
Groq | ALLaM-2-7b |
allam-2-7b
|
$0.00 | $0.00 | Free | ||
|
|
Groq | Llama 3.3 70B Versatile |
llama-3.3-70b-versatile
|
$0.59 | $0.79 | |||
|
|
Groq | Llama 3.1 8B Instant |
llama-3.1-8b-instant
|
$0.05 | $0.08 |