All models
Groq LLAMA3.3 70B Versatile
Meta
Claude 3.5 Sonnet Frontier Claude 3.7 Sonnet Frontier Claude 3.7 Sonnet (high output) Frontier Claude 3.7 Sonnet (thinking) Frontier Claude Opus Frontier Gemini 2.5 Pro Frontier GPT-4.1 Frontier GPT-4o Frontier o1 Frontier o1-mini Frontier

Groq LLAMA3.3 70B Versatile

The 70B parameter version of Meta's Llama model delivers state of the art performance (running on Groq)

Model Specifications

Context window 131,072 tokens
Max output 8,000 tokens
Knowledge cutoff February 2024
Multipart messages No
Vision capabilities No

Default Parameters

Temperature 0.3
Top P 1.0
Frequency penalty 0.0
Presence penalty 0.0
Top K 50
Try on Simtheory

Supported Parameters

Temperature

Supported

Controls randomness: Lower values make output more deterministic, higher values more creative.

Range: 0.0 - 1.0 Default: 0.3

More models from Meta

Meta Llama 4 Scout

Meta Llama 4 Scout

Llama 4 Scout is a versatile small model served with 1M token context suitable for a wide range of applications including chatbots and question answering.

Context: 1,000,000 Output: 16,384
Meta Llama 4 Maverick

Meta Llama 4 Maverick

Llama 4 Maverick is a powerful medium model with 1M token context designed for advanced reasoning tasks and multimodal understanding.

Context: 1,000,000 Output: 16,384