Llama 3.1 8B (Groq)

Groq

Llama 3.1 8B with ultra-fast Groq inference

Text Generation API Llama Family
Back to Models
Parameters
-
params
Context Window
128K
tokens
Max Output
8K
tokens
Input Price
$0.0500
per 1M tokens
Output Price
$0.0800
per 1M tokens

Llama Family Timeline 8 versions

Llama 4 Scout api
Apr 2025
Llama 4 Scout Latest local
Apr 2025
Llama 4 Maverick Latest api
Apr 2025
Llama 3.1 70B local
Jul 2024
Llama 3.1 8B local
Jul 2024
Llama 3.1 8B (Groq) Current api
-
Llama 3.3 70B (Groq) api
-
Llama 3.1 405B (Together) api
-

Capabilities

👁️
Vision
⚡
Function Calling
📋
JSON Mode
🌊
Streaming
💬
System Prompt
🖥️
Code Execution
🔍
Web Search
🔌
MCP Support

Details

Release Date
-
Knowledge Cutoff
December 1, 2023
Source
API
API Key Required
Yes
License
Proprietary
Model ID
groq-llama-3.1-8b
Last updated: November 26, 2025