Meta Llama 2 Chat 7B

Chat-focused Llama 2 model with 7 billion parameters, optimized for chat applications

Creator: MetaLicense: Open

Summary

Artificial Analysis Quality
Index
Output Speed (Tokens per
Second)
124
Model Pricing (USD per 1M Tokens)
$0.300
Latency (to receive the first
token)
14.21s
Context Window (tokens)
4k

Comparison with other models

Quality

Artificial Analysis Quality Index; Higher is better

+ Add model

Speed

Output Tokens per Second; Higher is better

+ Add model

Pricing

USD per 1M Tokens; Lower is better

+ Add model

Latency

Seconds to First Tokens Chunk Received; Lower is better

+ Add model