Mistral Mistral Small (Sep '24)
September 2024 update of the Mistral Small model, optimized for resource-constrained environments
Creator: MistralLicense: Open
Summary
Artificial Analysis Quality
Index
Index
60The model performs better than the average model
Output Speed (Tokens per
Second)
Second)
66The model's speed is lesser than the average model 
Model Pricing (USD per 1M Tokens)
$0.300The model's pricing is lower than the average model
Latency (to receive the first
token)
token)
14.21sThe model's latency is lower than the average model
Context Window (tokens)
128k
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