weightsapi.INFERENCEConsole
Navigation
Mistral Small 3 vs Llama 3.1 405B

Mistral Small 3 vs Llama 3.1 405B

Compare the exact deployment revisions, published rates and context limits.

Generated from the model catalogue

Values here, in pricing and in the machine-readable feed use the same model records.

ModelInput / 1MOutput / 1MContextType
MMistral Small 3$0.10$0.2032K*Text
LLlama 3.1 405B$1.20$1.20128K*Text

Mistral Small 3

Efficient text tasks, function calling and European-language chat.

Native context
32,768 tokens
Quantization
Not verified
License
Apache 2.0
Output speed
No measurements yet
Read model details ↗

Llama 3.1 405B

Demanding general-purpose generation and complex instructions.

Native context
131,072 tokens
Quantization
Not verified
License
Llama 3.1 Community
Output speed
No measurements yet
Read model details ↗