Model comparison

Mixtral 8x22B Instruct vs Mistral Small

Capability radar, value bars, and side-by-side posture.

← Back to Compare

Mixtral 8x22B Instruct
Not scored
value score
Mistral Small
74
value score
Mixtral 8x22B Instruct ctx
Mistral Small ctx
32K

Capability radar

Value · context · multimodal · openness · speed posture

Value head-to-head

  • Mistral Small74

Attribute tape

FieldMixtral 8x22B InstructMistral Small
DeveloperMistral AIMistral AI
Context32K
ModalitiesText, Code
OpennessProprietary Model
Speed
Price$0.1/1M in · $0.3/1M out
Value score74
SummaryMixtral 8x22B Instruct is Mistral AI's open-weight instruction-tuned language model using a Sparse Mixture-of-Experts architecture with 141B total parameters and 39B active per token. It is designed for chat, reasoning, coding, and multilingual generation with a 64K context window and native function calling support.Fast Mistral small model.
Open Mixtral 8x22B InstructOpen Mistral Small