Models/Mistral Small 3.1
?Mistral Small 3.1
Released: 3/17/2025
texttext
Input: $0.10 / Output: $0.30

Mistral Small 3.1 is a 24 billion parameter Multimodal LLM designed for a wide range of generative AI tasks.

It excels in instruction following, conversational assistance, image understanding, and function calling, while being lightweight enough to run on a single RTX 4090 or a Mac with 32GB RAM when quantized.

Some other noteworthy features of Mistral Small 3.1 include fast-response conversational assistance, low-latency function calling, and the ability to be fine-tuned for specialized domains such as legal advice, medical diagnostics, and technical support.

MetricValue
Parameter Count24 billion
Mixture of ExpertsNo
Context Length128,000 tokens
MultilingualYes
Quantized*Yes
Precision*Unknown

*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.