Mistral: Mistral Small 3

mistralai/mistral-small-24b-instruct-2501

Description

Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment. The model achieves 81% accuracy on the MMLU benchmark and performs competitively with larger models like Llama 3.3 70B and Qwen 32B, while operating at three times the speed on equivalent hardware.

How this model compares

Overall covers the full catalog. By plan covers only models available on that tier (same rules as available models in your list). Position on min–average–max. Prices use the higher of prompt or completion per token, shown per 1M tokens.

Price (per 1M tokens)

Min
Max
This model
339 models in this groupPrice (per 1M tokens)
Min
$0.04
Avg
$12.395447
Max
$750.00
This model: $0.08 / 1M tokens

Context length (tokens)

Min
Max
This model
339 models in this groupContext length (tokens)
Min
4,095 tokens
Avg
379,884.782 tokens
Max
10,000,000 tokens
This model: 32,768 tokens

Capabilities

Text → TextContext: 32,768 tokens
Input:
Text
Output:
Text
    Mistral: Mistral Small 3