Mistral

Mistral Small 3 24B Instruct

Mistral mistral-small-24b-instruct-2501

Model Information
Slug mistral-small-24b-instruct-2501
Aliases mistral-small-24b-instruct-2501 mistralsmall24binstruct2501
Release Date January 30, 2025
GPQA 0.453
Organization
Name Mistral
Website https://mistral.ai/

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. [Read the blog post about the model here.](https://mistral.ai/news/mistral-small-3/)

Available at 10 Providers
Provider Model Name Original Model Input ($/1M) Output ($/1M) Free
Chutes.ai icon Chutes.ai Mistral-Small-24B-Instruct-2501 unsloth/Mistral-Small-24B-Instruct-2501 $0.03 $0.11 Visit
OpenRouter icon OpenRouter Mistral Small 3 mistralai/mistral-small-24b-instruct-2501 $0.03 $0.11
FastRouter icon FastRouter Mistral: Mistral Small 3 mistralai/Mistral-Small-24B-Instruct-2501 $0.05 $0.08
DeepInfra icon DeepInfra Mistral-Small-24B-Instruct-2501 mistralai/Mistral-Small-24B-Instruct-2501 $0.05 $0.08 Visit
Together AI icon Together AI Mistral Small (24B) Instruct 25.01 mistralai/Mistral-Small-24B-Instruct-2501 $0.10 $0.30 Visit
Fireworks AI icon Fireworks AI Mistral Small 24B Instruct 2501 mistral-small-24b-instruct-2501 $0.90 - Visit
ValorGPT icon ValorGPT Mistral Small 3 mistralai-mistral-small-24b-instruct-2501 - -
Yupp icon Yupp Mistral Small 24B Instruct (Together AI) mistralai/Mistral-Small-24B-Instruct-2501 - - Visit
Yupp icon Yupp Mistral Small 3 24B Instruct (OpenRouter) mistralai/mistral-small-24b-instruct-2501 - - Visit
LangDB icon LangDB mistral-small-24b-instruct-2501 mistral-small-24b-instruct-2501 - -