Mistral: Mistral Small 3

Text input Text output Free Option
Author's 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. [Read the blog post about the model here.](https://mistral.ai/news/mistral-small-3/)

Key Specifications
Cost
$
Context
32K
Parameters
24B
Released
Jan 30, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Top Logprobs Logit Bias Logprobs Stop Seed Min P Top P Max Tokens Frequency Penalty Temperature Presence Penalty
Performance Summary

Mistral Small 3, a 24B-parameter model, demonstrates strong overall performance, particularly excelling in speed and cost-efficiency. It performs among the fastest models, ranking in the 68th percentile for speed across eight benchmarks, and consistently offers highly competitive pricing, placing in the 90th percentile across seven benchmarks. The model exhibits exceptional reliability with a 100% success rate across all evaluated benchmarks, indicating consistent and usable responses. In terms of specific benchmarks, Mistral Small 3 achieved perfect accuracy in one instance of Instruction Following, showcasing its precision for complex directives. It also performed well in Hallucinations (96.0% accuracy) and General Knowledge (98.0% accuracy), indicating a robust understanding and ability to acknowledge uncertainty. While its performance in Reasoning (62.0% accuracy) and Coding (79.0% accuracy) is moderate, it remains competitive within its peer group. A notable strength is its efficiency, operating at three times the speed of larger models like Llama 3.3 70B and Qwen 32B on equivalent hardware, making it ideal for low-latency applications and efficient local deployment.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.04
Completion $0.15

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Kluster
Kluster | mistralai/mistral-small-24b-instruct-2501 32K $0.04 / 1M tokens $0.15 / 1M tokens
DeepInfra
DeepInfra | mistralai/mistral-small-24b-instruct-2501 32K $0.05 / 1M tokens $0.08 / 1M tokens
Enfer
Enfer | mistralai/mistral-small-24b-instruct-2501 28K $0.04 / 1M tokens $0.15 / 1M tokens
NextBit
NextBit | mistralai/mistral-small-24b-instruct-2501 32K $0.04 / 1M tokens $0.15 / 1M tokens
Mistral
Mistral | mistralai/mistral-small-24b-instruct-2501 32K $0.1 / 1M tokens $0.3 / 1M tokens
Ubicloud
Ubicloud | mistralai/mistral-small-24b-instruct-2501 32K $0.04 / 1M tokens $0.15 / 1M tokens
Together
Together | mistralai/mistral-small-24b-instruct-2501 32K $0.8 / 1M tokens $0.8 / 1M tokens
Enfer
Enfer | mistralai/mistral-small-24b-instruct-2501 28K $0.04 / 1M tokens $0.15 / 1M tokens
Chutes
Chutes | mistralai/mistral-small-24b-instruct-2501 32K $0.04 / 1M tokens $0.15 / 1M tokens
Chutes
Chutes | mistralai/mistral-small-24b-instruct-2501 32K $0.04 / 1M tokens $0.15 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by mistralai