Mistral: Codestral 2501

Text input Text output
Author's Description

[Mistral](/mistralai)'s cutting-edge language model for coding. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. Learn more on their blog post: https://mistral.ai/news/codestral-2501/

Key Specifications
Cost
$$$
Context
262K
Parameters
2.5B (Rumoured)
Released
Jan 14, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Stop Presence Penalty Tool Choice Top P Temperature Seed Tools Structured Outputs Response Format Frequency Penalty Max Tokens
Features

This model supports the following features:

Tools Structured Outputs Response Format
Performance Summary

Mistral's Codestral 2501, a cutting-edge language model for coding, demonstrates competitive response times, performing among the faster models with a 56th percentile speed ranking. It also offers cost-effective solutions, ranking in the 62nd percentile for price. A standout feature is its exceptional reliability, achieving a 95th percentile, indicating very few technical issues and consistent usable responses. In terms of performance across benchmarks, Codestral 2501 shows strong capabilities in its specialized domain, achieving 82.0% accuracy in Coding (Baseline). It also excels in Instruction Following (64.0% accuracy) and General Knowledge (94.0% accuracy), with particularly fast response times in Instruction Following and Email Classification. While its Email Classification accuracy is 94.0%, its percentile ranking suggests this is a less competitive area. Key strengths include its robust coding performance, high reliability, and efficient instruction following. Notable weaknesses appear in Reasoning (52.0% accuracy) and Ethics (65.0% accuracy), where its accuracy percentiles are lower, suggesting these are areas for potential improvement. Overall, Codestral 2501 is a reliable and cost-efficient model, particularly strong for coding and instruction-based tasks.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.3
Completion $0.9

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Mistral
Mistral | mistralai/codestral-2501 262K $0.3 / 1M tokens $0.9 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Free Executions Accuracy Cost Duration
Other Models by mistralai