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:

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

This model supports the following features:

Tools Response Format Structured Outputs
Performance Summary

Mistral's Codestral 2501 demonstrates strong overall performance, particularly in speed and reliability. It performs among the fastest models, ranking in the 67th percentile for speed across various benchmarks. The model also offers competitive pricing, typically providing cost-effective solutions in the 63rd percentile. Notably, Codestral 2501 exhibits exceptional reliability with a 96% success rate, indicating minimal technical failures and consistent evaluable responses. In terms of specific performance, Codestral 2501 excels in Hallucinations (98.0% accuracy), demonstrating a strong ability to acknowledge uncertainty. It also shows impressive speed in Mathematics, ranking in the top 3 and being the most accurate among models of similar speed. Its core specialization in Coding yields a solid 82.0% accuracy. However, the model shows weaknesses in Ethics (65.0% accuracy) and Reasoning (52.0% accuracy), where its performance is below average. General Knowledge and Email Classification also present opportunities for improvement. Its high context length of 262144 is a significant advantage for complex coding 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 Strategy Free Executions Accuracy Cost Duration
Other Models by mistralai