codestral-2501

completions

On:mistralaiopenrouter

codestral-2501

completions

Published by: mistralaiProviders:

mistralai openrouter

Mistral'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/

Provider	Input	Output
mistralai	$0.3 / 1M tokens	$0.9 / 1M tokens
openrouter	$0.3 / 1M tokens	$0.9 / 1M tokens

Released

Jan 13, 2025

Knowledge

Jul 17, 2024

Context

256K

Input

$0.3 / 1M tokens

Output

$0.9 / 1M tokens

Capabilities: tools

Accepts: text

Returns: text

Providers	Context	Input Price	Output Price	Input Formats	Output Formats
mistralai	256K tokens	$0.3 / 1M tokens	$0.9 / 1M tokens	text	text
openrouter	262144 tokens	$0.3 / 1M tokens	$0.9 / 1M tokens	text	text

Released Jan 13, 2025Knowledge Cutoff: Jul 17, 2024

Access codestral-2501 through LangDB AI Gateway

Recommended

Integrate with mistralai's codestral-2501 and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.

Unified API

Cost Optimization

Enterprise Security

Get Started Now

Free tier available • No credit card required

Instant Setup

99.9% Uptime

10,000+Monthly Requests

Available from 2 providers

Provider:

Benchmark Results for codestral-2501

Category Performance Scores:

Academia: Score 22.20 (Top 84% - Rank #290)
Marketing: Score 35.08 (Top 70% - Rank #242)
Programming: Score 24.50 (Top 63% - Rank #218)
Science: Score 33.44 (Top 89% - Rank #308)
Writing: Score 32.56 (Top 83% - Rank #287)

Overall Performance: 29.555888888888894 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AIME	4.30	Top 79%	Mathematics
AA Coding Index	24.50	Top 63%	Programming
AAII	13.20	Top 76%	General
GPQA	31.20	Top 90%	STEM (Physics, Chemistry, Biology)
HLE	4.50	Top 50%	General Knowledge
LiveCodeBench	24.30	Top 65%	Programming
MATH-500	60.70	Top 72%	Mathematics
MMLU-Pro	44.60	Top 88%	General Knowledge
SciCode	24.70	Top 56%	Scientific

GPQA Score: 31.20 - Graduate-level reasoning benchmark

Model Comparison:

Provider: mistralai

Model Type: completions

Context Size: 256000 tokens

Comparing against 345 models in the database

Performance Analytics for codestral-2501

Usage Statistics (Last 1 Days):

Total Requests: 1 API calls
Average TPS: 94.82 tokens per second
Average Response Time: 358.60ms
Average Time to First Token: 247.70ms
Total Cost: $0.00
Average Request Cost: $0.0000

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
9/19/2025	1	94.82	358.60ms	247.70ms	$0.00

Performance Summary:

Model: codestral-2501 by mistralai

Monitoring Period: 9/13/2025 to 9/20/2025

Average Daily Requests: 1

Peak Daily Requests: 1

Statistics

View Full Statistics

Request Volume

Daily API requests

Performance (TPS)

Tokens per second

94.82 tokens/s

Category Scores

Benchmark Tests

View Other Benchmarks

AIME

4.3

Mathematics

AA Coding Index

24.5

Programming

AAII

13.2

General

GPQA

31.2

STEM (Physics, Chemistry, Biology)

HLE

4.5

General Knowledge

LiveCodeBench

24.3

Programming

MATH-500

60.7

Mathematics

MMLU-Pro

44.6

General Knowledge

SciCode

24.7

Scientific

Metric	AIME	AA Coding Index	AAII	GPQA	HLE	LiveCodeBench	MATH-500	MMLU-Pro	SciCode
Score	4.3	24.5	13.2	31.2	4.5	24.3	60.7	44.6	24.7

Compare with Similar Models

gemini-2.5-pro-preview

grok-4

Code Examples

Integration samples and API usage

Code Samples for codestral-2501

Python SDK Example:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    api_key="<your_api_key>"
)

response = client.chat.completions.create(
    model="codestral-2501",
    messages=[
        {"role": "user", "content": "Hello, how are you?"}
    ]
)

print(response.choices[0].message.content)

TypeScript SDK Example:

import OpenAI from 'openai';

const client = new OpenAI({
    baseURL: "https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    apiKey: "<your_api_key>"
});

const response = await client.chat.completions.create({
    model: "codestral-2501",
    messages: [
        { role: "user", content: "Hello, how are you?" }
    ]
});

console.log(response.choices[0].message.content);

cURL Example:

curl -X POST "https://api.us-east-1.langdb.ai/projects/<your_project_id>/v1/chat/completions" \
  -H "Authorization: Bearer <your_api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "codestral-2501",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: codestral-2501

Provider: mistralai

API Endpoint: $https://api.us-east-1.langdb.ai

Create API Key

Related Models

Similar models from mistralai

codestral-2501

codestral-2501

Access codestral-2501 through LangDB AI Gateway

Statistics

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

aion-1.0

aion-1.0-mini

aion-rp-llama-3.1-8b

coder-large

codestral-2508

codestral-2508

codestral-2501 by mistralai - AI Model Details, Pricing, and Performance Metrics

codestral-2501

codestral-2501

Access codestral-2501 through LangDB AI Gateway

Statistics

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

aion-1.0

aion-1.0-mini

aion-rp-llama-3.1-8b

coder-large

codestral-2508

codestral-2508