magistral-small-2506

completions

byopenrouter

magistral-small-2506

completions

Published by: mistralaiProvider:

openrouter

Magistral Small is a 24B parameter instruction-tuned model based on Mistral-Small-3.1 (2503), enhanced through supervised fine-tuning on traces from Magistral Medium and further refined via reinforcement learning. It is optimized for reasoning and supports a wide multilingual range, including over 20 languages.

Released

Jun 10, 2025

Knowledge

Jun 1, 2025

License

Apache-2.0

Context

40K

Input

$0.5 / 1M tokens

Output

$1.5 / 1M tokens

Capabilities: tools

Accepts: text

Returns: text

Released Jun 10, 2025Knowledge Cutoff: Jun 1, 2025License: Apache-2.0

Context: 40K Input: $0.5 / 1M tokensOutput: $1.5 / 1M tokensCapabilities: toolsAccepts: textReturns: text

Access magistral-small-2506 through LangDB AI Gateway

Recommended

Integrate with mistralai's magistral-small-2506 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

Benchmark Results for magistral-small-2506

Category Performance Scores:

Science: Score 68.18 (Top 25% - Rank #87)
Writing: Score 68.18 (Top 7% - Rank #25)

Overall Performance: 68.17999999999999 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
GPQA	68.18	Top 27%	STEM (Physics, Chemistry, Biology)

GPQA Score: 68.18 - Graduate-level reasoning benchmark

Model Comparison:

Provider: openrouter

Model Type: completions

Context Size: 40000 tokens

Comparing against 345 models in the database

Category Scores

Benchmark Tests

View Other Benchmarks

GPQA

68.2

STEM (Physics, Chemistry, Biology)

Metric	GPQA
Score	68.2

Compare with Similar Models

gemini-2.5-pro-preview

grok-4

Code Examples

Integration samples and API usage

Code Samples for magistral-small-2506

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="magistral-small-2506",
    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: "magistral-small-2506",
    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": "magistral-small-2506",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: magistral-small-2506

Provider: openrouter

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

Create API Key

Related Models

Similar models from openrouter

magistral-small-2506

magistral-small-2506

Access magistral-small-2506 through LangDB AI Gateway

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-2501

codestral-2508

magistral-small-2506 by openrouter - AI Model Details, Pricing, and Performance Metrics

magistral-small-2506

magistral-small-2506

Access magistral-small-2506 through LangDB AI Gateway

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-2501

codestral-2508