Devstral Medium

About Devstral Medium

Devstral Medium is a high-performance code generation and agentic reasoning model developed jointly by Mistral AI and All Hands AI. Positioned as a step up from Devstral Small, it achieves 61.6% on SWE-Bench Verified, placing it ahead of Gemini 2.5 Pro and GPT-4.1 in code-related tasks, at a fraction of the cost. It is designed for generalization across prompt styles and tool use in code agents and frameworks. Devstral Medium is available via API only (not open-weight), and supports enterprise deployment on private infrastructure, with optional fine-tuning capabilities.

Model Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

Mistral Model Lineup

Compare all models from Mistral to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Kimi K2 0905 (exacto)

Moonshot AI

Input: $0.40

Output: $2.00

Context: 262k

Llama 3.1 Nemotron 70B Instruct

NVIDIA

Input: $1.20

Output: $1.20

Context: 131k

GLM 4.5V

Zhipu Ai

Input: $0.60

Output: $1.80

Context: 66k

Llama 3.1 Nemotron Ultra 253B v1

NVIDIA

Input: $0.60

Output: $1.80

Context: 131k

💡 Cheaper Alternatives

Same Brand (Mistral)

Cross Brand

🚀 Quick Start

Get started with Devstral Medium API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="mistralai/devstral-medium-2507",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision