Chuizi.AI

Devstral 2

Mistral
mistral/devstral-2

131K context, vision

Context Window

131K

131,072 tokens

Max Output

8K

8,192 tokens

About this model

Devstral 2 123B, purpose-built for software engineering

This model supports up to 131K tokens of context. It includes native vision understanding for analyzing images and documents. It provides strong code generation and debugging capabilities.

Access it through Chuizi.AI with a single ck- API key — no separate Mistral AI account needed.

Highlights

131K context window
8K max output
Native vision support
Strong code generation

Best For

Code generationRefactoringDebuggingDocumentation
2025-07-10

Capabilities

ChatVisionCodetools

Pricing (per 1M tokens)

Pricing (per 1M tokens)/ 1M tokens
Input / 1M$0.420
Output / 1M$1.05

Final prices shown

Quick Start

from openai import OpenAI

client = OpenAI(
    base_url="https://api.chuizi.ai/v1",
    api_key="ck-your-key-here",
)

response = client.chat.completions.create(
    model="mistral/devstral-2",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

FAQ

Related Models