Mistral: Mistral Small 4

mistralai/mistral-small-2603

262KContext Window

Supported Protocols:reasoninginclude_reasoningmax_tokenstemperaturetop_pstopfrequency_penaltypresence_penaltyseedresponse_formatstructured_outputstoolstool_choice

Normal

Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from Magistral, multimodal understanding from Pixtral, and agentic coding capabilities from Devstral, enabling one model to handle complex analysis, software development, and visual tasks within the same workflow.

Capabilities

👁 Vision🧠 Reasoning🔧 Function CallingText GenerationCode GenerationAnalysis & ReasoningReasoning

Technical Specs

Input Modality

Text、Image

Output Modality

Text

Arch

—

Default Temperature

0.7

Default Top_P

Pricing

Pay per use, no monthly fees

Billing Type	Unit	Price
Text Input	—	$0.1500/M tokens
Text Output	—	$0.6000/M tokens
Cache Read	—	$0.0150/M tokens

Quick Start

from openai import OpenAI

client = OpenAI(
    base_url="https://api.uniontoken.ai/v1",
    api_key="YOUR_UNIONTOKEN_API_KEY",
)

response = client.chat.completions.create(
    model="mistralai/mistral-small-2603",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)

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