ScaledThought
← All models

Mistral AI

Mistral Large 3

Live · US + CAtextApache 2.0

Mistral's largest Apache 2.0 model, and its first fully permissive flagship.

Price per 1M tokens

Input

$0.50

Cached input

—

Output

$1.50

Priced per model · Same in US and CA · Free tier included · Pricing

Specs

Model id
mistral-large-3
Weights released
Dec 1, 2025
Parameters
675B
Architecture
MoE
Context
256K tokens (262,144)
Input
text
License
Apache 2.0
Regions
us, ca

Benchmarks

Independent scores aren't published yet. They'll appear here as soon as they are.

Sources: mistral.ai · huggingface.co · artificialanalysis.ai

Use it

Three lines of code, or zero.

OpenAI-compatible. Use the model id below, or auto to let the router decide when this model is worth it.

Quickstart→
import os
from openai import OpenAI

client = OpenAI(base_url=os.environ["ST_BASE_URL"], api_key=os.environ["ST_API_KEY"])
resp = client.chat.completions.create(
    model="mistral-large-3",
    messages=[{"role": "user", "content": "Hello"}],
)

Opens your agent with the prompt typed. You press Enter.