Gemini 3.1 Flash

textVisionFiles

Fast Google reasoning model.

Pricing

0.38 $

Request / 1M

2.25 $

Response / 1M

Price uses the live FX rate — shown equals charged.

Parameters

messagesrequired

temperature0–2

max_tokensoptional

streamtrue · false

image_urlimage (data: URL)

filePDF

How to use via API

from openai import OpenAI

client = OpenAI(base_url="https://api.mixen.ai/v1", api_key="mxn-...")
resp = client.chat.completions.create(
    model="google/gemini-3.1-flash-lite-preview",
    messages=[{"role": "user", "content": "Привет"}],
    temperature=0.7,
    max_tokens=1024,
    stream=False,
)
print(resp.choices[0].message.content)

Try in the bot Open in web app API docs

Related models