Gemini 3.1 Flash Lite

40% cheaper

gemini-3.1-flash-lite

Get an API key

INPUT / 1M$0.150list $0.250

OUTPUT / 1M$0.900list $1.50

CACHE READ / 1M—caching not supported on this model

CONTEXT1Mtokens per request

Call this model

from openai import OpenAI

client = OpenAI(
    api_key="sk-ak-...",
    base_url="https://apikey.sh/v1",
)

resp = client.chat.completions.create(
    model="gemini-3.1-flash-lite",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

Specifications

ProviderGoogle

CategoryFast & cheap

Context1M tokens

Max output65.5K

Endpoint/v1/chat/completions

visiontoolsstreaming

Related models

Gemini Pro Agent$1.20 / $7.20 · 1M

Gemini 3.1 Pro$1.20 / $7.20 · 1M

Gemini 3.6 Flash$0.900 / $4.50 · 1M