Chat model

Gemini 3.8 Flash API

Gemini 3.8 Flash is a chat model you call through the OpenAI-compatible /chat/completions endpoint, with streaming and tool calls. Send "gemini-3.8-flash" as the model name and keep the rest of your code. You pay per token from a prepaid balance.

1M tokens of contextUp to 65.5K output tokensFrom $0.675 per 1M input tokensStreaming and tool calls

Price

US$ per 1M tokens. The first figure is what you pay; the list price is struck through.

ModelInput (cache hit)Input (cache miss)Output
gemini-3.8-flash−10% off the list price
Context: 1M
$0.0675 $0.075$0.675 $0.75$3.375 $3.75Try it

See all prices →

Specifications

Model IDgemini-3.8-flash
TypeChat model
EndpointPOST /chat/completions
Context window1,048,576 tokens
Max output65,536 tokens

Copy, paste, run

Copy this request, put in your key, and run it. "gemini-3.8-flash" is the model name to send.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.apistore.cloud/v1",
    api_key="sk-...",
)

stream = client.chat.completions.create(
    model="gemini-3.8-flash",
    messages=[{"role": "user", "content": "Hello!"}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

Questions

How do I call Gemini 3.8 Flash?

Send an OpenAI-format request to /chat/completions with "model": "gemini-3.8-flash". Any SDK or tool that accepts an OpenAI-compatible base URL and key works.

How much does Gemini 3.8 Flash cost?

From $0.675 per 1M input tokens and from $3.375 per 1M output tokens. The table above always shows the current prices.

What are the limits of Gemini 3.8 Flash?

A context window of 1M tokens and up to 65.5K output tokens per answer. Request limits apply per key and per account.

How do I get an API key for Gemini 3.8 Flash?

Create an account with email or Google, verify your address, then create a key on the API keys page. Add credit by card and the key works at once.

Other models

Start in a few minutes

Create an account, verify your email, create a key and make your first call.