Roar AI
DiscordGet started
All models
Google · Chat

Gemini 3.8 Flash

Gemini 3.8 Flash costs $0.75 per million input tokens and $3.75 per million output tokens on Roar AI. Google’s newest Flash model, with coding close to its flagship at Flash speed.

Input$0.75per 1M tokens
Output$3.75per 1M tokens
Context window1.05Mtokens

Gemini 3.8 Flash API pricing

Input$0.75 per 1M tokens
Output$3.75 per 1M tokens
Cached input$0.075 per 1M tokens
Batch input$0.375 per 1M tokens
Batch output$1.875 per 1M tokens

Example: 1,000 requests with 3,000 input and 1,000 output tokens each cost $6. Every rate is published and stays the same from one request to the next. See every model.

Rates as of 20 November 2026.

Specs

Made byGoogle
ReleasedSeptember 2026
TypeChat
Context window1.05M tokens
Longest answer66K tokens
ReadsText, images, audio, video, PDFs
Thinks before answeringAlways on
WeightsClosed
Processed inGlobal
Model idgemini-3.8-flash

About Gemini 3.8 Flash

Gemini 3.8 Flash is the third Flash release in six weeks and Google’s most capable so far. On the DeepSWE coding test it scored 73.7%, just under Claude Opus 5 and ahead of GPT-5.6 Sol, and Google reports wins over Opus 5 on finance and legal agent tests. It reads the same mix as Gemini Pro (text, images, audio, video and PDFs) in a million-token window.

Once it starts, it is fast: about 300 tokens a second in independent tests. Starting is slower, at about 13 seconds to the first token against a median of 3, and it is wordy, so tasks can cost more than its rates suggest.

What is Gemini 3.8 Flash good for?

  • Coding agents at a mid-range price.
  • Working through large volumes of video, audio and PDFs.
  • Finance and legal analysis agents.
  • Batch jobs where total throughput matters more than the first word.

Gemini 3.8 Flash limitations

  • Slow to begin answering, which makes it a poor fit for live chat.
  • Verbose: one review measured tasks costing about 40% more than on Gemini 3.7 Flash at the same rates.
  • Google’s model card notes its safety behaviour in languages other than English slipped compared with 3.7 Flash.

How to use the Gemini 3.8 Flash API

Use the OpenAI SDK you already have: point it at Roar AI and set the model name. Read the docs.

from openai import OpenAI

client = OpenAI(base_url="https://api.roar-ai.com/v1", api_key="roar_live_…")

reply = client.chat.completions.create(
    model="gemini-3.8-flash",
    messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)

Gemini 3.8 Flash FAQ

How much does Gemini 3.8 Flash cost?

Input is $0.75 per 1M tokens; output is $3.75 per 1M tokens. For example, 1,000 requests with 3,000 input and 1,000 output tokens each cost $6.

Can I use Gemini 3.8 Flash alongside other models?

Yes. Every model on Roar AI is on the same API key and the same monthly invoice, so switching from Gemini 3.8 Flash to another model only means changing the model name in your code.

Is Gemini 3.8 Flash open source?

No. Google does not publish the weights, so it is only available through an API like this one.

What is the context window of Gemini 3.8 Flash?

Gemini 3.8 Flash can read up to 1.05M tokens in one request, and write an answer of up to 66K tokens.

Can Gemini 3.8 Flash read images and PDFs?

Yes. Gemini 3.8 Flash reads images and PDFs directly.

Start using Gemini 3.8 Flash

Create a free account, get an API key and call Gemini 3.8 Flash with the OpenAI SDK.