Gemini 3.8 Flash: pricing, context and performance

Overview

Released on September 2, 2026, Gemini 3.8 Flash is one of the 14 Google DeepMind models tracked on this site. It is a closed model: you access it through an API, from Google DeepMind or one of the 33 providers listed on models.dev. It has a reasoning mode: it can "think" before answering, which helps with multi-step problems but uses more tokens, and therefore more money. It is a very recent release.

We file it under mid-range models (34 models in this category on the site).

Pricing and budget

Gemini 3.8 Flash costs $0.75 per million input tokens and $3.75 per million output tokens (developer's price, checked on October 22, 2026).

To put it in perspective: reading 20,000 tokens (about thirty pages) and writing 2,000 costs roughly $0.023; a thousand of those tasks, $22.5.

That is 1.2 times cheaper than the median output price of mid-range models ($4.38).

Tokens read back from cache cost $0.075 per million, which helps an agent that keeps resending the same context.

To estimate your own budget, use the agent cost calculator.

Measured performance

According to results published by Epoch AI (checked on October 22, 2026), Gemini 3.8 Flash has a capability index of 83.7 out of 100, computed on 5 benchmarks from our basket.

That puts it at #22 in our weekly model ranking.

• GPQA Diamond (PhD-level science questions): 95.4% — the best tracked model, Gemini 4 Argon, reaches 96.4%
• OTIS Mock AIME (competition mathematics problems): 98.9% — the best tracked model, GPT-5.5 Pro, reaches 100%
• FrontierMath (very hard research-level mathematics): 68.4% — the best tracked model, GPT-6 Astra, reaches 93.7%
• FrontierCode (advanced programming tasks): 41.2% — the best tracked model, Claude Opus 5.5, reaches 54.6%

What it can do

Its context window reaches 1,048,576 tokens, roughly 1,573 pages of text at 500 words per page: enough to load a whole book or a mid-sized codebase. A single answer can run to 65,536 tokens.

It accepts as input: text, image, video, audio and PDF.

It can call tools (functions, APIs) and return structured JSON output, which makes it a possible foundation for an AI agent.

What is it good for?

Given its category, Gemini 3.8 Flash is mainly aimed at a balance between quality and cost, for everyday uses that do not justify a frontier model.

Its very large context window makes it worth considering for analysing large sets of documents in a single request.

Before adopting it, test it on your own examples: benchmarks measure standard tasks, not your job.

What could replace it?

In the same category, the models closest to Gemini 3.8 Flash are:

• Claude Opus 4.8 (Anthropic, index 83.4) — see the comparison
• Claude Opus 4.7 (Anthropic, index 83.3) — see the comparison
• Gemini 3 Flash Preview (Google DeepMind, index 80.3) — see the comparison
• Grok 4.7 (xAI, index 79.9) — see the comparison