Skip to content
Google

Gemini 3.8 Flash

Gemini 3.8 Flash is a large language model made by Google, added to the catalog on 2 Sep 2026. It has a context window of 1,048,576 tokens and costs $0.825 per 1M input tokens and $4.125 per 1M output tokens. It accepts text, images, files, audio and video and produces text. Typical uses: software engineering tasks, multi-step reasoning and working with text and media inputs.

Price checked ยท source: OpenRouter

What Gemini 3.8 Flash is

Google Gemini 3.8 Flash is a multimodal model from Google. It accepts text, images, video, files, and audio as input, and produces text. Its inputs can include more than one kind of material, while the response remains text. The model supports a context of up to 1,048,576 tokens, with a maximum output of 65,536 tokens. This gives it room to work with extensive prompts or provided material and to return longer text when a task calls for it.

It supports reasoning, tools, structured outputs, and response formats. These capabilities suit tasks that combine detailed instructions, source material, and a defined output shape. Google's description identifies software engineering, agentic tasks, and multi-step reasoning as areas of use. With text generation as its output, it can draft explanations, summaries, and other written responses based on text or supplied media. It can also be used with tools where the application makes tools available. The large context can be useful for considering long documents, video or audio material, or multiple inputs within one request. Its suitability depends on the task and supplied content; the catalog does not specify further limits for each media type. The model returns text rather than generated images, video, or audio.

Key features

  • Accepts text, images, video, files, and audio as input
  • Produces text with a context window of up to 1,048,576 tokens
  • Supports up to 65,536 output tokens
  • Supports tools, structured outputs, and response formats
  • Includes support for reasoning

Typical uses

  • Software engineering tasks
  • Multi-step reasoning
  • Working with text and media inputs
  • Summarising long documents
  • Producing structured text responses

Gemini 3.8 Flash pricing

US dollars, list price through OpenRouter.

Checked
Gemini 3.8 Flash price list, by variant
ItemStandardBatch
Input, per 1M tokens$0.825$0.375
Output, per 1M tokens$4.125$1.875
Cached input read, per 1M tokens$0.0825$0.0375
Cache write, per 1M tokens$0.0417$0.0417
Image input, per image$0.000001$0.00
Web search, per search$0.014$0.014
Variants of Gemini 3.8 Flash that share this page
VariantModel id
Batchgoogle/gemini-3.8-flash:batch

A variant is the same model under another id, with prices or limits of its own. Its prices are the columns of the list above.

No price change since it was added on 2 Sep 2026.

What typical tasks cost with Gemini 3.8 Flash
What a task costsCost
Answer a short question500 in / 300 out$0.0017
Summarise a 50-page PDF25,000 in / 800 out$0.024
Review a 2,000-line source file30,000 in / 2,000 out$0.033
Read a 300-page contract set150,000 in / 1,500 out$0.130
Check the provider's pageToken counts are estimates. A maker's direct price and its monthly plans can differ from the per-token price shown here.

Gemini 3.8 Flash specifications

Gemini 3.8 Flash limits and identity
Model idgoogle/gemini-3.8-flash
Versiongemini-3.8-flash-20260902
Context window1,048,576 tokensAbout 786,432 English words
Max output65,536 tokens
Knowledge cutoffNot published
Added to catalog2 Sep 2026
Gemini 3.8 Flash capabilities
Input typestext, image, video, file, audio
Output typestext
Tool callingYes
Structured outputsYes
Reasoning effort controlYes
Content moderationNot applied by provider

Sample outputs

The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.

No output has been recorded for Gemini 3.8 Flash yet.

Compare Gemini 3.8 Flash

Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.

Gemini 3.8 Flash questions

How much does Gemini 3.8 Flash cost?

Gemini 3.8 Flash costs $0.825 per 1M input tokens and $4.125 per 1M output tokens through OpenRouter, as checked on 22 Nov 2026. Summarising a 50-page PDF costs about $0.024.

What is the context window of Gemini 3.8 Flash?

1,048,576 tokens, or roughly 786,432 English words. It can write up to 65,536 tokens in one response.

Can Gemini 3.8 Flash read images and PDFs?

It accepts text, images, files, audio and video as input. It produces text, so it cannot generate images.

How do I try Gemini 3.8 Flash?

Use the "Try Gemini 3.8 Flash" button on this page. It opens the chat with Gemini 3.8 Flash selected; you type the question and press send.

Try Gemini 3.8 Flash on your own question.

It opens in the chat with this model already selected.

Sign in to Upend

Use an account you already have, or get a one-time code by email.

Use a password instead

For accounts that already have a password. Forgotten it? An emailed code signs you in just the same.