# Gemini 3.8 Flash

> A Google Flash model for software engineering, agentic tasks and reasoning, callable through RealRelay's OpenAI-compatible endpoint.

## Key facts

- Model author: Google
- Input: $0.75 per 1M tokens
- Output: $3.75 per 1M tokens
- Cached input: $0.075 per 1M tokens
- Context window: 1,048,576 tokens
- Input modalities: audio, file, image, text, video
- Output modalities: text
- Capabilities: reasoning, structured_output, tools, vision
- Released: 2026-09-02
- Model IDs: `jd/gemini-3.8-flash`
- Model page: https://www.realrelay.ai/model/google/gemini-3.8-flash

## Overview

Gemini 3.8 Flash is a Google Flash model for software engineering, agentic tasks and reasoning. It accepts text, images, audio, video and files, and returns text.

Reasoning, structured output, tool calling and vision are supported. The context window is 1,048,576 tokens and the model was released on September 2, 2026. Requests use the model ID jd/gemini-3.8-flash on RealRelay.

## Capabilities

Text, image, audio, video and file input are accepted, and every response is text. Reasoning, structured output, tool calling and vision are part of the capability set.

The 1,048,576-token context window holds long inputs and mixed-media prompts in one request, and structured output supports replies that a downstream system can parse.

## Pricing

Prices are per 1M tokens: input is $0.75 per 1M tokens and output is $3.75 per 1M tokens. Cached input reads are $0.075 per 1M tokens.

Usage is metered on input and output tokens, and text is the only output modality.

## Use Cases

Software engineering assistance, agentic workflows that call tools, and prompts that mix text with images, audio, video or files fit this model.

Long inputs of up to 1,048,576 tokens can be handled in a single request, and structured output suits automation that expects a formatted reply.

## Call it

OpenAI-compatible chat completions:

```bash
curl https://www.realrelay.ai/v1/chat/completions \
  -H "Authorization: Bearer $REALRELAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "jd/gemini-3.8-flash", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is Gemini 3.8 Flash?

It is a Google Flash model for software engineering, agentic tasks and reasoning, with tool calling, structured output and vision.

### What are the prices for Gemini 3.8 Flash?

Input is $0.75 per 1M tokens, output is $3.75 per 1M tokens, and cached input reads are $0.075 per 1M tokens.

### How large is the context window?

The context window is 1,048,576 tokens.

### Which inputs and outputs does Gemini 3.8 Flash support?

Text, image, audio, video and file input; output is text only.

### Does Gemini 3.8 Flash support tool calling and structured output?

Yes, alongside reasoning and vision.

### When was Gemini 3.8 Flash released?

It was released on September 2, 2026.

### How do I call Gemini 3.8 Flash through the API?

Use the model ID jd/gemini-3.8-flash in a request to RealRelay's OpenAI-compatible endpoint.