# Gemini 3.5 Flash

> Gemini 3.5 Flash is Google's multimodal model for reasoning, structured output, tool calling and vision, available through RealRelay's OpenAI-compatible API.

## Key facts

- Model author: Google
- Input: $1.4521 per 1M tokens
- Output: $8.7126 per 1M tokens
- Cached input: $0.1452 per 1M tokens
- Context window: 1,048,576 tokens
- Input modalities: audio, image, text, video
- Output modalities: text
- Capabilities: reasoning, structured_output, tools, vision
- Released: 2026-05-19
- Knowledge cutoff: 2025-01-01
- Model IDs: `jd/gemini-3.5-flash`
- Model page: https://www.realrelay.ai/model/google/gemini-3.5-flash

## Overview

Gemini 3.5 Flash is a Google model that accepts text, image, audio and video input and returns text output. It supports reasoning, structured output, tool calling and vision.

On RealRelay the model is callable as jd/gemini-3.5-flash through one OpenAI-compatible endpoint, so requests use the OpenAI chat completions format with a RealRelay API key. Input is $1.45 per 1M tokens and output is $8.71 per 1M tokens. The model was released on May 19, 2026, with a knowledge cutoff of January 1, 2025.

## Capabilities

The model accepts text, image, audio and video as input and returns text. A 1,048,576 token context window means a single request can carry large amounts of text, image, audio and video input together.

Capabilities include reasoning, structured output, tool calling and vision. Structured output returns responses that follow a defined format, and vision covers reasoning over images sent in a request.

## Pricing

Input is billed at $1.45 per 1M tokens and output at $8.71 per 1M tokens. Cached input reads are billed at $0.1452 per 1M tokens.

Billing is metered by tokens, so the price of a request depends on how many input tokens it sends and how many output text tokens it returns.

## Use cases

Gemini 3.5 Flash fits work that combines reasoning with multimodal input, such as answering questions about images, audio or video and turning free-form text into structured output.

With tool calling and structured output, it can also run agent workflows that call functions and return structured results through the OpenAI-compatible endpoint.

## 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-3.5-flash", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is Gemini 3.5 Flash?

Gemini 3.5 Flash is a Google multimodal model available on RealRelay as jd/gemini-3.5-flash. It accepts text, image, audio and video input and returns text output.

### What is the price of Gemini 3.5 Flash?

Input is $1.45 per 1M tokens and output is $8.71 per 1M tokens. Cached input reads are $0.1452 per 1M tokens.

### What is the context window of Gemini 3.5 Flash?

The context window is 1,048,576 tokens.

### Which inputs and outputs does Gemini 3.5 Flash support?

It accepts text, image, audio and video input and returns text output.

### Does Gemini 3.5 Flash support tool calling?

Yes. The model supports tool calling, reasoning, structured output and vision.

### When was Gemini 3.5 Flash released?

It was released on May 19, 2026, with a knowledge cutoff of January 1, 2025.

### How do I call Gemini 3.5 Flash through the OpenAI-compatible API?

Send a chat completions request to RealRelay's OpenAI-compatible endpoint with the model ID jd/gemini-3.5-flash and your RealRelay API key.