How much does the Gemini 3.5 Flash API cost?

On FastMetal, Gemini 3.5 Flash is billed per token in yen: ¥268.05 per 1M input tokens and ¥1,608.3 per 1M output tokens, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.

Can I call Gemini 3.5 Flash with the OpenAI SDK?

Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "gemini-3.5-flash" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.

What is the context window of Gemini 3.5 Flash?

1,048,576 tokens, shared between the prompt and the response.

What do I need to try Gemini 3.5 Flash?

Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.

Back to Models

google/gemini-3-5-flash

Gemini 3.5 Flash

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...

5/19/2026

1,048,576 tokens

Input: ¥268.05/M

Output: ¥1,608.3/M

Try in Chat Get API Key

Specifications

Modalities

Input

text

image

video

file

audio

Output

text

Supported Parameters

include_reasoning

max_tokens

reasoning

reasoning_effort

response_format

seed

stop

structured_outputs

temperature

tool_choice

tools

top_p

Max Output Tokens

65,536

Reasoning Configuration

Default: Thinking on (effort: medium)
Selectable effort levels: high
medium
low
minimal
Turning thinking off: Not possible (always thinks)

How to control thinking, and what it costs

Code Examples

curl https://api.fastmetal.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gemini-3.5-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How Gemini 3.5 Flash actually answers

Real responses to our standard prompts, recorded on FastMetal.

Count the number of 'r's in 'strawberry'

Count the number of 'r's in 'strawberry'. Explain your reasoning step by step.

There are **3** 'r's in the word "strawberry". Here is the step-by-step breakdown of how to count them: 1. **Break the word down into its individual letters:** * 1st letter: **s** * 2nd letter: **t** * 3rd letter: **r** (First 'r') * 4th letter: **a** * 5th letter: **w** * 6th letter: **b** * 7th letter: **e** * 8th letter: **r** (Second 'r') * 9th letter: **r** (Third 'r') * 10th letter: **y** 2. **Identify and count only the 'r's:** * s - t - **r** (1) - a - w - b - e - **r** (2) - **r** (3) - y By counting them as we go through the word, we find a total of **3** 'r's.

4.8s response601 output tokens

Debug This Error

I'm getting the following error in my Node.js application: TypeError: Cannot read properties of undefined (reading 'map') at UserList (/app/components/UserList.js:12:25) at renderWithHooks (/app/node_modules/rea…

### What is causing this error? The error `TypeError: Cannot read properties of undefined (reading 'map')` means that your `UserList` component is trying to call `.map()` on the `users` variable, but **`users` is currently `undefined`**. This usually happens for one of two reasons: 1. **The parent component forgot to pass the prop:** `<UserList />` was rendered without the `users` attribute. 2. **Asynchronous data fetching:** The parent component fetches the users from an API, but the API request hasn't finished yet when the component first renders, so `users` starts as `undefined`. --- ### How to fix it Here are the three best ways to fix this, depending on how you want your UI to beh…

11.2s response1524 output tokens

Code Review

Please review the following Python function and suggest improvements for readability, performance, and best practices: def get_data(url, retries=3): import requests import time for i in range(retries):…

Here is a review of your function, followed by two improved versions (one that keeps your structure but makes it Pythonic, and one production-ready version that uses industry best practices). --- ### Key Areas for Improvement 1. **Imports inside the function:** `import requests` and `import time` should be at the top of the file (PEP 8). Keeping them inside the function slows down execution if the function is called repeatedly. 2. **Bare `except:` clause:** Using `except:` without specifying an exception type is a major anti-pattern. It catches things you don't want to catch, like `KeyboardInterrupt` (Ctrl+C) or `SystemExit`. It should target `requests.RequestException`. 3. **Implicit `Tr…

19.7s response2975 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the Gemini 3.5 Flash API cost?: On FastMetal, Gemini 3.5 Flash is billed per token in yen: ¥268.05 per 1M input tokens and ¥1,608.3 per 1M output tokens, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
Can I call Gemini 3.5 Flash with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "gemini-3.5-flash" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of Gemini 3.5 Flash?: 1,048,576 tokens, shared between the prompt and the response.
What do I need to try Gemini 3.5 Flash?: Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.