How much does the Gemini Flash Lite API cost?

On FastMetal, Gemini Flash Lite is billed per token in yen: ¥0 per 1M input tokens and ¥0 per 1M output tokens, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.

Can I call Gemini Flash Lite with the OpenAI SDK?

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

What is the context window of Gemini Flash Lite?

1,000,000 tokens, shared between the prompt and the response.

What do I need to try Gemini Flash Lite?

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-flash-lite

Gemini Flash Lite

Google's fastest and most cost-efficient model in the Gemini series. Delivers frontier-class performance with 2.5x faster time-to-first-token, ideal for high-volume, latency-sensitive applications.

1,000,000 tokens

Input: ¥0/M

Output: ¥0/M

Try in Chat Get API Key

Specifications

Modalities

Input

text

image

video

audio

Output

text

Code Examples

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

How Gemini Flash Lite 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.

To find the number of 'r's in the word **"strawberry"**, let's break it down letter by letter: 1. **s** 2. **t** 3. **r** (That's 1) 4. **a** 5. **w** 6. **b** 7. **e** 8. **r** (That's 2) 9. **r** (That's 3) 10. **y** Step-by-step reasoning: * Looking at the first half of the word ("straw"), we find the first **r** as the third letter. * Looking at the second half ("berry"), we find two more **r**s right next to each other before the final 'y'. Adding them up (1 + 2), there are a total of **3** 'r's in "strawberry".

1.4s response197 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…

This error occurs because the `users` prop is being passed as `undefined` (or hasn't loaded yet) when the component first renders, and JavaScript throws an error when you try to call the `.map()` method on `undefined`. This commonly happens when: 1. The parent component is fetching data asynchronously, and `users` isn't available on the initial render. 2. The parent component forgets to pass the `users` prop. Here are the three best ways to fix this: ### Fix 1: Optional Chaining (Recommended & Modern) You can use the optional chaining operator (`?.`) to safely attempt to map over `users` only if it exists. If it's undefined, it will render nothing instead of crashing. ```jsx function Use…

2.2s response458 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 Python function, categorized by **Readability**, **Performance**, **Best Practices**, and **Robustness**, followed by an optimized version of the code. --- ### 1. Issues & Areas for Improvement * **Imports Inside the Function:** `import requests` and `import time` are placed inside the function body. This causes Python to look up and import these modules on every single function call, which hurts performance. They should be placed at the top of the file. * **Bare `except:` Clause:** Catching all exceptions blindly (including `KeyboardInterrupt` and `SystemExit`) is an anti-pattern. You should catch specific exceptions, primarily `requests.exceptions.RequestExcepti…

3.2s response745 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the Gemini Flash Lite API cost?: On FastMetal, Gemini Flash Lite is billed per token in yen: ¥0 per 1M input tokens and ¥0 per 1M output tokens, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
Can I call Gemini Flash Lite with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "gemini-flash-lite-free" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of Gemini Flash Lite?: 1,000,000 tokens, shared between the prompt and the response.
What do I need to try Gemini Flash Lite?: 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.

Try Gemini Flash Lite right now

Gemini Flash Lite is available on FastMetal through one API key. Start in the browser, or call it from the OpenAI SDK.

Create a free account

More from Google

Gemini 3.1 Pro Preview Custom Tools

1,048,576 tokens

Gemini 3 Flash Preview

Nano Banana (Gemini 2.5 Flash Image)

32,768 tokens

Gemini 2.5 Flash Lite Preview 09-2025

1,048,576 tokens