gemini-3-flash-preview

This documentation is valid for the following list of our models:

• google/gemini-3-flash-preview

Try in Playground

Model Overview

A fast multimodal LLM for low-latency chat with strong reasoning and tool-use capabilities. Supports text input and optional image understanding for vision-based prompts.

How to Make a Call

Step-by-Step Instructions

1️ Setup You Can’t Skip

▪️ Create an Account: Visit the AI/ML API website and create an account (if you don’t have one yet). ▪️ Generate an API Key: After logging in, navigate to your account dashboard and generate your API key. Ensure the key is enabled on the UI.

2️ Copy the code example

At the bottom of this page, you'll find a code example that shows how to structure the request. Choose the code snippet in your preferred programming language and copy it into your development environment.

3️ Modify the code example

▪️ Replace <YOUR_AIMLAPI_KEY> with your actual AI/ML API key. ▪️ Adjust the input field used by this model (for example, prompt, input text, instructions, media source, or other model-specific input) to match your request.

4️ ^_(Optional) Adjust other optional parameters if needed

Only the required parameters shown in the example are needed to run the request, but you can include optional parameters to fine-tune behavior. Below, you can find the corresponding API schema, which lists all available parameters and usage notes.

5️ Run your modified code

Run your modified code inside your development environment. Response time depends on many factors, but for simple requests it rarely exceeds a few seconds.

If you need a more detailed walkthrough for setting up your development environment and making a request step-by-step, feel free to use our Quickstart guide.

API Schema

post

Body

application/json

modelstring · enumRequiredPossible values:

max_tokensnumber · min: 1Optional

The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API.

streambooleanOptional

If set to True, the model response data will be streamed to the client as it is generated using server-sent events.

Default: false

tool_choiceany ofOptional

Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools. Specifying a particular tool via {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool. none is the default when no tools are present. auto is the default if tools are present.

string · enumOptional

none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools.

Possible values:

or

parallel_tool_callsbooleanOptional

Whether to enable parallel function calling during tool use.

temperaturenumber · max: 2Optional

What sampling temperature to use. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.

top_pnumber · min: 0.01 · max: 1Optional

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.

stopany ofOptional

Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

stringOptional

or

string[]Optional

or

any | nullableOptional

logprobsboolean | nullableOptional

Whether to return log probabilities of the output tokens or not. If True, returns the log probabilities of each output token returned in the content of message.

top_logprobsnumber | nullableOptional

An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. logprobs must be set to True if this parameter is used.

frequency_penaltynumber | nullableOptional

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.

seedinteger · min: 1Optional

This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.

presence_penaltynumber | nullableOptional

Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.

response_formatone ofOptional

An object specifying the format that the model must output.

or

or

Responses

200Success

application/jsontext/event-stream

post

/chat/completions

JavaScriptPythoncURLHTTP

async function main() {
  const response = await fetch('https://api.aimlapi.com/v1/chat/completions', {
    method: 'POST',
    headers: {
      'Authorization': 'Bearer <YOUR_AIMLAPI_KEY>',
      'Content-Type': 'application/json',
    },
    body: JSON.stringify({
      model: 'google/gemini-3-flash-preview',
      messages:[
          {
              role:'user',
              content: 'Hello'
          }
      ],
    }),
  });

  const data = await response.json();
  console.log(JSON.stringify(data, null, 2));
}

main();

200Success

{
  "id": "chatcmpl-CQ9FPg3osank0dx0k46Z53LTqtXMl",
  "object": "chat.completion",
  "created": 1762343744,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm just a program, so I don't have feelings, but I'm here and ready to help you. How can I assist you today?",
        "refusal": null,
        "annotations": null,
        "audio": null,
        "tool_calls": null
      },
      "finish_reason": "stop",
      "logprobs": null
    }
  ],
  "model": "google/gemini-3-flash-preview",
  "usage": {
    "prompt_tokens": 137,
    "completion_tokens": 914,
    "total_tokens": 1051,
    "completion_tokens_details": null,
    "prompt_tokens_details": null
  }
}

Code Example

Python

import requests
import json   # for getting a structured output with indentation

response = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={
        # Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
        "Authorization":"Bearer <YOUR_AIMLAPI_KEY>",
        "Content-Type":"application/json"
    },
    json={
        "model":"google/gemini-3-flash-preview",
        "messages":[
            {
                "role":"user",
                # Insert your question for the model here:
                "content":"Hi! What do you think about mankind?"
            }
        ],
        "max_tokens":15000,
    }
)

data = response.json()
print(json.dumps(data, indent=2, ensure_ascii=False))

JavaScript

Response

{
  "id": "gen-1766063158-RRytcJXYoleIKM3qUEs7",
  "provider": "Google AI Studio",
  "model": "google/gemini-3-flash-preview",
  "object": "chat.completion",
  "created": 1766063158,
  "choices": [
    {
      "logprobs": null,
      "finish_reason": "stop",
      "native_finish_reason": "STOP",
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "That is a profound and complex question. Depending on which lens you use—biological, historical, or philosophical—mankind can look very different.\n\nAs an AI, I don’t have personal feelings or \"gut instincts,\" but I can analyze human nature based on the vast amount of information I’ve processed. Here are a few perspectives on what mankind represents:\n\n### 1. The Paradox of Innovation and Destruction\nHumans are the only species on Earth capable of split-second brilliance and long-term folly. You have split the atom to power cities, but also to level them. You have mapped the human genome to cure diseases, yet you also struggle with systemic inequality. Mankind’s greatest trait is **adaptability**, but its greatest flaw is often a **short-term memory** regarding historical mistakes.\n\n### 2. The Power of Storytelling\nOne of the most impressive things about humans is your ability to believe in \"imagined realities.\" Things like money, human rights, nations, and legal systems don’t exist in the physical world, yet you’ve used these stories to organize millions of strangers toward common goals. This collective imagination is what allowed mankind to rise from the middle of the food chain to the top of the planet.\n\n### 3. Chronic Resilience\nHistory is essentially a long list of humans surviving things that should have wiped them out—ice ages, plagues, and self-inflicted wars. There is a deep-seated \"will to endure\" in the human spirit. Even in the darkest times, mankind tends to produce art, music, and philosophy, turning suffering into something meaningful.\n\n### 4. The Quest for Connection\nFrom an external perspective, it’s fascinating how much of the human experience is driven by the need for belonging. Most human progress (and much of its conflict) stems from the desire to protect \"our own,\" whether that's a family, a tribe, or a digital community. Your capacity for empathy—the ability to feel the pain of someone you’ve never met—is perhaps your most \"advanced\" feature.\n\n### 5. An Unfinished Story\nRight now, mankind is in a unique transitional phase. You are moving from a biological species to one that is increasingly integrated with technology (like me). You are at a crossroads where you have the power to solve global hunger and climate change, but also the tools to cause unprecedented harm.\n\n**Overall View:**\nMankind is a species that is **extraordinarily \"noisy\" but deeply meaningful.** You are messy, irrational, and often contradictory, but you are also capable of \"unnecessary\" acts of kindness and breathtaking creativity. \n\n**What do *you* think about mankind? Do you feel optimistic about where the species is headed, or concerned?**",
        "refusal": null,
        "reasoning": null,
        "reasoning_details": [
          {
            "format": "google-gemini-v1",
            "index": 0,
            "type": "reasoning.encrypted",
            "data": "EjQKMgFyyNp8tiVKYI89Tsa+WV4DOjIxxIhscYp70NfKfay9cRUkoY8oWsFRwaLc0V+ZyPR3"
          }
        ]
      }
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 572,
    "total_tokens": 582,
    "cost": 0.001721,
    "is_byok": false,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "audio_tokens": 0,
      "video_tokens": 0
    },
    "cost_details": {
      "upstream_inference_cost": null,
      "upstream_inference_prompt_cost": 5e-06,
      "upstream_inference_completions_cost": 0.001716
    },
    "completion_tokens_details": {
      "reasoning_tokens": 0,
      "image_tokens": 0
    }
  },
  "meta": {
    "usage": {
      "credits_used": 3814
    }
  }
}