gemma-3n-4b

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

google/gemma-3n-e4b-it

Model Overview

Gemma 3n is the first open model built on Google’s next-generation, mobile-first architecture—designed for fast, private, and multimodal AI directly on-device. With Gemma 3n, developers get early access to the same technology that will power on-device AI experiences across Android and Chrome later this year, enabling them to start building for the future today.

How to Make a Call

Setup You Can’t Skip

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

Copy the code example

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

Modify the code example

Replace <YOUR_AIMLAPI_KEY> with your actual AI/ML API key from your account. Insert your question or request into the content field—this is what the model will respond to.

^_(Optional)Adjust other optional parameters if needed

Only model and messages are required parameters for this model (and we’ve already filled them in for you in the example), but you can include optional parameters if needed to adjust the model’s behavior. Below, you can find the corresponding , which lists all available parameters along with notes on how to use them.

Run your modified code

Run your modified code in your development environment. Response time depends on various factors, but for simple prompts 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 .

API Schema

Code Example (Python)

import requests
import json

response = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={
        "Content-Type":"application/json", 

        # Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
        "Authorization":"Bearer <YOUR_AIMLAPI_KEY>",
        "Content-Type":"application/json"
    },
    json={
        "model":"google/gemma-3n-e4b-it",
        "messages":[
            {
                "role":"user",

                # Insert your question for the model here, instead of Hello:
                "content":"Hello!"
            }
        ]
        
    }
)

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

Response

{
  "id": "gen-1749195015-2RpzznjKbGPQUJ9OK1M4",
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "finish_reason": "stop",
      "logprobs": null,
      "message": {
        "role": "assistant",
        "content": "Hello there! 👋 \n\nIt's nice to meet you! How can I help you today?  Do you have any questions, need some information, want to chat, or anything else? 😊 \n\nJust let me know what's on your mind!\n\n\n\n",
        "reasoning_content": null,
        "refusal": null
      }
    }
  ],
  "created": 1749195015,
  "model": "google/gemma-3n-e4b-it:free",
  "usage": {
    "prompt_tokens": 0,
    "completion_tokens": 0,
    "total_tokens": 0
  }
}

Previousgemma-3 NextGryphe

Last updated 18 hours ago

Was this helpful?

Model Overview

How to Make a Call

Setup You Can’t Skip

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

Copy the code example

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

Modify the code example

Replace <YOUR_AIMLAPI_KEY> with your actual AI/ML API key from your account. Insert your question or request into the content field—this is what the model will respond to.

^_(Optional)Adjust other optional parameters if needed

Run your modified code

Run your modified code in your development environment. Response time depends on various factors, but for simple prompts 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 .

Code Example (Python)

import requests
import json

response = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={
        "Content-Type":"application/json", 

        # Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
        "Authorization":"Bearer <YOUR_AIMLAPI_KEY>",
        "Content-Type":"application/json"
    },
    json={
        "model":"google/gemma-3n-e4b-it",
        "messages":[
            {
                "role":"user",

                # Insert your question for the model here, instead of Hello:
                "content":"Hello!"
            }
        ]
        
    }
)

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

Response

{
  "id": "gen-1749195015-2RpzznjKbGPQUJ9OK1M4",
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "finish_reason": "stop",
      "logprobs": null,
      "message": {
        "role": "assistant",
        "content": "Hello there! 👋 \n\nIt's nice to meet you! How can I help you today?  Do you have any questions, need some information, want to chat, or anything else? 😊 \n\nJust let me know what's on your mind!\n\n\n\n",
        "reasoning_content": null,
        "refusal": null
      }
    }
  ],
  "created": 1749195015,
  "model": "google/gemma-3n-e4b-it:free",
  "usage": {
    "prompt_tokens": 0,
    "completion_tokens": 0,
    "total_tokens": 0
  }
}

POST /v1/chat/completions HTTP/1.1 Host: api.aimlapi.com Authorization: Bearer <YOUR_AIMLAPI_KEY> Content-Type: application/json Accept: */* Content-Length: 1002 { "model": "google/gemma-3n-e4b-it", "top_k": 1, "repetition_penalty": 1, "min_p": 1, "top_a": 1, "reasoning": { "effort": "low", "max_tokens": 1, "exclude": true }, "frequency_penalty": 1, "logit_bias": { "ANY_ADDITIONAL_PROPERTY": 1 }, "logprobs": true, "top_logprobs": 1, "max_tokens": 512, "max_completion_tokens": 512, "n": 1, "prediction": { "type": "content", "content": "text" }, "presence_penalty": 1, "seed": 1, "messages": [ { "role": "system", "content": "text", "name": "text" } ], "stream": false, "stream_options": { "include_usage": true }, "top_p": 1, "temperature": 1, "stop": "text", "tools": [ { "type": "function", "function": { "description": "text", "name": "text", "parameters": null, "strict": true, "required": [ "text" ] } } ], "tool_choice": "none", "parallel_tool_calls": true, "reasoning_effort": "low", "response_format": { "type": "text" }, "audio": { "format": "wav", "voice": "alloy" }, "modalities": [ "text" ], "web_search_options": { "search_context_size": "low", "user_location": { "approximate": { "city": "text", "country": "text", "region": "text", "timezone": "text" }, "type": "approximate" } } }

Model Overview

How to Make a Call

Setup You Can’t Skip

Copy the code example

Modify the code example

(Optional) Adjust other optional parameters if needed

Run your modified code

API Schema

Code Example (Python)

Model Overview

How to Make a Call

Setup You Can’t Skip

Copy the code example

Modify the code example

(Optional) Adjust other optional parameters if needed

Run your modified code

API Schema

Code Example (Python)

Generate a conversational response using a language model.

^_(Optional)Adjust other optional parameters if needed

^_(Optional)Adjust other optional parameters if needed