Llama-4-scout

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

• meta-llama/llama-4-scout

Model Overview

A 17 billion active parameter model with 16 experts, is the best multimodal model in the world in its class and is more powerful than all previous generation Llama models. Additionally, the model offers an industry-leading context window of 10M and delivers better results than Gemma 3, Gemini 2.0 Flash-Lite, and Mistral 3.1 on a wide range of common benchmarks.

How to Make a Call

1

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 that key is enabled on UI.

2

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.

3

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.

4

^_(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 API schema, which lists all available parameters along with notes on how to use them.

5

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 Quickstart guide.

API Schema

Generate a conversational response using a language model.

post

Creates a chat completion using a language model, allowing interactive conversation by predicting the next response based on the given chat history. This is useful for AI-driven dialogue systems and virtual assistants.

Authorizations

Body

modelundefined · 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.

Default: 512

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

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

ninteger · min: 1Optional

How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs.

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.

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.

top_knumberOptional

Only sample from the top K options for each subsequent token. Used to remove "long tail" low probability responses. Recommended for advanced use cases only. You usually only need to use temperature.

temperaturenumberOptional

What sampling temperature to use, between 0 and 2. 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.

repetition_penaltynumber | nullableOptional

A number that controls the diversity of generated text by reducing the likelihood of repeated sequences. Higher values decrease repetition.

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.

echobooleanOptional

If True, the response will contain the prompt. Can be used with logprobs to return prompt logprobs.

min_pnumber · max: 1Optional

A number between 0 and 1 that can be used as an alternative to top_p and top_k.

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.

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.

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

response_formatone ofOptional

An object specifying the format that the model must output.

or

or

Responses

201Success

post

HTTPcURLJavaScriptPython

POST /v1/chat/completions HTTP/1.1
Host: api.aimlapi.com
Authorization: Bearer <YOUR_AIMLAPI_KEY>
Content-Type: application/json
Accept: */*
Content-Length: 530

{
  "model": "meta-llama/llama-4-scout",
  "messages": [
    {
      "role": "system",
      "content": "text",
      "name": "text"
    }
  ],
  "max_tokens": 1,
  "stop": "text",
  "stream": true,
  "stream_options": {
    "include_usage": true
  },
  "n": 1,
  "seed": 1,
  "top_p": 1,
  "top_k": 1,
  "temperature": 1,
  "repetition_penalty": 1,
  "logprobs": true,
  "echo": true,
  "min_p": 1,
  "presence_penalty": 1,
  "frequency_penalty": 1,
  "logit_bias": {
    "ANY_ADDITIONAL_PROPERTY": 1
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "description": "text",
        "name": "text",
        "parameters": null
      }
    }
  ],
  "tool_choice": "none",
  "response_format": {
    "type": "text"
  }
}

201Success

No content

Code Example (Python)

import requests

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":"meta-llama/llama-4-scout",
        "messages":[
            {
                "role":"user",

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

data = response.json()
print(data)

Response

{'id': 'npXpsYC-2j9zxn-92e24e9e0c97d74d', 'object': 'chat.completion', 'choices': [{'index': 0, 'finish_reason': 'stop', 'logprobs': None, 'message': {'role': 'assistant', 'content': "Hello! It's nice to meet you. Is there something I can help you with or would you like to chat?", 'tool_calls': []}}], 'created': 1744288767, 'model': 'meta-llama/Llama-4-Scout-17B-16E-Instruct', 'usage': {'prompt_tokens': 4, 'completion_tokens': 30, 'total_tokens': 34}}