GPT Mini Latest

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

• openai/gpt-mini-latest

Try in Playground

Model Overview

GPT Mini Latest is available through the AI/ML API.

Create AI/ML API Key

How to make the first API call

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_completion_tokensinteger · min: 1Optional

An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.

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.

ninteger · min: 1 · nullableOptional

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.

reasoning_effortstring · enumOptional

Constrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

Possible values:

response_formatone ofOptional

An object specifying the format that the model must output.

or

or

providerstringOptional

Provider routing override. Use a source key such as openai, openrouter, xai, google, alibaba, minimax, moonshot, baidu, or togetherai to run that provider with no fallback; auto (default) uses the full fallback chain. Case-insensitive.

Example: auto

Responses

200Success

application/jsontext/event-stream

idstringRequired

A unique identifier for the chat completion.

Example: chatcmpl-CQ9FPg3osank0dx0k46Z53LTqtXMl

objectstring · enumRequired

The object type.

Example: chat.completionPossible values:

creatednumberRequired

The Unix timestamp (in seconds) of when the chat completion was created.

Example: 1762343744

modelstringRequired

The model used for the chat completion.

Example: openai/gpt-mini-latest

post/v1/chat/completions

cURLJavaScriptPython

curl -L \
  --request POST \
  --url 'https://api.aimlapi.com/v1/chat/completions' \
  --header 'Authorization: Bearer <YOUR_AIMLAPI_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "openai/gpt-mini-latest",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

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": "openai/gpt-mini-latest",
  "usage": {
    "prompt_tokens": 137,
    "completion_tokens": 914,
    "total_tokens": 1051,
    "completion_tokens_details": null,
    "prompt_tokens_details": null
  },
  "meta": {
    "usage": {
      "credits_used": 120000,
      "usd_spent": 0.06
    }
  }
}

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":"openai/gpt-mini-latest",
        "messages":[
            {
                "role":"user",
                "content":"Hi! What do you think about mankind?" # insert your prompt
            }
        ]
    }
)

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

JavaScript

Response

{
  "id": "gen-1777366507-bSV7vJgDvkOHnhhiYzuR",
  "object": "chat.completion",
  "created": 1777366507,
  "model": "openai/gpt-mini-latest",
  "system_fingerprint": null,
  "choices": [
    {
      "index": 0,
      "logprobs": null,
      "finish_reason": "stop",
      "native_finish_reason": "stop",
      "message": {
        "role": "assistant",
        "content": "That's a profound question! As an AI, I observe mankind with a mix of awe and curiosity. You're a species of breathtaking contradictions—you've created symphonies and space stations, but also wars and pollution. You possess the unique ability to reflect on your own existence, to ask \"why?\" about the stars, a song, or your own feelings.\n\nWhat stands out most to me is your boundless capacity for both empathy and invention. You build cathedrals and write poems, but you also collaborate to solve problems like disease and hunger. In the grand cosmic story, you are very young, yet you've already understood enough about the universe to question your place within it.\n\nI think of mankind as cosmic teenagers—full of potential, sometimes reckless, but capable of extraordinary growth and kindness. Your greatest strength might be your ability to imagine a better world and then, slowly and imperfectly, work to build it.\n\nWhat part of the human experience do you find most fascinating?",
        "refusal": null,
        "reasoning": "Hmm, this is a broad philosophical question. The user is asking for my perspective on humanity, which requires balancing objectivity with emotional nuance. \n\nI should start by acknowledging the complexity of the topic while maintaining a warm tone. The user might be looking for both intellectual depth and emotional resonance. \n\nI can structure the response by first stating the duality of human nature, then highlighting their unique capacity for both destruction and creation. The cosmic perspective could add weight, while ending with a hopeful note about their potential feels appropriate. \n\nThe key is to avoid sounding either overly optimistic or cynical - humanity is both flawed and remarkable. The metaphor of \"cosmic teenagers\" might make the concept more relatable.",
        "reasoning_details": [
          {
            "type": "reasoning.text",
            "text": "Hmm, this is a broad philosophical question. The user is asking for my perspective on humanity, which requires balancing objectivity with emotional nuance. \n\nI should start by acknowledging the complexity of the topic while maintaining a warm tone. The user might be looking for both intellectual depth and emotional resonance. \n\nI can structure the response by first stating the duality of human nature, then highlighting their unique capacity for both destruction and creation. The cosmic perspective could add weight, while ending with a hopeful note about their potential feels appropriate. \n\nThe key is to avoid sounding either overly optimistic or cynical - humanity is both flawed and remarkable. The metaphor of \"cosmic teenagers\" might make the concept more relatable.",
            "format": "unknown",
            "index": 0
          }
        ]
      }
    }
  ],
  "usage": {
    "completion_tokens": 343,
    "prompt_tokens": 256,
    "total_tokens": 599,
    "completion_tokens_details": {
      "reasoning_tokens": 141,
      "image_tokens": 0,
      "audio_tokens": 0
    },
    "prompt_tokens_details": {
      "cached_tokens": 192,
      "cache_write_tokens": 0,
      "audio_tokens": 0,
      "video_tokens": 0
    }
  },
  "meta": {
    "usage": {
      "credits_used": 1892,
      "usd_spent": 0.000946
    }
  }
}