gpt-4-turbo

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

• gpt-4-turbo

• gpt-4-turbo-2024-04-09

Model Overview

The model enhances the already impressive capabilities of ChatGPT 4 by significantly reducing response times, making it ideal for applications requiring instant feedback. It maintains the advanced conversational abilities of ChatGPT 4, ensuring that speed enhancements do not sacrifice the depth and coherence of interactions. Replacement for all previous GPT-4 preview models.

Setup your API Key

If you don’t have an API key for the AI/ML API yet, feel free to use our Quickstart guide.

Submit a request

API Schema

Generate a conversational response using a language model.

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.

post

/v1/chat/completions

Authorizations

Body

frequency_penaltynumber | nullable

logprobsboolean | nullable

top_logprobsnumber | nullable

max_tokensnumber · min: 1 · default: 512

max_completion_tokensinteger · min: 1

ninteger | nullable

presence_penaltynumber | nullable

seedinteger · min: 1

streamboolean · default: false

top_pnumber · min: 0.1 · max: 1

temperaturenumber · max: 2

parallel_tool_callsboolean

modelundefined · enumrequired

Options: gpt-4-turbo, gpt-4-turbo-2024-04-09

reasoning_effortstring · enum

Options: low, medium, high

logit_biasobject | nullable

stream_optionsobject

stopany of

tool_choiceany of

toolsobject[]

response_formatone of

predictionobject

messagesone of[]required

Responses

cURL

JavaScript

Python

HTTP

cURL

curl -L \
  --request POST \
  --url 'https://api.aimlapi.com/v1/chat/completions' \
  --header 'Authorization: Bearer JWT' \
  --header 'Content-Type: application/json' \
  --data '{
    "frequency_penalty": 1,
    "logprobs": true,
    "top_logprobs": 1,
    "max_tokens": 512,
    "max_completion_tokens": 1,
    "n": 1,
    "presence_penalty": 1,
    "seed": 1,
    "stream": false,
    "top_p": 1,
    "temperature": 1,
    "parallel_tool_calls": true,
    "model": "gpt-4-turbo",
    "reasoning_effort": "low",
    "logit_bias": {
      "ANY_ADDITIONAL_PROPERTY": 1
    },
    "stream_options": {
      "include_usage": true
    },
    "stop": "text",
    "tool_choice": "none",
    "tools": [
      {
        "type": "function",
        "function": {
          "description": "text",
          "name": "text",
          "parameters": null,
          "required": [
            "text"
          ]
        }
      }
    ],
    "response_format": {
      "type": "text"
    },
    "prediction": {
      "type": "content",
      "content": "text"
    },
    "messages": [
      {
        "name": "text",
        "role": "system",
        "content": "text"
      }
    ]
  }'

201

201

No body