LLM API

TTAPI LLM API, Cheap and stable chatgpt

ChatGPT - Create chat completion

POST https://api.ttapi.io/v1/chat/completions

Creates a model response for the given chat conversation.

Headers

Name	Type	Description
TT-API-KEY*	String	Your API Key in TT API used for request authorization

Request Body

Name	Type	Required	Description
messages	array	true	A list of messages comprising the conversation so far. Example code.
model	string	true	ID of the model to use. See the model endpoint compatibility table for details on which models work with the Chat API.
others	...	false	More refer to... (opens in a new tab)

Example Request

import requests
endpoint = "https://api.ttapi.io/v1/chat/completions"
headers = {
"TT-API-KEY": your_key
}
data = {
    "messages":[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"}
    ],
    "model": "gpt-4o"
}
response = requests.post(endpoint, headers=headers, json=data)
print(response.status_code)
print(response.json())

Example Response

{
    "id": "chatcmpl-83jZ61GDHtdlsFUzXDbpGeoU193Mj",
    "object": "chat.completion",
    "created": 1695900828,
    "model": "gpt-3.5-turbo",
    "choices": [{
        "index": 0,
        "message": {
            "role": "assistant",
            "content": "Hello! How can I assist you today?"
        },
        "finish_reason": "stop"
    }],
    "usage": {
        "prompt_tokens": 19,
        "completion_tokens": 9,
        "total_tokens": 28
    }
}

Claude - Create a Message

POST https://api.ttapi.io/v1/messages

💡

Claude does not support "system" and "think" params.

Create a Message.

Headers

Name	Type	Description
TT-API-KEY*	String	Your API Key in TT API used for request authorization

Request Body

Name	Type	Required	Description
messages	array	true	Example with a single user message. Example code.
model	string	true	See models for additional details and options.
max_tokens	integer	true	The maximum number of tokens to generate before stopping.
others	...	false	More refer to... (opens in a new tab)

Example Request

import requests
endpoint = "https://api.ttapi.io/v1/messages"
headers = {
    "TT-API-KEY": your_key
}
data = {
    "messages":[
        {"role": "user", "content": "Hello!"}
    ],
    "model": "claude-3-5-sonnet-20240620",
    "max_tokens": 1024
}
response = requests.post(endpoint, headers=headers, json=data)
print(response.status_code)
print(response.json())

Example Response

{
    "content": [
        {
            "text": "Hi! My name is Claude.",
            "type": "text"
        }
    ],
    "id": "msg_013Zva2CMHLNnXjNJJKqJ2EF",
    "model": "claude-3-5-sonnet-20240620",
    "role": "assistant",
    "stop_reason": "end_turn",
    "stop_sequence": null,
    "type": "message",
    "usage": {
        "input_tokens": 10,
        "output_tokens": 25
    }
}

Grok - Chat

POST https://api.ttapi.io/v1/grok/chat/completions

TTAPI integrates Grok chat endpoint (opens in a new tab), except for the inconsistent key in the header, the rest of the usage is consistent with the official one

Headers

Name	Type	Description
TT-API-KEY*	String	Your API Key in TT API used for request authorization

Request Body

Name	Type	Required	Description
messages	array	true	Example with a single user message. Example code.
model	string	true	See models for additional details and options.
others	...	false	More refer to... (opens in a new tab)

Example Request

import requests
endpoint = "https://api.ttapi.io/v1/grok/chat/completions"
headers = {
    "TT-API-KEY": your_key
}
data = {
    "messages":[
        {
            "role": "user",
            "content": "hello"
        }
    ],
    "model": "grok-2-latest",
}
response = requests.post(endpoint, headers=headers, json=data)
print(response.status_code)
print(response.json())

Example Response

{
"status": "SUCCESS",
"message": "success",
"data": {
    "created": 1741243022,
    "usage": {
        "completion_tokens": 10,
        "prompt_tokens": 7,
        "prompt_tokens_details": {
            "audio_tokens": 0,
            "text_tokens": 7,
            "image_tokens": 0,
            "cached_tokens": 0
        },
        "total_tokens": 17,
        "reasoning_tokens": 0
    },
    "model": "grok-2-1212",
    "id": "31fd8288-82ef-4c82-b490-7dc02c3c3d0a",
    "choices": [
        {
            "finish_reason": "stop",
            "index": 0,
            "message": {
                "role": "assistant",
                "refusal": null,
                "content": "Hello! How can I assist you today?"
            }
        }
    ],
    "system_fingerprint": "fp_5c0c5bd9d9",
    "object": "chat.completion"
}
}

GPT - Example Message

[
   {"role": "system", "content": "You are a helpful assistant."},
   {"role": "user", "content": "Hello!"}
]

Claude - Example Message

[
  {"role": "user", "content": "Hello there."},
  {"role": "assistant", "content": "Hi, I'm Claude. How can I help you?"},
  {"role": "user", "content": "Can you explain LLMs in plain English?"},
]

Grok - Example Message

{
    "messages": [
        {
            "role": "user",
            "content": "hello"
        }
    ],
    "model": "grok-2-latest",
    "stream": false
}

Luma Flux API