Chat Completion

In this section, we will guide you on how to use the OpenAI compatible Chat Completion API to generate human-like conversational responses.

The Chat Completion API allows you to interact with a wide range of language models in a conversational manner. You can use models from various providers, including but not limited to: GPT-4, Claude, Gemini, Llama, etc.

This versatility enables you to choose the most suitable model for your specific use case, whether you need advanced reasoning capabilities, specialized knowledge, or cost-effective solutions.

With this API, you can send a series of messages as input and receive a model-generated message as output, creating dynamic and context-aware conversations across a broad spectrum of applications.

POSThttps://api.model.box/v1/chat/completion

Chat completions

This endpoint creates a model response for the given chat conversation.

Authentication

To use the Chat Completion API, you must authenticate your requests using your API key. See Authentication for more information.

Required attributes

Name
messages
Type
array
Description
A list of messages comprising the conversation so far.
Name
model
Type
string
Description
ID of the model to use. See the model endpoint compatibility table for details on which models work with the Chat API.

Optional attributes

Name
frequency_penalty
Type
number
Description
Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far.
Name
logit_bias
Type
map
Description
Modify the likelihood of specified tokens appearing in the completion.
Name
logprobs
Type
boolean
Description
Whether to return log probabilities of the output tokens or not.
Name
max_tokens
Type
integer
Description
The maximum number of tokens that can be generated in the chat completion.
Name
n
Type
integer
Description
How many chat completion choices to generate for each input message.
Name
presence_penalty
Type
number
Description
Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far.
Name
response_format
Type
object
Description
An object specifying the format that the model must output.
Name
seed
Type
integer
Description
If specified, our system will make a best effort to sample deterministically.
Name
stop
Type
string / array
Description
Up to 4 sequences where the API will stop generating further tokens.
Name
stream
Type
boolean
Description
If set, partial message deltas will be sent, like in ChatGPT.
Name
temperature
Type
number
Description
What sampling temperature to use, between 0 and 2.
Name
top_p
Type
number
Description
An alternative to sampling with temperature, called nucleus sampling.
Name
tools
Type
array
Description
A list of tools the model may call. Currently, only functions are supported as a tool.
Name
tool_choice
Type
string / object
Description
Controls which (if any) tool is called by the model.
Name
user
Type
string
Description
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.

Request

POST

/v1/chat/completions

curl https://api.model.box/v1/chat/completions \
  -H "Authorization: Bearer $MODELBOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Response

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-4o-mini-0613",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Hello! How can I assist you today?"
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}