Chat Completions API Reference

The Chat Completions API is the core of our text generation service. Given a series of messages, the model will return a predicted response. This is ideal for building chatbots and other conversational AI applications. Our API is compliant with OpenAI's Chat Completions API, making it easy to integrate with existing applications. To read more about the OpenAI Chat Completions API, visit the OpenAI Chat Completions API documentation.

Request Body

The request body must be a JSON object with the following parameters:

Parameter	Type	Required	Description
`model`	string	Yes	The ID of the model to use.
`messages`	array	Yes	A list of message objects that form the conversation history. See the structure below.
`temperature`	number	No	Controls randomness. A value between 0 and 2. Higher values like 0.8 make the output more random, while lower values like 0.2 make it more focused and deterministic. Defaults to `1`.
`max_tokens`	integer	No	The maximum number of tokens to generate in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length.
`stream`	boolean	No	If `true`, the API will send back partial message deltas as they are generated, like in ChatGPT. This is useful for creating a real-time, responsive user experience. Defaults to `false`.
`top_p`	number	No	An alternative to temperature sampling, called nucleus sampling. The model considers only the tokens with a cumulative probability of `top_p`. For example, `0.1` means only the top 10% of tokens are considered. Defaults to `1`.
`n`	integer	No	How many chat completion choices to generate for each input message. Note that this will multiply the number of API calls you make. Defaults to `1`.
`stop`	string or array	No	Up to 4 sequences where the API will stop generating further tokens.
`tools`	array	No	A list of tools the model may call. Each tool is typically a function definition with a name, description, and JSON Schema parameters object.
`tool_choice`	string or object	No	Controls how the model uses tools. Supported values are `"auto"`, `"required"`, `"none"`, or an object that forces a specific function call.

The `messages` Object

The messages array is the heart of the request, providing the conversation history that the model will use to generate a response. Each message object in the array has a role and content.

Role	Description
`system`	The system message helps set the behavior of the assistant. It can be used to provide high-level instructions for the conversation, like "You are a helpful assistant that translates English to French."
`user`	A message from the user. This is where you provide the prompts and questions for the assistant.
`assistant`	A message from the assistant. This can be used to provide examples of desired behavior (few-shot prompting), continue a conversation, or return `tool_calls` when the model decides to call a function.
`tool`	A message containing the result of a previously executed tool call. Send this after your application runs the requested tool and before asking the model for a final answer.

A typical conversation starts with a system message, followed by an alternating series of user and assistant messages.

The `tools` Object

Each item in the tools array defines a callable tool for the model. For function calling, use the following shape:

Field	Type	Description
`type`	string	The tool type. Use `"function"`.
`function.name`	string	The function name the model should call.
`function.description`	string	A short description of what the function does.
`function.parameters`	object	A JSON Schema object describing the function arguments.

The `tool_choice` Object

Use tool_choice to control whether the model can call tools:

Value	Description
`"auto"`	The model decides whether to answer normally or call a tool.
`"required"`	The model must call a tool.
`"none"`	Tool calling is disabled for that request.
`{"type": "function", "function": {"name": "get_mission_status"}}`	Force a specific function call.

Response Body

The API returns a JSON object containing the completion choices.

Parameter	Type	Description
`id`	string	A unique identifier for the chat completion.
`object`	string	The object type, which is always `chat.completion`.
`created`	integer	The Unix timestamp (in seconds) of when the completion was created.
`model`	string	The model used for the completion.
`choices`	array	A list of chat completion choices.
`usage`	object	An object containing token usage statistics for the completion.

The `choices` object

Parameter	Type	Description
`index`	integer	The index of the choice in the list of choices.
`message`	object	The message object generated by the model, containing `role` and `content`.
`finish_reason`	string	The reason the model stopped generating tokens. Can be `stop`, `length`, `content_filter`, or `tool_calls` when the model wants your application to execute a tool.

The `message` object

Parameter	Type	Description
`role`	string	The role of the generated message, usually `assistant`.
`content`	string or null	The assistant text content. This may be `null` when the model returns only tool calls.
`tool_calls`	array	Present when the assistant requests one or more tool calls. Each tool call includes an `id`, `type`, and function payload with `name` and JSON string `arguments`.

The `usage` object

Parameter	Type	Description
`prompt_tokens`	integer	The number of tokens in the prompt.
`completion_tokens`	integer	The number of tokens in the generated completion.
`total_tokens`	integer	The total number of tokens used in the request (prompt + completion).

Example Response

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "MiniMaxAI/MiniMax-M2.5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "\n\nHello there, how may I assist you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}

Example Tool Calling Response

{
  "id": "chatcmpl-456",
  "object": "chat.completion",
  "created": 1677652299,
  "model": "moonshotai/Kimi-K2.6",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": null,
        "tool_calls": [
          {
            "id": "call_abc123",
            "type": "function",
            "function": {
              "name": "get_mission_status",
              "arguments": "{\"mission_name\":\"Artemis II\",\"detail_level\":\"summary\"}"
            }
          }
        ]
      },
      "finish_reason": "tool_calls"
    }
  ],
  "usage": {
    "prompt_tokens": 42,
    "completion_tokens": 18,
    "total_tokens": 60
  }
}

Example Request

Here is an example of a request to the Chat Completions API using different programming languages.

Stream

Python
JavaScript
cURL

import os
from openai import OpenAI

client = OpenAI(
  base_url="https://api.inceptron.io/v1",
  api_key=os.environ["INCEPTRON_API_KEY"],
)

completion = client.chat.completions.create(
  model="MiniMaxAI/MiniMax-M2.5",
  messages=[
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is the capital of France?"}
  ],
)

print(completion.choices[0].message.content)

import { OpenAI } from "openai";

const client = new OpenAI({
baseURL: "https://api.inceptron.io/v1",
apiKey: process.env.INCEPTRON_API_KEY,
});

const chatCompletion = await client.chat.completions.create({
model: "MiniMaxAI/MiniMax-M2.5",
  messages: [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is the capital of France?"},
  ],
});

console.log(chatCompletion.choices[0].message.content);

curl https://api.inceptron.io/v1/chat/completions \
        -H "Content-Type: application/json" \
        -H "Authorization: Bearer $INCEPTRON_API_KEY" \
        -d '{
              "model": "MiniMaxAI/MiniMax-M2.5",
              "messages": [
                {"role": "system", "content": "You are a helpful assistant."},
                {"role": "user", "content": "What is the capital of France?"}
              ]
          }'

Tool Calling Example

The Chat Completions API also supports OpenAI-compatible tool calling. For a complete walkthrough, see the Tool Calling guide.

Stream

Python
JavaScript
cURL

import os
from openai import OpenAI

client = OpenAI(
  base_url="https://api.inceptron.io/v1",
  api_key=os.environ["INCEPTRON_API_KEY"],
)

tools = [
  {
      "type": "function",
      "function": {
          "name": "get_mission_status",
          "description": "Get the latest status for a space mission",
          "parameters": {
              "type": "object",
              "properties": {
                  "mission_name": {"type": "string"},
                  "detail_level": {
                      "type": "string",
                      "enum": ["summary", "full"],
                  },
              },
              "required": ["mission_name", "detail_level"],
          },
      },
  },
]

completion = client.chat.completions.create(
  model="moonshotai/Kimi-K2.6",
  messages=[
      {"role": "user", "content": "Give me the latest status for Artemis II."}
  ],
  tools=tools,
  tool_choice="auto",
)

print(completion.choices[0].message.tool_calls)

import { OpenAI } from "openai";

const client = new OpenAI({
baseURL: "https://api.inceptron.io/v1",
apiKey: process.env.INCEPTRON_API_KEY,
});

const tools = [
{
	type: "function",
	function: {
		name: "get_mission_status",
		description: "Get the latest status for a space mission",
		parameters: {
			type: "object",
			properties: {
				mission_name: { type: "string" },
				detail_level: {
					type: "string",
					enum: ["summary", "full"],
				},
			},
			required: ["mission_name", "detail_level"],
		},
	},
},
];

const completion = await client.chat.completions.create({
model: "moonshotai/Kimi-K2.6",
messages: [
	{ role: "user", content: "Give me the latest status for Artemis II." },
],
tools,
tool_choice: "auto",
});

console.log(completion.choices[0].message.tool_calls);

curl https://api.inceptron.io/v1/chat/completions \
        -H "Content-Type: application/json" \
        -H "Authorization: Bearer $INCEPTRON_API_KEY" \
        -d '{
              "model": "moonshotai/Kimi-K2.6",
              "messages": [
                {"role": "user", "content": "Give me the latest status for Artemis II."}
              ],
              "tools": [
                {
                  "type": "function",
                  "function": {
                    "name": "get_mission_status",
                    "description": "Get the latest status for a space mission",
                    "parameters": {
                      "type": "object",
                      "properties": {
                        "mission_name": {"type": "string"},
                        "detail_level": {
                          "type": "string",
                          "enum": ["summary", "full"]
                        }
                      },
                      "required": ["mission_name", "detail_level"]
                    }
                  }
                }
              ],
              "tool_choice": "auto"
          }'

Response Body

The response body is a JSON object that contains the result of the chat completion.

Standard Response

{
"id": "chatcmpl-123",
"object": "chat.completion",
"created": 1677652288,
"model": "MiniMaxAI/MiniMax-M2.5",
"choices": [{
  "index": 0,
  "message": {
    "role": "assistant",
    "content": "

Paris is the capital of France."
  },
  "finish_reason": "stop"
}],
"usage": {
  "prompt_tokens": 9,
  "completion_tokens": 12,
  "total_tokens": 21
}
}

Streaming Response

When stream is set to true, the API will return a stream of data:-prefixed JSON objects. The final object will be [DONE].

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"MiniMaxAI/MiniMax-M2.5","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"MiniMaxAI/MiniMax-M2.5","choices":[{"index":0,"delta":{"content":"
"},"finish_reason":null}]}

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"MiniMaxAI/MiniMax-M2.5","choices":[{"index":0,"delta":{"content":"Paris"},"finish_reason":null}]}

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"MiniMaxAI/MiniMax-M2.5","choices":[{"index":0,"delta":{"content":" is"},"finish_reason":null}]}

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"MiniMaxAI/MiniMax-M2.5","choices":[{"index":0,"delta":{"content":" the"},"finish_reason":null}]}

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"MiniMaxAI/MiniMax-M2.5","choices":[{"index":0,"delta":{"content":" capital"},"finish_reason":null}]}

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"MiniMaxAI/MiniMax-M2.5","choices":[{"index":0,"delta":{"content":" of"},"finish_reason":null}]}

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"MiniMaxAI/MiniMax-M2.5","choices":[{"index":0,"delta":{"content":" France"},"finish_reason":null}]}

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"MiniMaxAI/MiniMax-M2.5","choices":[{"index":0,"delta":{"content":"."},"finish_reason":null}]}

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"MiniMaxAI/MiniMax-M2.5","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]

Streaming Tool Call Response

When streaming a tool call, the function name and arguments may arrive across multiple chunks. Your application should accumulate the partial tool_calls payload before parsing the final arguments JSON.

data: {"id":"chatcmpl-456","object":"chat.completion.chunk","created":1677652299,"model":"moonshotai/Kimi-K2.6","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}

data: {"id":"chatcmpl-456","object":"chat.completion.chunk","created":1677652299,"model":"moonshotai/Kimi-K2.6","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"id":"call_abc123","type":"function","function":{"name":"get_mission_status","arguments":""}}]},"finish_reason":null}]}

data: {"id":"chatcmpl-456","object":"chat.completion.chunk","created":1677652299,"model":"moonshotai/Kimi-K2.6","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\"mission_name\":\"Artemis II\""}}]},"finish_reason":null}]}

data: {"id":"chatcmpl-456","object":"chat.completion.chunk","created":1677652299,"model":"moonshotai/Kimi-K2.6","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":",\"detail_level\":\"summary\"}"}}]},"finish_reason":null}]}

data: {"id":"chatcmpl-456","object":"chat.completion.chunk","created":1677652299,"model":"moonshotai/Kimi-K2.6","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}

data: [DONE]

Request Body​

The messages Object​

The tools Object​

The tool_choice Object​

Response Body​

The choices object​

The message object​

The usage object​

Example Response​

Example Tool Calling Response​

Example Request​

Tool Calling Example​

Response Body​

Standard Response​

Streaming Response​

Streaming Tool Call Response​

Request Body

The `messages` Object

The `tools` Object

The `tool_choice` Object

Response Body

The `choices` object

The `message` object

The `usage` object

Example Response

Example Tool Calling Response

Example Request

Tool Calling Example

Response Body

Standard Response

Streaming Response

Streaming Tool Call Response