Create Chat Completion

POST /v1/chat/completions

Create Chat Completion

cURL

curl --request POST \
  --url https://api.neosantara.xyz/v1/chat/completions \
  --header 'x-api-key: <api-key>'

200

{
  "id": "<string>",
  "object": "<string>",
  "created": 123,
  "model": "<string>",
  "choices": [
    {
      "index": 123,
      "message": {
        "role": "<string>",
        "content": "<string>",
        "tool_calls": [
          {}
        ]
      },
      "finish_reason": "<string>"
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123
  }
}

Get your free API key

Start with 10,000 Monthly Token Limit on our Free Plan. No credit card required. Your tokens automatically reset on the 1st of each month.

model · string · required

ID of the model to use (e.g., garda-beta-mini, nusantara-base). See /v1/models.

messages · array · required

A list of messages comprising the conversation so far.

Show message properties

role · string · required

The role of the messages author. One of system, user, assistant, or tool.

content · string or array · required

The contents of the message.

name · string

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

tool_call_id · string

Tool call that this message is responding to (required for tool role).

max_tokens · integer

The maximum number of tokens to generate in the chat completion.

temperature · number · default: "1"

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

top_p · number · default: "1"

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass.

stream · boolean · default: "false"

If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events as they become available.

stop · string or array

Up to 4 sequences where the API will stop generating further tokens.

tools · array

A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for.

tool_choice · string or object

Controls which (if any) tool is called by the model. Can be none, auto, required, or a specific tool object.

reasoning · object

Enable reasoning capabilities for supported models (e.g., nusantara-base, garda-beta-mini).

Show properties

effort · string

Controls the reasoning effort. Can be low, medium, or high. (Cannot be used with max_tokens)

max_tokens · integer

The maximum number of tokens to reserve for reasoning. (Cannot be used with effort)

web_search_options · object

Configuration for web search capabilities on supported models.

Show properties

search_depth · string

The depth of the search. Can be basic or advanced.

response_format · object

An object specifying the format that the model must output.

Show properties

type · string

Must be one of text, json_object, or json_schema.

user · string

A unique identifier representing your end-user, which can help Neosantara AI to monitor and detect abuse.

Returns

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 chat completion was created.

model · string

The model used for the chat completion.

choices · array

A list of chat completion choices.

Show choices properties

index · integer

The index of the choice in the list of choices.

message · object

A chat completion message generated by the model.

Show properties

role · string

The role of the author of this message.

content · string

The contents of the message.

tool_calls · array

The tool calls generated by the model, such as function calls.

finish_reason · string

The reason the model stopped generating tokens. This will be stop if the model hit a natural stop point or a provided stop sequence, length if the maximum number of tokens specified in the request was reached, tool_calls if the model called a tool, or content_filter if content was omitted due to a flag from our content filters.

usage · object

Usage statistics for the completion request.

Show usage properties

prompt_tokens · integer

Number of tokens in the prompt.

completion_tokens · integer

Number of tokens in the generated completion.

total_tokens · integer

Total number of tokens used in the request (prompt + completion).

Return Examples

Response 200

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "nusantara-base",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello there, how may I assist you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}