​
Completions API

The completions endpoint allows you to generate text completions using KrosAI’s language models. This is ideal for tasks like content generation, translation, and text transformation.

​
Create Completion

​
Request Body

​
prompt
string
required

The prompt to generate completions for

​
model
string
required

The ID of the model to use. Currently supported: KrosMLingual1.0.1

​
max_tokens
integer
default:"100"

The maximum number of tokens to generate

​
temperature
number
default:"0.7"

Controls randomness in the output. Values between 0 and 1. Higher values mean more random completions.

​
top_p
number
default:"1"

Controls diversity via nucleus sampling. Values between 0 and 1.

​
Example Request

{
  "prompt": "Translate to Yoruba: Hello, how are you?",
  "model": "KrosMLingual1.0.1",
  "max_tokens": 50,
  "temperature": 0.7
}

​
Example Response

{
  "id": "cmpl-123abc",
  "object": "text_completion",
  "created": 1677649420,
  "model": "KrosMLingual1.0.1",
  "choices": [{
    "text": "Bawo ni, se daadaa ni?",
    "index": 0,
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 8,
    "completion_tokens": 6,
    "total_tokens": 14
  }
}

All requests must include an API key in the Authorization header.

​
Error Responses

​
400: Bad Request
object

Invalid request parameters

​
401: Unauthorized
object

Invalid or missing API key

​
429: Too Many Requests
object

Rate limit exceeded

​
Best Practices

  1. System Messages: Use system messages to set the behavior and context for your assistant.
  2. Message History: Keep message history concise to stay within token limits.
  3. Temperature: Use lower temperature (0.2-0.4) for more focused, deterministic responses.
  4. Rate Limits: Implement proper error handling for rate limits.