API Reference

The KoboiLLM API is an OpenAI-compatible proxy gateway providing unified access to 100+ LLM models under standard endpoints.

Base URL: https://lite.koboillm.com/v1 (or https://api.koboillm.com/v1)

Authentication: Include your API Key in the request header Authorization: Bearer *** or x-litellm-api-key: ***

---

Chat Completions

Endpoint for model conversations and completions.

POST /v1/chat/completions

Creates a chat completion following the standard OpenAI Chat API specification.

Request Body Parameters:

Parameter	Type	Required	Description
model	string	Yes	Target Model ID (e.g., openai/gpt-4o-mini, anthropic/claude-3-5-sonnet)
messages	array	Yes	Array of message objects
temperature	number	No	Sampling temperature (0.0 to 2.0), default 1.0
max_tokens	integer	No	Maximum token response limit
stream	boolean	No	Enable server-sent event (SSE) streaming
top_p	number	No	Nucleus sampling probability
frequency_penalty	number	No	Frequency penalty (-2.0 to 2.0)
presence_penalty	number	No	Presence penalty (-2.0 to 2.0)
stop	string/array	No	Stop sequences
tools	array	No	Tool and function definitions for tool calling
tool_choice	string/object	No	Controls tool invocation behavior
response_format	object	No	Enforce JSON output (e.g., { "type": "json_object" })

cURL Request Example:

curl -X POST https://lite.koboillm.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer *** \
  -d '{
    "model": "openai/gpt-4o-mini",
    "messages": [
      {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

JSON Response Example:

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "openai/gpt-4o-mini",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Hello! I'm doing well, thank you for asking!"
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 15,
    "total_tokens": 25
  }
}

---

Embeddings

POST /v1/embeddings

Generate text embeddings for semantic search, RAG, and classification.

Request Body Parameters:

Parameter	Type	Required	Description
model	string	Yes	Embedding model ID (e.g., text-embedding-3-small, gemini/gemini-embedding-2)
input	string/array	Yes	Input text string or array of strings to embed

cURL Request Example:

curl -X POST https://lite.koboillm.com/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer *** \
  -d '{
    "model": "text-embedding-3-small",
    "input": "The quick brown fox jumps over the lazy dog"
  }'