API Reference

Prepare in the dashboard

1. Sign in to dashboard.koboillm.com with your email and password, then select your team at the top.
2. Open API Keys → Create API key. Enter a Key name; the key budget is optional. The defaults are No expiry and All Team Models. Select Create and save the full key, which is shown once.
3. Copy an accessible model name from Model List. Choose a model that supports this guide's endpoint; API Quickstart also provides request examples.
4. After running your application, open Logs in the same team, select a time range, and use View details on a request to check its key, tokens, and recorded spend.

OpenAI-compatible base URL: https://api.koboillm.com/v1. Follow the client-specific URL format below. The dashboard address is for your account; applications use the API key, not your account password.

Show the current key creation form

Actual dashboard interface with fictional demonstration data. Click to enlarge.

Model names and provider prices in examples are reference values. Availability, endpoint support, and final recorded costs depend on your key and request.

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

Base URL: https://api.koboillm.com/v1

Authentication: Send Authorization: Bearer sk-xxxxxx with your application API key.

---

Responses

POST /v1/responses

The Chat page supports Chat Completions and Responses. Use API Quickstart for a copyable request, and check that your key can use the selected model.

curl https://api.koboillm.com/v1/responses \
  -H "Authorization: Bearer sk-xxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.6-luna",
    "input": "Reply with one word: ready"
  }'

This endpoint uses input and returns Responses output items; do not read it as choices[0].message.content. Parameters vary by model.

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://api.koboillm.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxx" \
  -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://api.koboillm.com/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxx" \
  -d '{
    "model": "text-embedding-3-small",
    "input": "The quick brown fox jumps over the lazy dog"
  }'