Chat Completions

Chat completions is the most commonly used interface and is fully compatible with the OpenAI protocol.

POST https://api.4allapi.com/v1/chat/completions

Request Parameters

Parameter	Type	Required	Description
`model`	string	Yes	Model name, see Model Overview
`messages`	array	Yes	Array of conversation messages; each item includes `role` and `content`
`stream`	boolean	No	Whether to return streamed output, see Streaming Output
`temperature`	number	No	Sampling temperature 0–2; higher values produce more diverse output
`top_p`	number	No	Nucleus sampling threshold; adjust it as an alternative to temperature
`max_tokens`	number	No	Maximum number of tokens in the reply
`stop`	string/array	No	Stop words
`presence_penalty`	number	No	Topic novelty penalty -2–2
`frequency_penalty`	number	No	Repetition penalty -2–2
`tools`	array	No	Tool/function call definitions (supported models)
`response_format`	object	No	For example `{"type":"json_object"}` forces JSON output

The role in messages supports system / user / assistant / tool. content can be a string, or a multimodal array (text + image, see Vision Understanding).

Request Example

curl https://api.4allapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AIPROXY_KEY" \
  -d '{
    "model": "fable-5",
    "messages": [
      {"role": "system", "content": "You are a rigorous technical assistant"},
      {"role": "user", "content": "Explain what an API gateway is in one sentence"}
    ],
    "temperature": 0.7,
    "max_tokens": 512
  }'

Response Structure

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1750000000,
  "model": "fable-5",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "The API gateway is..." },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 32,
    "completion_tokens": 41,
    "total_tokens": 73
  }
}

The usage field is the basis for billing; see Billing and Credits.