Chat Completions

curl --request POST \
  --url https://openp.ai/v1/chat/completions

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://openp.ai/v1/chat/completions",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://openp.ai/v1/chat/completions"

	req, _ := http.NewRequest("POST", url, nil)

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://openp.ai/v1/chat/completions")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)

response = http.request(request)
puts response.read_body

POST

chat

completions

Chat Completions

curl --request POST \
  --url https://openp.ai/v1/chat/completions

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://openp.ai/v1/chat/completions",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://openp.ai/v1/chat/completions"

	req, _ := http.NewRequest("POST", url, nil)

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://openp.ai/v1/chat/completions")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)

response = http.request(request)
puts response.read_body

Create a model response based on the conversation context (the messages array). Every model with chat capability (OpenAI / Claude / Gemini / DeepSeek / Qwen, etc.) can be called through this endpoint.

Request

Authentication

Authorization: Bearer sk-XXXXXXXXXXXXXXXX

Main parameters

Field	Type	Required	Description
`model`	string	✅	Model ID, e.g. `gpt-5.5`
`messages`	array	✅	Conversation history, each item `{ role, content }`
`temperature`	number		0-2, default 1. Lower is more deterministic
`top_p`	number		0-1, nucleus sampling; use this or temperature, not both
`n`	integer		How many candidates to generate (default 1)
`stream`	boolean		true enables SSE streaming
`stream_options`	object		`{ include_usage: true }` appends usage at the end of the stream
`max_tokens`	integer		Maximum output tokens (legacy field, replaced by `max_completion_tokens` for some models)
`max_completion_tokens`	integer		New field, for o3 / GPT-5
`stop`	string \| array		Stop sequences
`presence_penalty`	number		-2 to 2
`frequency_penalty`	number		-2 to 2
`logit_bias`	map		Token bias
`seed`	integer		Reproducibility seed
`response_format`	object		`{ type: "json_object" }` or a JSON Schema
`tools`	array		List of function-calling tools
`tool_choice`	string \| object		`auto` / `required` / `{ type:"function", function:{name:"..."}}`
`parallel_tool_calls`	boolean		Whether to allow parallel tool calls
`reasoning_effort`	string		Reasoning effort for o3 / GPT-5: `low` / `medium` / `high`
`modalities`	array		Multimodal output, e.g. `["text","audio"]`
`audio`	object		Audio output options
`user`	string		End-user identifier (for auditing)

messages structure

[
  {"role": "system",    "content": "You are a helpful assistant"},
  {"role": "user",      "content": "Tell a joke"},
  {"role": "assistant", "content": "Why do programmers like the dark? Because there are no bugs."},
  {"role": "user",      "content": [
    {"type": "text", "text": "Describe this image"},
    {"type": "image_url", "image_url": {"url": "https://..."}}
  ]}
]

Supported roles: system / user / assistant / tool (function return).

Response

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "created": 1715750400,
  "model": "gpt-5.5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "answer content..."
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 27,
    "completion_tokens": 19,
    "total_tokens": 46,
    "prompt_tokens_details": { "cached_tokens": 0 },
    "completion_tokens_details": { "reasoning_tokens": 0 }
  },
  "system_fingerprint": "fp_..."
}

finish_reason possible values: stop / length / tool_calls / content_filter.

Streaming response

With stream: true, the server pushes chunks in SSE format:

data: {"id":"chatcmpl-...","object":"chat.completion.chunk","choices":[{"delta":{"content":"He"},"index":0}]}

data: {"id":"chatcmpl-...","choices":[{"delta":{"content":"llo"},"index":0}]}

data: {"id":"chatcmpl-...","choices":[{"delta":{},"index":0,"finish_reason":"stop"}]}

data: [DONE]

With stream_options.include_usage: true, an extra chunk with usage is sent at the end:

data: {"id":"chatcmpl-...","choices":[],"usage":{"prompt_tokens":...,"completion_tokens":...}}

Function calling

{
  "model": "gpt-5.5",
  "messages": [{"role": "user", "content": "Weather in Shanghai"}],
  "tools": [{
    "type": "function",
    "function": {
      "name": "get_weather",
      "description": "Get weather",
      "parameters": {
        "type": "object",
        "properties": {"city": {"type": "string"}},
        "required": ["city"]
      }
    }
  }]
}

In the response:

{
  "choices": [{
    "message": {
      "role": "assistant",
      "content": null,
      "tool_calls": [{
        "id": "call_abc",
        "type": "function",
        "function": {"name": "get_weather", "arguments": "{\"city\":\"Shanghai\"}"}
      }]
    },
    "finish_reason": "tool_calls"
  }]
}

After executing the tool, append the result to messages:

{"role": "tool", "tool_call_id": "call_abc", "content": "Shanghai is 26°C and clear today"}

Call chat completions again to let the model continue answering based on the tool result.

Reasoning models

For the o3 / GPT-5 series, use reasoning_effort:

{
  "model": "o3-mini-high",
  "messages": [{"role": "user", "content": "Prove that √2 is irrational"}],
  "reasoning_effort": "high",
  "max_completion_tokens": 4096
}

You can also use a suffixed model ID (o3-mini-low / -medium / -high) for the equivalent effect.

Errors

See Error codes for common errors.

Overview

OpenAI-compatible

Claude Messages

Google Gemini

Rerank

Video & image generation

Account

Chat Completions

Request

Authentication

Main parameters

messages structure

Response

Streaming response

Function calling

Reasoning models

Errors

​Request

​Authentication

​Main parameters

​messages structure

​Response

​Streaming response

​Function calling

​Reasoning models

​Errors

Request

Authentication

Main parameters

messages structure

Response

Streaming response

Function calling

Reasoning models

Errors