Chat Completions

Creates a model response for the given chat conversation.

POST /v1/chat/completions

Chat Completion

cURL

curl --request POST \
  --url https://www.anyfast.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "claude-sonnet-5",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "max_tokens": 2,
  "temperature": 1,
  "top_p": 0.5,
  "frequency_penalty": 0,
  "presence_penalty": 0,
  "stream": false,
  "stop": "<string>",
  "n": 1,
  "response_format": {},
  "tools": [
    {}
  ],
  "tool_choice": "<string>",
  "user": "<string>"
}
'

import requests

url = "https://www.anyfast.ai/v1/chat/completions"

payload = {
    "model": "claude-sonnet-5",
    "messages": [
        {
            "role": "user",
            "content": "Hello!"
        }
    ],
    "max_tokens": 2,
    "temperature": 1,
    "top_p": 0.5,
    "frequency_penalty": 0,
    "presence_penalty": 0,
    "stream": False,
    "stop": "<string>",
    "n": 1,
    "response_format": {},
    "tools": [{}],
    "tool_choice": "<string>",
    "user": "<string>"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'claude-sonnet-5',
    messages: [{role: 'user', content: 'Hello!'}],
    max_tokens: 2,
    temperature: 1,
    top_p: 0.5,
    frequency_penalty: 0,
    presence_penalty: 0,
    stream: false,
    stop: '<string>',
    n: 1,
    response_format: {},
    tools: [{}],
    tool_choice: '<string>',
    user: '<string>'
  })
};

fetch('https://www.anyfast.ai/v1/chat/completions', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://www.anyfast.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",
  CURLOPT_POSTFIELDS => json_encode([
    'model' => 'claude-sonnet-5',
    'messages' => [
        [
                'role' => 'user',
                'content' => 'Hello!'
        ]
    ],
    'max_tokens' => 2,
    'temperature' => 1,
    'top_p' => 0.5,
    'frequency_penalty' => 0,
    'presence_penalty' => 0,
    'stream' => false,
    'stop' => '<string>',
    'n' => 1,
    'response_format' => [
        
    ],
    'tools' => [
        [
                
        ]
    ],
    'tool_choice' => '<string>',
    'user' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

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

curl_close($curl);

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

package main

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

func main() {

	url := "https://www.anyfast.ai/v1/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"claude-sonnet-5\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Hello!\"\n    }\n  ],\n  \"max_tokens\": 2,\n  \"temperature\": 1,\n  \"top_p\": 0.5,\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"stream\": false,\n  \"stop\": \"<string>\",\n  \"n\": 1,\n  \"response_format\": {},\n  \"tools\": [\n    {}\n  ],\n  \"tool_choice\": \"<string>\",\n  \"user\": \"<string>\"\n}")

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

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://www.anyfast.ai/v1/chat/completions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"claude-sonnet-5\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Hello!\"\n    }\n  ],\n  \"max_tokens\": 2,\n  \"temperature\": 1,\n  \"top_p\": 0.5,\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"stream\": false,\n  \"stop\": \"<string>\",\n  \"n\": 1,\n  \"response_format\": {},\n  \"tools\": [\n    {}\n  ],\n  \"tool_choice\": \"<string>\",\n  \"user\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

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

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"claude-sonnet-5\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Hello!\"\n    }\n  ],\n  \"max_tokens\": 2,\n  \"temperature\": 1,\n  \"top_p\": 0.5,\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"stream\": false,\n  \"stop\": \"<string>\",\n  \"n\": 1,\n  \"response_format\": {},\n  \"tools\": [\n    {}\n  ],\n  \"tool_choice\": \"<string>\",\n  \"user\": \"<string>\"\n}"

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

200

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 123,
  "model": "claude-sonnet-5",
  "choices": [
    {
      "index": 123,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      }
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>"
  }
}

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

model · enum<string> · required

Model ID to use for completion.

Available options: claude-sonnet-5, claude-sonnet-4-6, claude-sonnet-4-5-20250929, claude-sonnet-4-20250514, claude-opus-4-6, claude-opus-4-5-20251101, claude-opus-4-1-20250805, claude-opus-4-20250514, claude-haiku-4-5-20251001, claude-3-7-sonnet-20250219, claude-3-5-sonnet-20241022, gpt-5-4, gpt-5.4-mini, gpt-5-3-codex, gpt-5-2, gpt-5-2-chat, gpt-5-2-chat-latest, gpt-5-2-codex, gpt-5-1, gpt-5-1-chat, gpt-5-1-chat-latest, gpt-5-1-codex-mini, gpt-5, gpt-5-chat-latest, gpt-5-pro, gpt-5-codex, gpt-5-codex-high, gpt-5-codex-low, gpt-5-mini, gpt-5-nano, gpt-4o, gpt-4o-mini, gpt-4-1, gpt-4, deepseek-v3-2-speciale, deepseek-v3-2, deepseek-v3-2-exp, deepseek-v3-2-251201, deepseek-v3-1-terminus, deepseek-v3-1, deepseek-v3, qwen3.5-397b-a17b, qwen3-coder-next, qwen3-coder, qwen3-235b-a22b, qwen3-32b, qwen3-14b, qwen2.5-72b-instruct, doubao-seed-2.0-pro, doubao-seed-2.0-code, doubao-seed-2.0-lite, doubao-seed-2.0-mini, doubao-seed-1-8-251228, doubao-seed-1-6-flash-250828, doubao-seed-1-6-251015, doubao-seed-1-6-lite-251015, doubao-seed-1-6-vision-250815, minimax-m2.5, minimax-m2.1, kimi-k2.5, grok-3, grok-3-mini, grok-4-fast-reasoning, grok-4-fast-non-reasoning, grok-4-1-fast-reasoning, grok-4-1-fast-non-reasoning, gemini-3.1-pro-preview, gemini-3.1-flash-image, gemini-3-pro-preview, gemini-3-flash-preview, gemini-2.5-pro, gemini-2.5-flash, gemini-2.0-flash, glm-4.7

Example:

"claude-sonnet-5"

messages · object[] · required

A list of messages comprising the conversation so far.

Minimum array length: 1

Show child attributes

Example:

[{ "role": "user", "content": "Hello!" }]

max_tokens · integer

The maximum number of tokens to generate in the chat completion.

Required range: x >= 1

temperature · number · default: 1

Sampling temperature between 0 and 2. Higher values make output more random, lower values more deterministic.

Required range: 0 <= x <= 2

Example:

1

top_p · number

Nucleus sampling threshold. An alternative to temperature.

Required range: 0 <= x <= 1

frequency_penalty · number · default: 0

Penalizes new tokens based on their existing frequency in the text so far.

Required range: -2 <= x <= 2

presence_penalty · number · default: 0

Penalizes new tokens based on whether they appear in the text so far.

Required range: -2 <= x <= 2

stream · boolean · default: false

If true, partial message deltas will be sent as server-sent events.

stop · string string[]

Up to 4 sequences where the API will stop generating further tokens.

n · integer · default: 1

How many chat completion choices to generate for each input message.

Required range: x >= 1

response_format · object

An object specifying the format that the model must output. Setting to {"type": "json_object"} enables JSON mode.

Show child attributes

tools · object[]

A list of tools the model may call. Currently, only functions are supported as a tool.

tool_choice · string object

Controls which (if any) tool is called by the model.

user · string

A unique identifier representing your end-user.

Response

200

application/json

Completion generated successfully

id · string · required

Example:

"chatcmpl-abc123"

object · string · required

Example:

"chat.completion"

created · integer · required

Unix timestamp of when the completion was created.

model · string · required

Example:

"claude-sonnet-5"

choices · object[] · required

Show child attributes

usage · object

Show child attributes