glm-5.2

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": "glm-5.2",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "thinking": {
    "type": "enabled"
  },
  "reasoning_effort": "max",
  "max_tokens": 65536,
  "temperature": 1,
  "top_p": 0.95,
  "stream": false,
  "tools": [
    {}
  ],
  "response_format": {
    "type": "text"
  },
  "stop": "<string>"
}
'

import requests

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

payload = {
    "model": "glm-5.2",
    "messages": [
        {
            "role": "user",
            "content": "Hello!"
        }
    ],
    "thinking": { "type": "enabled" },
    "reasoning_effort": "max",
    "max_tokens": 65536,
    "temperature": 1,
    "top_p": 0.95,
    "stream": False,
    "tools": [{}],
    "response_format": { "type": "text" },
    "stop": "<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: 'glm-5.2',
    messages: [{role: 'user', content: 'Hello!'}],
    thinking: {type: 'enabled'},
    reasoning_effort: 'max',
    max_tokens: 65536,
    temperature: 1,
    top_p: 0.95,
    stream: false,
    tools: [{}],
    response_format: {type: 'text'},
    stop: '<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' => 'glm-5.2',
    'messages' => [
        [
                'role' => 'user',
                'content' => 'Hello!'
        ]
    ],
    'thinking' => [
        'type' => 'enabled'
    ],
    'reasoning_effort' => 'max',
    'max_tokens' => 65536,
    'temperature' => 1,
    'top_p' => 0.95,
    'stream' => false,
    'tools' => [
        [
                
        ]
    ],
    'response_format' => [
        'type' => 'text'
    ],
    'stop' => '<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\": \"glm-5.2\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Hello!\"\n    }\n  ],\n  \"thinking\": {\n    \"type\": \"enabled\"\n  },\n  \"reasoning_effort\": \"max\",\n  \"max_tokens\": 65536,\n  \"temperature\": 1,\n  \"top_p\": 0.95,\n  \"stream\": false,\n  \"tools\": [\n    {}\n  ],\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"stop\": \"<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\": \"glm-5.2\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Hello!\"\n    }\n  ],\n  \"thinking\": {\n    \"type\": \"enabled\"\n  },\n  \"reasoning_effort\": \"max\",\n  \"max_tokens\": 65536,\n  \"temperature\": 1,\n  \"top_p\": 0.95,\n  \"stream\": false,\n  \"tools\": [\n    {}\n  ],\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"stop\": \"<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\": \"glm-5.2\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Hello!\"\n    }\n  ],\n  \"thinking\": {\n    \"type\": \"enabled\"\n  },\n  \"reasoning_effort\": \"max\",\n  \"max_tokens\": 65536,\n  \"temperature\": 1,\n  \"top_p\": 0.95,\n  \"stream\": false,\n  \"tools\": [\n    {}\n  ],\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"stop\": \"<string>\"\n}"

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

200

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 123,
  "model": "glm-5.2",
  "choices": [
    {
      "index": 123,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?",
        "reasoning_content": "<string>"
      }
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "prompt_tokens_details": {
      "cached_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

Available options: glm-5.2

Example:

"glm-5.2"

messages · object[] · required

A list of messages comprising the conversation so far.

Minimum array length: 1

Show child attributes

Example:

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

thinking · object

Controls chain-of-thought. GLM-5.2 performs forced thinking when enabled.

Show child attributes

reasoning_effort · enum<string> · default: max

Controls how hard the model reasons; effective only when thinking is enabled. none/minimal skip thinking, low/medium map to high, xhigh maps to max.

Available options: max, xhigh, high, medium, low, minimal, none

max_tokens · integer · default: 65536

The maximum number of tokens to generate (up to 128K). Recommended >= 1024.

Required range: 1 <= x <= 131072

temperature · number · default: 1

Sampling temperature. Higher values make output more random.

Required range: 0 <= x <= 1

Example:

1

top_p · number · default: 0.95

Nucleus sampling threshold.

Required range: 0.01 <= x <= 1

stream · boolean · default: false

If true, stream partial message deltas using SSE.

tools · object[]

A list of tools (functions or MCP) the model may call.

response_format · object

Output format. Use { "type": "json_object" } for structured JSON output.

Show child attributes

stop · string string[]

Sequences where the model will stop generating further tokens.

Response

200

application/json

Completion generated successfully

id · string · required

Example:

"chatcmpl-abc123"

object · string · required

Example:

"chat.completion"

created · integer · required

Unix timestamp

model · string · required

Example:

"glm-5.2"

choices · object[] · required

Show child attributes

usage · object

Show child attributes