glm-5.3

Create a GLM-5.3 chat completion

curl --request POST \
  --url https://www.anyfast.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "glm-5.3",
  "messages": [
    {
      "role": "user",
      "content": "Reply with exactly OK."
    }
  ],
  "max_tokens": 128
}
'

import requests

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

payload = {
    "model": "glm-5.3",
    "messages": [
        {
            "role": "user",
            "content": "Reply with exactly OK."
        }
    ],
    "max_tokens": 128
}
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-5.3',
    messages: [{role: 'user', content: 'Reply with exactly OK.'}],
    max_tokens: 128
  })
};

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-5.3',
    'messages' => [
        [
                'role' => 'user',
                'content' => 'Reply with exactly OK.'
        ]
    ],
    'max_tokens' => 128
  ]),
  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-5.3\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Reply with exactly OK.\"\n    }\n  ],\n  \"max_tokens\": 128\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-5.3\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Reply with exactly OK.\"\n    }\n  ],\n  \"max_tokens\": 128\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-5.3\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Reply with exactly OK.\"\n    }\n  ],\n  \"max_tokens\": 128\n}"

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

{
  "id": "20260819113252725deddc07234b73",
  "object": "chat.completion",
  "created": 1787110376,
  "model": "glm-5.3",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "reasoning_content": "The user requested an exact short response, so the final answer should be OK.",
        "content": "OK"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 17,
    "completion_tokens": 91,
    "completion_tokens_details": {
      "reasoning_tokens": 88
    },
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "total_tokens": 108
  }
}

{
  "error": {
    "message": "该模型始终思考，不支持关闭思考；请使用 low、high 或 max。",
    "type": "upstream_error",
    "param": "",
    "code": "1210"
  }
}

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

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

POST

chat

completions

Create a GLM-5.3 chat completion

curl --request POST \
  --url https://www.anyfast.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "glm-5.3",
  "messages": [
    {
      "role": "user",
      "content": "Reply with exactly OK."
    }
  ],
  "max_tokens": 128
}
'

import requests

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

payload = {
    "model": "glm-5.3",
    "messages": [
        {
            "role": "user",
            "content": "Reply with exactly OK."
        }
    ],
    "max_tokens": 128
}
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-5.3',
    messages: [{role: 'user', content: 'Reply with exactly OK.'}],
    max_tokens: 128
  })
};

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-5.3',
    'messages' => [
        [
                'role' => 'user',
                'content' => 'Reply with exactly OK.'
        ]
    ],
    'max_tokens' => 128
  ]),
  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-5.3\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Reply with exactly OK.\"\n    }\n  ],\n  \"max_tokens\": 128\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-5.3\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Reply with exactly OK.\"\n    }\n  ],\n  \"max_tokens\": 128\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-5.3\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Reply with exactly OK.\"\n    }\n  ],\n  \"max_tokens\": 128\n}"

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

{
  "id": "20260819113252725deddc07234b73",
  "object": "chat.completion",
  "created": 1787110376,
  "model": "glm-5.3",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "reasoning_content": "The user requested an exact short response, so the final answer should be OK.",
        "content": "OK"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 17,
    "completion_tokens": 91,
    "completion_tokens_details": {
      "reasoning_tokens": 88
    },
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "total_tokens": 108
  }
}

{
  "error": {
    "message": "该模型始终思考，不支持关闭思考；请使用 low、high 或 max。",
    "type": "upstream_error",
    "param": "",
    "code": "1210"
  }
}

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

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "type": "<string>",
    "param": "<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. Must be glm-5.3.

Available options:

glm-5.3

Example:

"glm-5.3"

messages

object[]

required

The complete conversation in chronological order.

Minimum array length: 1

Show child attributes

Example:

[
  {
    "role": "system",
    "content": "You are a senior software engineer."
  },
  {
    "role": "user",
    "content": "Design a reliable distributed job queue."
  }
]

thinking

object

Thinking configuration. Thinking remains enabled when this field is omitted. GLM-5.3 does not accept disabled.

Show child attributes

reasoning_effort

enum<string>

default:max

Thinking intensity. Use low for lightweight reasoning, high for enhanced reasoning, or max for deep reasoning.

Available options:

low,

high,

max

stream

boolean

default:false

Streams partial response deltas over SSE when true.

do_sample

boolean

default:true

Enables sampling. When false, temperature and top_p are ignored.

temperature

number<float>

default:1

Sampling temperature. Adjust either temperature or top_p, not both.

Required range: 0 <= x <= 1

Example:

1

top_p

number<float>

default:0.95

Nucleus sampling threshold. AnyFast accepts values from 0 to 1.

Required range: 0 <= x <= 1

Example:

0.95

max_tokens

integer

default:65536

Maximum generated tokens. Zhipu AI recommends at least 1024.

Required range: 1 <= x <= 131072

tool_stream

boolean

default:false

Streams Function Call output when streaming is enabled.

tools

object[]

Function or MCP tool definitions available to the model.

Show child attributes

tool_choice

enum<string>

Controls tool selection.

Available options:

auto

stop

string[]

Up to four sequences that stop generation.

Maximum array length: 4

response_format

object

Selects text or JSON object output.

Show child attributes

request_id

string

Client-provided unique request ID.

Required string length: 6 - 64

user_id

string

Non-sensitive identifier for the end user.

Required string length: 6 - 128

Response

Completion generated successfully

string

required

Completion ID.

object

string

required

Example:

"chat.completion"

created

integer

required

Unix timestamp in seconds.

model

string

required

Example:

"glm-5.3"

choices

object[]

required

Show child attributes

request_id

string

Request ID.

usage

object

Show child attributes

Overview

Native Compatible Endpoints

Model APIs

Authorizations

Body

Response