Deep Thinking

Deep thinking models are AI systems with complex reasoning capabilities that solve problems requiring deep cognitive processing through multi-step logical analysis, self-reflection, and chain-of-thought reasoning. This document describes how to call models that support deep thinking, including GLM, Deepseek, and Minimax.

GLM Models - Mixed thinking mode, thinking enabled by default: GLM-5.1, GLM-5, GLM-4.7

MiniMax Models - Thinking mode only: MiniMax-M2.5, MiniMax-M2.1

1. Using Deep Thinking in curl

curl --request POST \
  --url https://api.jalapeno-cloud.ai/v1/chat/completions \
  --header 'Authorization: Bearer ${API_KEY}' \
  --header 'Content-Type: application/json' \
  --data '{
 "model": "${MODEL_NAME}",
 "messages": [{
 "role": "user",
 "content": "Who are you"
 }],
 "stream": true,
 "stream_options":{"include_usage": true},
 "chat_template_kwargs": {"thinking": true}
 }'

2. Using Deep Thinking in Python

import requests

url = "https://api.jalapeno-cloud.ai/v1/chat/completions"

payload = {
    "model": "${MODEL_NAME}",
    "messages": [
        {
            "role": "user",
            "content": "Please give a travel plan"
        }
    ],
    "stream": True,
    "stream_options":{"include_usage": True},
    "chat_template_kwargs": {"thinking": True}
}
headers = {
    "Authorization": "Bearer ${API_KEY}",
    "Content-Type": "application/json"
}

response = requests.request("POST", url, json=payload, headers=headers)

print(response.text)

3. Using Deep Thinking in JavaScript

var myHeaders = new Headers();
myHeaders.append("Authorization", "Bearer ${API_KEY}");
myHeaders.append("Content-Type", "application/json");

var raw = JSON.stringify({
    "messages": [
        {
            "role": "user",
            "content": "Please give a travel plan"
        }
    ],
    "model": "${MODEL_NAME}",
    "stream": true,
    "chat_template_kwargs": {"thinking": true}
});

var requestOptions = {
    method: 'POST',
    headers: myHeaders,
    body: raw,
    redirect: 'follow'
};

fetch("https://api.jalapeno-cloud.ai/v1/chat/completions", requestOptions)
    .then(response => response.text())
    .then(result => console.log(result))
    .catch(error => console.log('error', error));

4. Using Deep Thinking in Golang

package main

import (
    "bytes"
    "encoding/json"
    "net/http"
)

func main() {
    url := "https://api.jalapeno-cloud.ai/v1/chat/completions"
    payload := map[string]interface{} {
        "model": "${MODEL_NAME}",
        "messages": []map[string]string{
            {"role": "user", "content": "Please give a travel plan"},
        },
        "stream": true,
        "chat_template_kwargs": {"thinking": true}
    }
    body, _ := json.Marshal(payload)
    req, _ := http.NewRequest("POST", url, bytes.NewBuffer(body))
    req.Header.Set("Authorization", "Bearer ${API_KEY}")
    req.Header.Set("Content-Type", "application/json")
    client := &http.Client{}
    resp, _ := client.Do(req)
    defer resp.Body.Close()
}