API Keys

Default Key Active
sk-anygpu-A8fK2mN9xP4qR7wL

Keep your API key secure. Do not share it in public repositories.

Code Examples

curl https://api.anygpu.com/v1/chat/completions \
  -H "Authorization: Bearer sk-anygpu-A8fK2mN9xP4qR7wL" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "user", "content": "Hello, world!"}
    ],
    "max_tokens": 1000
  }'
import requests

response = requests.post(
    "https://api.anygpu.com/v1/chat/completions",
    headers={
        "Authorization": "Bearer sk-anygpu-A8fK2mN9xP4qR7wL",
        "Content-Type": "application/json"
    },
    json={
        "model": "gpt-4o",
        "messages": [
            {"role": "user", "content": "Hello, world!"}
        ],
        "max_tokens": 1000
    }
)
print(response.json())
const response = await fetch("https://api.anygpu.com/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer sk-anygpu-A8fK2mN9xP4qR7wL",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: "gpt-4o",
    messages: [
      { role: "user", content: "Hello, world!" }
    ],
    max_tokens: 1000
  })
});
const data = await response.json();
console.log(data);
package main

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

func main() {
    reqBody, _ := json.Marshal(map[string]interface{}{
        "model": "gpt-4o",
        "messages": []map[string]string{
            {"role": "user", "content": "Hello, world!"},
        },
        "max_tokens": 1000,
    })
    req, _ := http.NewRequest("POST", "https://api.anygpu.com/v1/chat/completions", bytes.NewBuffer(reqBody))
    req.Header.Set("Authorization", "Bearer sk-anygpu-A8fK2mN9xP4qR7wL")
    req.Header.Set("Content-Type", "application/json")
    client := &http.Client{}
    resp, _ := client.Do(req)
    defer resp.Body.Close()
    fmt.Println(resp)
}

Request Parameters

Parameter Type Default Description
modelstringModel ID (e.g. gpt-4o, claude-3-5-sonnet)
messagesarrayChat message history with role and content
max_tokensinteger4096Maximum tokens to generate
temperaturefloat0.7Sampling temperature (0–2)
top_pfloat1.0Nucleus sampling threshold
streambooleanfalseEnable streaming responses
stoparray/stringnullStop sequences
frequency_penaltyfloat0Penalize repeated tokens
presence_penaltyfloat0Penalize new topic introduction

Rate Limits

1,000
Requests / Minute
100K
Tokens / Minute
$50
Spending Limit