curl --request POST \
  --url https://api.zerogpu.ai/v1/chat/completions \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "model": "qwen3-30b-a3b-fp8",
  "messages": [
    {
      "role": "system",
      "content": "You are a pragmatic senior engineer. Be brief."
    },
    {
      "role": "user",
      "content": "My API is getting rate-limited by a third party. Give me 3 battle-tested strategies to handle it, one line each."
    }
  ]
}
'

import requests

url = "https://api.zerogpu.ai/v1/chat/completions"

payload = {
    "model": "qwen3-30b-a3b-fp8",
    "messages": [
        {
            "role": "system",
            "content": "You are a pragmatic senior engineer. Be brief."
        },
        {
            "role": "user",
            "content": "My API is getting rate-limited by a third party. Give me 3 battle-tested strategies to handle it, one line each."
        }
    ]
}
headers = {
    "x-api-key": "<api-key>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'x-api-key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'qwen3-30b-a3b-fp8',
    messages: [
      {role: 'system', content: 'You are a pragmatic senior engineer. Be brief.'},
      {
        role: 'user',
        content: 'My API is getting rate-limited by a third party. Give me 3 battle-tested strategies to handle it, one line each.'
      }
    ]
  })
};

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

false

package main

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

func main() {

	url := "https://api.zerogpu.ai/v1/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"qwen3-30b-a3b-fp8\",\n  \"messages\": [\n    {\n      \"role\": \"system\",\n      \"content\": \"You are a pragmatic senior engineer. Be brief.\"\n    },\n    {\n      \"role\": \"user\",\n      \"content\": \"My API is getting rate-limited by a third party. Give me 3 battle-tested strategies to handle it, one line each.\"\n    }\n  ]\n}")

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

	req.Header.Add("x-api-key", "<api-key>")
	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))

}

require 'uri'
require 'net/http'

url = URI("https://api.zerogpu.ai/v1/chat/completions")

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

request = Net::HTTP::Post.new(url)
request["x-api-key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"qwen3-30b-a3b-fp8\",\n  \"messages\": [\n    {\n      \"role\": \"system\",\n      \"content\": \"You are a pragmatic senior engineer. Be brief.\"\n    },\n    {\n      \"role\": \"user\",\n      \"content\": \"My API is getting rate-limited by a third party. Give me 3 battle-tested strategies to handle it, one line each.\"\n    }\n  ]\n}"

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

{
  "id": "id-1784324156320",
  "object": "chat.completion",
  "created": 1784324156,
  "model": "qwen3-30b-a3b-fp8",
  "choices": [
    {
      "index": 0,
      "finish_reason": "stop",
      "message": {
        "role": "assistant",
        "content": "**1. Exponential backoff with jitter** – Retry on 429s with doubling delays plus randomness so your retries don't stampede in sync.\n\n**2. Client-side token bucket** – Throttle your own outbound rate just below the provider's limit so you never hit the wall in the first place.\n\n**3. Cache and coalesce** – Cache hot responses and merge duplicate in-flight requests so repeat calls never reach the third party at all.",
        "reasoning": "The user's API is being rate-limited by a third party and wants 3 battle-tested strategies, one line each. The classic answers: exponential backoff with jitter, client-side throttling below the limit, and caching plus request coalescing. Keep each to one line.",
        "tool_calls": []
      }
    }
  ],
  "usage": {
    "prompt_tokens": 52,
    "completion_tokens": 143,
    "total_tokens": 195
  }
}

{}