Limits

{
  "error": {
    "code": 429,
    "message": "Rate limit exceeded. Please retry later.",
    "type": "rate_limit_error",
    "metadata": {
      "error_type": "rate_limit_exceeded"
    }
  }
}

import os
import time

import requests

URL = "https://api.vultrinference.com/v1/chat/completions"
HEADERS = {"Authorization": f"Bearer {os.environ['VULTR_INFERENCE_API_KEY']}"}


# Retry what a later attempt can fix: 429 after Retry-After, and 502, 503 and 504 with a growing wait
def post(body: dict, attempts: int = 5) -> dict:
    for attempt in range(attempts):
        response = requests.post(URL, headers=HEADERS, json=body, timeout=600)
        if response.status_code not in (429, 502, 503, 504) or attempt == attempts - 1:
            response.raise_for_status()
            return response.json()
        time.sleep(int(response.headers.get("Retry-After", 2**attempt)))


reply = post({"model": "deepseek-v4.1-flash", "messages": [{"role": "user", "content": "Say hello."}]})
print(reply["choices"][0]["message"]["content"])

const URL = "https://api.vultrinference.com/v1/chat/completions";

// Retry what a later attempt can fix: 429 after Retry-After, and 502, 503 and 504 with a growing wait
async function post(body: object, attempts = 5): Promise<any> {
  for (let attempt = 0; ; attempt++) {
    const response = await fetch(URL, {
      method: "POST",
      headers: { Authorization: `Bearer ${process.env.VULTR_INFERENCE_API_KEY}`, "Content-Type": "application/json" },
      body: JSON.stringify(body),
    });
    if (![429, 502, 503, 504].includes(response.status) || attempt === attempts - 1) {
      if (!response.ok) throw new Error(`${response.status}: ${await response.text()}`);
      return response.json();
    }
    const wait = Number(response.headers.get("Retry-After") ?? 2 ** attempt);
    await new Promise((resolve) => setTimeout(resolve, wait * 1000));
  }
}

const reply = await post({ model: "deepseek-v4.1-flash", messages: [{ role: "user", content: "Say hello." }] });
console.log(reply.choices[0].message.content);

Your input is ~1203887 tokens, which exceeds the model context limit of 1048576. Please shorten your messages.