Error 502: what to do when gpt-5.4 fails

A 502 means the gateway received an invalid response from the upstream model service: the request reached the gateway, but the hop to the upstream failed.

502 Bad Gateway means the gateway received an invalid response from the upstream model service. The request reached the gateway; the failure happened on the hop from gateway to upstream, usually due to an upstream restart or a dropped connection.

gpt-5.4 is served by OpenAI. Everything on this page — triggers, fixes and measured data — is compiled from the real runtime behaviour of this model at the gateway layer.

At this gateway, the most common trigger is: The upstream model service is unavailable or returned a malformed response. The recommended first action is: Retry once — 502s are usually transient.

Common causes

  • The upstream model service is unavailable or returned a malformed response
  • An upstream node is restarting
  • The gateway-to-upstream connection was interrupted
  • The model was temporarily taken offline

How to fix

  • Retry once — 502s are usually transient
  • Switch to an equivalent model from another vendor
  • If only one model keeps returning 502, its upstream is unhealthy
  • Try again later or contact us

Retry with exponential backoff

The snippet below retries when gpt-5.4 returns 502, up to 5 attempts, with an increasing wait plus random jitter so concurrent calls do not retry in lockstep. Read the base URL and API key from environment variables — never hardcode them.

import os, time, random
import requests

BASE  = os.getenv("OPENAI_BASE_URL")   # e.g. https://<your-gateway>/v1
KEY   = os.getenv("OPENAI_API_KEY")
MODEL = 'gpt-5.4'


def chat(messages, retries=5):
    """Retry with exponential backoff + jitter."""
    for i in range(retries):
        try:
            r = requests.post(
                BASE + "/chat/completions",
                headers={"Authorization": "Bearer " + KEY},
                json={"model": MODEL, "messages": messages, "stream": True},
                timeout=60,
            )
            if r.status_code == 429 or r.status_code >= 500:
                time.sleep(min(2 ** i + random.uniform(0, 1), 30))
                continue
            r.raise_for_status()
            return r.json()
        except requests.exceptions.Timeout:
            time.sleep(min(2 ** i + random.uniform(0, 1), 30))
    raise RuntimeError("gave up after " + str(retries) + " retries")


print(chat([{"role": "user", "content": "hello"}]))

Key facts for this model

API endpointhttps://api.airai.cc/v1
OpenAI-compatibleOpenAI-compatible
VendorOpenAI
Context1.1M
CapabilitiesReasoning, Tools, Files, Vision
API formatsopenai, openai-response, openai-response-compact, anthropic, gemini, openai-alpha-search
Billing formulap * 2.5 + cr * 0.25 + c * 15) : tier("272k_plus", p * 5 + cr * 0.5 + c * 22.5

FAQ

How long should the timeout be?

Lower the concurrency first — most throughput complaints disappear once you do. This model has a 1.1M context window and comes from OpenAI. A 1.1M context means long inputs add noticeably to first-token latency. Add a cache layer so repeated requests do not all hit the model.

502 keeps recurring on gpt-5.4 — how do I tell whether it is the model or my account?

It is usually transient and recovers on its own. The capability tags for this model are Reasoning, Tools, Files, Vision. Decide account-level versus model-level first; the two need completely different handling.

Does sharing one key across several services make 502 more likely?

It is mainly a quota matter, not a fault in the model itself. Billing follows p * 2.5 + cr * 0.25 + c * 15) : tier("272k_plus", p * 5 + cr * 0.5 + c * 22.5, so no output means no charge. With billing p * 2.5 + cr * 0.25 + c * 15) : tier("272k_plus", p * 5 + cr * 0.5 + c * 22.5, failed requests are not counted toward usage. Check your balance and rate limits in the console before debugging code. When estimating cost from p * 2.5 + cr * 0.25 + c * 15) : tier("272k_plus", p * 5 + cr * 0.5 + c * 22.5, include the retry budget.

Do failed requests count against my rate limit quota?

No charge — only output actually produced counts toward usage. Only the output already produced is billed; the failed part is not. With billing p * 2.5 + cr * 0.25 + c * 15) : tier("272k_plus", p * 5 + cr * 0.5 + c * 22.5, the cost of long output comes mostly from output tokens. With billing p * 2.5 + cr * 0.25 + c * 15) : tier("272k_plus", p * 5 + cr * 0.5 + c * 22.5, failed requests are not counted toward usage. Check your balance and rate limits in the console before debugging code. When estimating cost from p * 2.5 + cr * 0.25 + c * 15) : tier("272k_plus", p * 5 + cr * 0.5 + c * 22.5, include the retry budget.

Other errors on this model

Other models with the same error

Back to the model page

Data updated: 2026-10-11 19:15

Technical SupportLive Support
Back to Top