Error 502: what to do when claude-sonnet-4-5 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.

claude-sonnet-4-5 is served by Anthropic. 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 claude-sonnet-4-5 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 = 'claude-sonnet-4-5'


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
VendorAnthropic
Context1M
CapabilitiesReasoning, Tools, Files, Vision
API formatsopenai, openai-response, openai-response-compact, anthropic, gemini, openai-alpha-search
Billing formulap * 3 + cr * 0.3 + cc * 3.75 + cc1h * 6 + c * 15

FAQ

Does a long context window make 502 more likely?

The request parameters must change; retrying alone will not help. This is a client-side configuration issue; nothing changes server-side. The 1M context window sets the maximum input per request; anything beyond it is rejected outright. Fail fast on parameter errors instead of spending retries on them. Truncate or summarise long inputs — it noticeably reduces 502.

Can switching to a comparable model from another vendor fix 502?

Keep a fallback model ready as well. Building a fallback into the architecture is more reliable than patching errors one by one. This model from Anthropic has several upstream nodes the gateway can switch between. Put the model name in config, so switching upstreams needs no code change.

How should I use the Retry-After header in the response?

You usually do not need to change business code, just the call cadence. Retrying is the most effective first step. With billing p * 3 + cr * 0.3 + cc * 3.75 + cc1h * 6 + c * 15, failed requests are not counted toward usage. Use exponential backoff for retryable errors and return immediately for the rest.

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

It is mainly a quota matter, not a fault in the model itself. Raising the plan ceiling or lowering the call rate both help. Input price is about $3.00 per million tokens. With billing p * 3 + cr * 0.3 + cc * 3.75 + cc1h * 6 + c * 15, the cost of long output comes mostly from output tokens. Check your balance and rate limits in the console before debugging code. When estimating cost from p * 3 + cr * 0.3 + cc * 3.75 + cc1h * 6 + c * 15, include the retry budget.

Other errors on this model

Other models with the same error

Back to the model page

Data updated: 2026-10-10 12:10

Technical SupportLive Support
Back to Top