Error 504: what to do when glm-5.1 fails

A 504 means the gateway timed out waiting for the upstream model: the request was sent, but the upstream did not return within the gateway timeout.

504 Gateway Timeout means the gateway gave up waiting for the upstream response. The request was forwarded, but no result came back within the gateway limit. Shortening the output, switching to streaming, or lowering max_tokens usually fixes it.

glm-5.1 is served by Z.AI. 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 took longer than the gateway timeout allows. The recommended first action is: Switch to streaming output.

Common causes

  • The upstream took longer than the gateway timeout allows
  • A long context pushed inference time up
  • An upstream node is stuck
  • A non-streaming request with a very long output

How to fix

  • Switch to streaming output
  • Shorten the context and lower max_tokens
  • Retry after a short wait
  • Use a model with faster inference

Retry with exponential backoff

The snippet below retries when glm-5.1 returns 504, 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 = 'glm-5.1'


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
VendorZ.AI
Context200K
CapabilitiesReasoning, Tools, Open Weights
API formatsopenai, openai-response, openai-response-compact, anthropic, gemini, openai-alpha-search
Billing formulap * 1.4 + cr * 0.26 + cc * 0 + c * 4.4

FAQ

How many retry attempts is reasonable?

Retrying is the most effective first step. With billing p * 1.4 + cr * 0.26 + cc * 0 + c * 4.4, failed requests are not counted toward usage. Set the retry ceiling to 3–5 attempts and add jitter. Use exponential backoff for retryable errors and return immediately for the rest.

Can setting max_tokens too high trigger 504?

The request parameters must change; retrying alone will not help. This is a client-side configuration issue; nothing changes server-side. The capability tags are Reasoning, Tools, Open Weights, and parameter ceilings follow from that capability set. The 200K context window sets the maximum input per request; anything beyond it is rejected outright. Truncate or summarise long inputs — it noticeably reduces 504.

Can async or batch processing avoid 504?

Concurrency and timeouts are the real variables here, not the model itself. Lower the concurrency first — most throughput complaints disappear once you do. A 200K context means long inputs add noticeably to first-token latency. Use batching or a queue to smooth peaks — steadier than raising concurrency on the fly.

How can I prevent 504 on glm-5.1 in advance?

Building a fallback into the architecture is more reliable than patching errors one by one. This model from Z.AI has several upstream nodes the gateway can switch between. Keep a lighter fallback model ready so the main flow never breaks.

Other errors on this model

Other models with the same error

Back to the model page

Data updated: 2026-10-10 18:35

Technical SupportLive Support
Back to Top