Error 403: what to do when gpt-5.5-pro fails

A 403 means you are authenticated but not allowed: the key is valid, yet it may not call this model or this group.

403 Forbidden means the identity was recognised but access is denied. The difference from 401: 401 asks who you are, 403 says you lack permission. Usually the model needs to be added to the allowed list or group bound to your key.

gpt-5.5-pro 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: This key is not authorised for this model. The recommended first action is: Add this model to the key allowlist on the Tokens page.

Common causes

  • This key is not authorised for this model
  • The model is not in the group the key is bound to
  • The key has an IP allowlist that excludes your current IP
  • The model was retired or requires higher permissions

How to fix

  • Add this model to the key allowlist on the Tokens page
  • Confirm the key group includes this model
  • Review the IP allowlist settings
  • Switch to a model you are allowed to call

Retry with exponential backoff

The snippet below retries when gpt-5.5-pro returns 403, 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-5.5-pro'


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 * 30 + c * 180) : tier("272k_plus", p * 60 + c * 270
Cache discount1×

FAQ

Is 403 related to how gpt-5.5-pro is billed?

No charge — only output actually produced counts toward usage. With billing p * 30 + c * 180) : tier("272k_plus", p * 60 + c * 270, the cost of long output comes mostly from output tokens. When estimating cost from p * 30 + c * 180) : tier("272k_plus", p * 60 + c * 270, include the retry budget.

Does switching to streaming reduce 403?

The request parameters must change; retrying alone will not help. This is a client-side configuration issue; nothing changes server-side. The 1.1M context window sets the maximum input per request; anything beyond it is rejected outright. Truncate or summarise long inputs — it noticeably reduces 403.

Can async or batch processing avoid 403?

Concurrency and timeouts are the real variables here, not the model itself. Lower the concurrency first — most throughput complaints disappear once you do. A 1.1M context means long inputs add noticeably to first-token latency. Start with low concurrency, watch it for a few minutes, then scale up.

Should retries add random jitter?

You usually do not need to change business code, just the call cadence. With billing p * 30 + c * 180) : tier("272k_plus", p * 60 + c * 270, 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.

Other errors on this model

Other models with the same error

Back to the model page

Data updated: 2026-10-11 13:20

Technical SupportLive Support
Back to Top