AI API errors / OpenAI
OpenAI · HTTP 403 · checked Oct 24, 2026
OpenAI 403 unsupported_country_region_territory: what it means and how to fix it
Do not retry: fix it first403 unsupported_country_region_territory: Country, region, or territory not supported
What it meansThe request comes from a location OpenAI does not serve. On cloud servers this is about where the server runs.
How to fix it
- Run the code in a supported region (check your cloud function's region).
Handle it in code
from openai import OpenAI, RateLimitError, InternalServerError
# The SDK retries some errors with backoff; quota and billing errors never clear by retrying.
client = OpenAI(max_retries=6)
try:
r = client.responses.create(model="gpt-5", input="Hello")
except RateLimitError as e: # 429: check e.code for quota vs rate limit
if getattr(e, "code", None) in ("insufficient_quota", "credit_balance_exhausted"):
raise # fix billing, do not retry
except InternalServerError: # 500 / 503 server_is_overloaded
pass # retry later or fall back to another modelThe official SDKs retry some errors automatically (max_retries); billing and quota errors never clear by retrying.
Same kind of error at other providers
- Anthropic 401 authentication_error
- Anthropic 403 permission_error
- Google Gemini API 403 PERMISSION_DENIED
- Google Gemini API 403 PERMISSION_DENIED
Other OpenAI errors
- 429rate_limit_error: Rate limit reached for requestsretry
- 429slow_down: Slow downretry
- 429insufficient_quota: You exceeded your current quota, please check your plan and billing defix
- 401invalid_api_key: Incorrect API key providedfix
- 401invalid_authentication: Invalid Authenticationfix
- 401ip_not_authorized: IP not authorizedfix
- 401You must be a member of an organization to use the APIfix
- 500server_error: The server had an error while processing your requestretry
- 503server_is_overloadedretry
- 400invalid_request_errorfix
Source
- OpenAI error documentation: developers.openai.com/api/docs/guides/error-codes (checked Oct 24, 2026)
Paying too much per call while you are here? Compare AI model prices or estimate your bill.
Up next
Paste any errorEvery AI API error, retry or fixAnthropic, OpenAI and Gemini in one finder.Read it next →Also worth your time
Did this answer your question?
Up next
Get 3 picks for your job, volume and budgetPick an AI model for your jobLLM API pricing for 71 models per 1M tokens, checked at the source. Pick for me: your job, volume and budget give 3 models with the monthly cost. Filters, CSV.Read it next →