Is ChatGPT down right now?
Authenticated API inference - 2 models monitored · How we classify outages
ChatGPT is currently operational - 169ms HTTP response. Last checked . 90-day uptime: 100%. ChatGPT API: all 2 models responding - fastest TTFT 754ms.
Stay informed
Follow @tickerr_ai
We post when tier 1 LLM APIs go down - before the official status page updates.
Follow on X →Or get the weekly reliability digest:
Add a status badge
Show live ChatGPT status on your site, README, or docs.
HTTP uptime (90d)
100%
20 incidents (90d)
HTTP response now
169ms
HTTP p50 (7d)
144ms
median ping response
HTTP p95 (7d)
739ms
tail ping response
API Inference Monitoring
Live · every 5 minBest TTFT (p50)
754ms
time to first token
Best throughput
93tok/s
output tokens/sec (24h avg)
Min success rate
100%
worst model (24h)
P50 = typical speed. P95 = worst case 95% of the time. Measured by Tickerr's independent inference checks. Requires ≥10 checks to display.
TTFT over 24 hours
ⓘ Authenticated streaming API calls via native fetch. TTFT = milliseconds from request start to first streamed token chunk. Throughput = output tokens ÷ generation time. Checks run from Vercel us-east-1. Independent of the provider's official status page.
Agent monitoring active · 2 agents reporting · Powered by Tickerr MCP
HTTP endpoint response time (7 days)
p50 144ms·p95 739msⓘ HTTP response times to ChatGPT's status endpoint - measures infrastructure availability, not API inference speed. For TTFT and model-level API status, see the ChatGPT API Status section above.
90-day uptime comparison
Independent monitoring catches issues faster - official pages sometimes lag by hours before acknowledging problems.
Service components
via status.openai.com ↗Incident history
We are investigating the issue for the listed services.
Some OpenAI website content pages, including Help Center articles, are currently unavailable. Help Center search functionality is also unavailable, and the chatbot experience may be degraded. We are i…
We are investigating an issue causing users to receive “Selected model is at capacity. Please try a different model.” errors across multiple models. We are working to identify the cause and restore no…
We are investigating elevated errors affecting image generation in ChatGPT. Some users may be unable to generate images.
Core functionality has been restored but we are aware of known and ongoing issues in FedRAMP workspaces with Codex, workspace analytics, conversation search, searching for custom GPTs, ChatGPT user in…
gpt-4o-mini API Latency Degraded
Independent monitoring detected elevated API latency for gpt-4o-mini. Current TTFT is 2.3× above the rolling p50 baseline (1884ms vs p50 837ms). The service is responding but slower than normal. Ticke…
gpt-4o-mini API Latency Degraded
Independent monitoring detected elevated API latency for gpt-4o-mini. Current TTFT is 2.4× above the rolling p50 baseline (1998ms vs p50 835ms). The service is responding but slower than normal. Ticke…
We are investigating an issue affecting some users of the ChatGPT Windows desktop app on Windows. Affected users may see chat history or conversations fail to load, missing sidebar icons, or login/sig…
We are investigating reports that Codex usage limits are being consumed faster than expected.
A small number of Users have incorrectly cancelled subscription.
gpt-4.1-mini API Latency Degraded
Independent monitoring detected elevated API latency for gpt-4.1-mini. Current TTFT is 2.5× above the rolling p50 baseline (2138ms vs p50 866ms). The service is responding but slower than normal. Tick…
We are investigating the issue for the listed services.
We have applied the mitigation and are monitoring the recovery.
We are investigating the issue for the listed services.
gpt-4.1-mini API Latency Degraded
Independent monitoring detected elevated API latency for gpt-4.1-mini. Current TTFT is 5× above the rolling p50 baseline (3823ms vs p50 761ms). The service is responding but slower than normal. Ticker…
We have identified an issue causing some users to be unable to access ChatGPT on [chatgpt.com](http://chatgpt.com "chatgpt.com"). We are working on implementing a mitigation. In the meantime, please t…
We are investigating the issue for the listed services.
We are investigating the issue for the listed services.
We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.
We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.
Related pages
ChatGPT API not working? Common error codes
If ChatGPT's API is returning errors, the table below explains what each code means and how to fix it. If errors are widespread, check the live status above - a service incident will appear there within minutes.
| Error | What it means & what to do |
|---|---|
| HTTP 429 | Rate limit or quota exceeded - check tier limits and retry with backoff |
| HTTP 500 | Internal server error - retry once; if persistent, check status.openai.com |
| HTTP 503 | Service unavailable - check for active OpenAI incidents |
| "context_length_exceeded" | Input too long for model - truncate or summarize context |
Note: Tickerr monitors ChatGPT's status endpoint, not individual API calls. An HTTP 429 or 500 in your app may be specific to your account tier - check the rate limits page for plan-specific thresholds.
About ChatGPT status
ChatGPT is an AI chatbot and API built by OpenAI, powering millions of apps and users globally. This page tracks two independent signals: HTTP availability (is chatgpt.com reachable?) and live API inference (is the OpenAI API actually working for developers?). Tickerr makes authenticated API calls to GPT-4o-mini, GPT-4o, and o4-mini every 5–15 minutes, measuring TTFT (time-to-first-token) and output throughput. This catches model-layer failures and overloads that don't show up as HTTP outages. Common ChatGPT API errors: HTTP 429 (rate limit or quota exceeded - check your tier and add backoff), HTTP 500 (internal server error - retry once), HTTP 503 (service unavailable - check for active incidents). OpenAI's official status page at status.openai.com is typically updated within 15–30 minutes of a confirmed incident; Tickerr's independent inference monitoring surfaces issues faster.
You can also check the official ChatGPT status page.