Is Gemini down right now?
Authenticated API inference - 2 models monitored · How we classify outages
Weekly AI pricing & uptime digest
Price drops, new model releases, and incident summaries - every Monday. Free.
Gemini is currently operational - 369ms HTTP response. Last checked . 90-day uptime: 94.9%. Gemini API: all 2 models responding - fastest TTFT 301ms.
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 Gemini status on your site, README, or docs.
HTTP uptime (90d)
94.9%
20 incidents (90d)
HTTP response now
369ms
HTTP p50 (7d)
679ms
median ping response
HTTP p95 (7d)
1747ms
tail ping response
Gemini API Status
Live · every 5 minBest TTFT (p50)
301ms
time to first token
Best throughput
1000tok/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.
Is Gemini slow right now?
No, Gemini is not slow right now. All 2 monitored models are responding within their normal speed range.Last checked just now.
HTTP endpoint response: 369ms (7-day p50: 679ms). This measures basic reachability, not model inference speed.
TTFT (time-to-first-token) is measured via authenticated streaming API calls every 5 minutes. Current values are compared against 7-day and 30-day rolling baselines. A minimum of 5 successful checks is required before classification. Methodology
Gemini speed FAQ
Is Gemini slow right now?
No, Gemini is not slow right now. All 2 monitored models are responding within their normal speed range.
Why is Gemini so slow today?
Gemini is currently responding within its normal speed range. If you're experiencing slowness, it may be specific to your region, account tier, or the particular model you're using. Tickerr monitors multiple models independently.
Is Gemini down or just responding slowly?
Gemini is responding to requests (not down). Response times are within the normal range.
How does Tickerr determine whether Gemini is slow?
Tickerr sends authenticated API requests to Gemini every 5 minutes and measures time-to-first-token (TTFT). Current TTFT is compared against a rolling 7-day and 30-day baseline. A model is classified as slow when its current p50 TTFT exceeds 2x its baseline, and severely slow at 3.5x. At least 5 successful checks are required before any classification is made.
What is normal response time for Gemini?
The normal p50 TTFT for Gemini is approximately 421ms based on the trailing 7-day baseline. This means half of all requests receive their first token within 421ms. The HTTP endpoint typically responds in 679ms.
Can one Gemini model be slow while others are working normally?
Yes. Gemini runs multiple models (e.g. gemini-2.5-flash, gemini-2.5-flash-lite), and each can have independent performance characteristics. Tickerr monitors each model separately. A slowdown on one model doesn't necessarily affect others.
Experimental capability checks
PUBLIC PILOTTickerr sends deterministic test prompts to Gemini every hour and evaluates the output using code-based pass/fail checks. These results are informational onlyduring the pilot period and do not affect the tool's status verdict.
How Tickerr tests this
Every hour, Tickerr sends three deterministic test prompts to each monitored model via the provider's API. Each response is evaluated with a code-based pass/fail check — no subjective judgement.
- Instruction following: asks the model to reply with an exact word. Graded by exact string match.
- JSON schema: asks for a JSON object matching a fixed schema. Graded by parse + field validation.
- Tool call: asks the model to call a function with specific arguments. Graded by parsing the tool-call response.
Infrastructure errors (timeouts, rate limits, auth failures) are tracked separately and excluded from capability pass rates. Models that don't support tool calls are marked “not supported” rather than counted as failures. Full methodology
HTTP endpoint response time (7 days)
p50 679ms·p95 1747msⓘ HTTP response times to Gemini's status endpoint - measures infrastructure availability, not API inference speed. For TTFT and model-level API status, see the Gemini API Status section above.
90-day uptime
Incident history
<p> Incident began at <strong>2026-08-20 08:40</strong> and ended at <strong>2026-08-20 12:20</strong> <span>(all times are <strong>US/Pacific</strong>)…
<p> Incident began at <strong>2026-08-20 08:40</strong> <span>(all times are <strong>US/Pacific</strong>).</span></p><div class="cBIRi14aVDP__status-…
gemini-2.5-flash-lite API Latency Degraded
Independent monitoring detected elevated API latency for gemini-2.5-flash-lite. Current TTFT is 2.5× above the rolling p50 baseline (1062ms vs p50 421ms). The service is responding but slower than nor…
<p> Incident began at <strong>2026-07-15 16:57</strong> and ended at <strong>2026-07-16 05:25</strong> <span>(all times are <strong>US/Pacific</strong>)…
<p> Incident began at <strong>2026-07-14 10:00</strong> and ended at <strong>2026-07-14 20:40</strong> <span>(all times are <strong>US/Pacific</strong>)…
<p> Incident began at <strong>2026-07-14 10:00</strong> and ended at <strong>2026-07-14 20:40</strong> <span>(all times are <strong>US/Pacific</strong>)…
<p> Incident began at <strong>2026-07-15 16:57</strong> and ended at <strong>2026-07-16 05:25</strong> <span>(all times are <strong>US/Pacific</strong>)…
<p> Incident began at <strong>2026-07-15 16:57</strong> <span>(all times are <strong>US/Pacific</strong>).</span></p><div class="cBIRi14aVDP__status-…
gemini-2.5-flash-lite API Latency Degraded
Independent monitoring detected elevated API latency for gemini-2.5-flash-lite. Current TTFT is 5.3× above the rolling p50 baseline (2143ms vs p50 406ms). The service is responding but slower than nor…
<p> Incident began at <strong>2026-07-14 10:00</strong> <span>(all times are <strong>US/Pacific</strong>).</span></p><div class="cBIRi14aVDP__status-…
gemini-2.5-flash-lite API Latency Degraded
Independent monitoring detected elevated API latency for gemini-2.5-flash-lite. Current TTFT is 3.9× above the rolling p50 baseline (1523ms vs p50 391ms). The service is responding but slower than nor…
Independent monitoring detected consecutive API failures for gemini-2.5-flash-lite. Tickerr measures time-to-first-token (TTFT) via live streaming API calls every 5 minutes.
gemini-2.5-flash-lite API Latency Degraded
Independent monitoring detected elevated API latency for gemini-2.5-flash-lite. Current TTFT is 8.7× above the rolling p50 baseline (3967ms vs p50 457ms). The service is responding but slower than nor…
gemini-2.5-flash-lite API Latency Degraded
Independent monitoring detected elevated API latency for gemini-2.5-flash-lite. Current TTFT is 3.1× above the rolling p50 baseline (1323ms vs p50 421ms). The service is responding but slower than nor…
gemini-2.5-flash-lite API Latency Degraded
Independent monitoring detected elevated API latency for gemini-2.5-flash-lite. Current TTFT is 16.9× above the rolling p50 baseline (6862ms vs p50 406ms). The service is responding but slower than no…
gemini-2.5-flash-lite API Latency Degraded
Independent monitoring detected elevated API latency for gemini-2.5-flash-lite. Current TTFT is 4.4× above the rolling p50 baseline (1827ms vs p50 412ms). The service is responding but slower than nor…
Independent monitoring detected consecutive API failures for gemini-2.5-flash. Tickerr measures time-to-first-token (TTFT) via live streaming API calls every 5 minutes.
Independent monitoring detected consecutive API failures for gemini-2.5-flash-lite. Tickerr measures time-to-first-token (TTFT) via live streaming API calls every 5 minutes.
gemini-2.5-flash-lite API Latency Degraded
Independent monitoring detected elevated API latency for gemini-2.5-flash-lite. Current TTFT is 8.8× above the rolling p50 baseline (4684ms vs p50 531ms). The service is responding but slower than nor…
Related pages
Gemini API not working? Common error codes
If Gemini'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 (RESOURCE_EXHAUSTED) | Rate limit exceeded - 15 RPM on free tier; add retry delay |
| HTTP 503 (UNAVAILABLE) | Service unavailable - check for Google Cloud incidents |
| HTTP 400 (INVALID_ARGUMENT) | Bad request - check prompt format and safety filters |
Note: Tickerr monitors Gemini'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 Gemini status
Gemini is Google's AI assistant and language model. Gemini downtime affects both the consumer app and the API used by developers. If Gemini is not working, it may be a Google infrastructure issue affecting multiple services. Gemini status is checked every 5 minutes.