Skip to content

Outage tracker / Anthropic

Is Anthropic down?

I'm having a problem

Operationalchecked moments ago

We reached Anthropic from all 10 regions we check.

As of Oct 5, 2026, 8:18 PM UTC, Anthropic answered RealUptime's probes in all 10 regions that returned a reading.

Functional endpoints verified

Last outage: 34 min on Sep 3, 2026 (web surface and API, from South America, US-East, UK, Asia-Pacific, US-Central, Southeast Asia, US-West and Australia).

our independent probeslive · checked Oct 5, 2026, 8:18 PM UTC
US-East222 msOperational
US-West192 msOperational
Europe143 msOperational
Asia-Pacific193 msOperational
US-Central214 msOperational
Canada123 msOperational
UK149 msOperational
Southeast Asia255 msOperational
Australia560 msOperational
South America200 msOperational
their status pagetheir claim, not our reading

Anthropic reports: All systems operational (“All Systems Operational”)

from Anthropic's own status page, checked Oct 5, 2026, 7:58 PM UTC
Our probes and Anthropic's own status page agree: both show Anthropic as reachable right now.

Anthropic's own component breakdown, as they publish it

  • claude.aiOperational
  • Claude Console (platform.claude.com)Operational
  • Claude API (api.anthropic.com)Operational
  • Claude CodeOperational
  • Claude CoworkOperational
  • Claude for GovernmentOperational

These are Anthropic's components, named and scored by Anthropic. We do not map them onto the functions we check above, because we have no way to know which of their components our checks touch. Two lists, side by side, neither one rewriting the other.

This is Anthropic's own claim about their service, shown separately from what we measured. We never change our own numbers based on what a vendor reports, and this reading never changes theirs. Read both.

Anthropic response time, by region

US-East
267msp95 · latest
1s500ms0ms
US-East response time (p95) over the last 30 daysDaily 95th-percentile response time for US-East, scaled to a maximum of 1s. Days with no samples are not plotted, not shown as zero.2026-09-06 UTC: p95 358ms2026-09-07 UTC: p95 393ms2026-09-08 UTC: p95 384ms2026-09-09 UTC: p95 358ms2026-09-10 UTC: p95 356ms2026-09-11 UTC: p95 399ms2026-09-12 UTC: p95 387ms2026-09-13 UTC: p95 291ms2026-09-14 UTC: p95 342ms2026-09-15 UTC: p95 308ms2026-09-16 UTC: p95 477ms2026-09-17 UTC: p95 512ms2026-09-18 UTC: p95 398ms2026-09-19 UTC: p95 365ms2026-09-20 UTC: p95 269ms2026-09-21 UTC: p95 395ms2026-09-22 UTC: p95 332ms2026-09-23 UTC: p95 382ms2026-09-24 UTC: p95 378ms2026-09-25 UTC: p95 365ms2026-09-26 UTC: p95 343ms2026-09-27 UTC: p95 355ms2026-09-28 UTC: p95 420ms2026-09-29 UTC: p95 370ms2026-09-30 UTC: p95 293ms2026-10-01 UTC: p95 440ms2026-10-02 UTC: p95 364ms2026-10-03 UTC: p95 311ms2026-10-04 UTC: p95 253ms2026-10-05 UTC: p95 267ms
Sep 6Sep 20Oct 5
US-West
286msp95 · latest
1s500ms0ms
US-West response time (p95) over the last 30 daysDaily 95th-percentile response time for US-West, scaled to a maximum of 1s. Days with no samples are not plotted, not shown as zero.2026-09-06 UTC: p95 482ms2026-09-07 UTC: p95 565ms2026-09-08 UTC: p95 404ms2026-09-09 UTC: p95 353ms2026-09-10 UTC: p95 383ms2026-09-11 UTC: p95 316ms2026-09-12 UTC: p95 248ms2026-09-13 UTC: p95 367ms2026-09-14 UTC: p95 418ms2026-09-15 UTC: p95 384ms2026-09-16 UTC: p95 514ms2026-09-17 UTC: p95 557ms2026-09-18 UTC: p95 518ms2026-09-19 UTC: p95 446ms2026-09-20 UTC: p95 447ms2026-09-21 UTC: p95 412ms2026-09-22 UTC: p95 485ms2026-09-23 UTC: p95 396ms2026-09-24 UTC: p95 416ms2026-09-25 UTC: p95 477ms2026-09-26 UTC: p95 519ms2026-09-27 UTC: p95 387ms2026-09-28 UTC: p95 350ms2026-09-29 UTC: p95 513ms2026-09-30 UTC: p95 409ms2026-10-01 UTC: p95 418ms2026-10-02 UTC: p95 340ms2026-10-03 UTC: p95 409ms2026-10-04 UTC: p95 227ms2026-10-05 UTC: p95 286ms
Sep 6Sep 20Oct 5
Europe
325msp95 · latest
1s500ms0ms
Europe response time (p95) over the last 30 daysDaily 95th-percentile response time for Europe, scaled to a maximum of 1s. Days with no samples are not plotted, not shown as zero.2026-09-06 UTC: p95 294ms2026-09-07 UTC: p95 391ms2026-09-08 UTC: p95 405ms2026-09-09 UTC: p95 375ms2026-09-10 UTC: p95 331ms2026-09-11 UTC: p95 364ms2026-09-12 UTC: p95 306ms2026-09-13 UTC: p95 266ms2026-09-14 UTC: p95 315ms2026-09-15 UTC: p95 344ms2026-09-16 UTC: p95 456ms2026-09-17 UTC: p95 575ms2026-09-18 UTC: p95 569ms2026-09-19 UTC: p95 444ms2026-09-20 UTC: p95 464ms2026-09-21 UTC: p95 561ms2026-09-22 UTC: p95 488ms2026-09-23 UTC: p95 370ms2026-09-24 UTC: p95 387ms2026-09-25 UTC: p95 394ms2026-09-26 UTC: p95 421ms2026-09-27 UTC: p95 443ms2026-09-28 UTC: p95 360ms2026-09-29 UTC: p95 348ms2026-09-30 UTC: p95 327ms2026-10-01 UTC: p95 511ms2026-10-02 UTC: p95 581ms2026-10-03 UTC: p95 531ms2026-10-04 UTC: p95 500ms2026-10-05 UTC: p95 325ms
Sep 6Sep 20Oct 5
Asia-Pacific
481msp95 · latest
1s500ms0ms
Asia-Pacific response time (p95) over the last 30 daysDaily 95th-percentile response time for Asia-Pacific, scaled to a maximum of 1s. Days with no samples are not plotted, not shown as zero.2026-09-06 UTC: p95 392ms2026-09-07 UTC: p95 559ms2026-09-08 UTC: p95 424ms2026-09-09 UTC: p95 473ms2026-09-10 UTC: p95 601ms2026-09-11 UTC: p95 665ms2026-09-12 UTC: p95 631ms2026-09-13 UTC: p95 510ms2026-09-14 UTC: p95 607ms2026-09-15 UTC: p95 552ms2026-09-16 UTC: p95 607ms2026-09-17 UTC: p95 669ms2026-09-18 UTC: p95 652ms2026-09-19 UTC: p95 644ms2026-09-20 UTC: p95 581ms2026-09-21 UTC: p95 652ms2026-09-22 UTC: p95 570ms2026-09-23 UTC: p95 592ms2026-09-24 UTC: p95 546ms2026-09-25 UTC: p95 702ms2026-09-26 UTC: p95 626ms2026-09-27 UTC: p95 669ms2026-09-28 UTC: p95 614ms2026-09-29 UTC: p95 751ms2026-09-30 UTC: p95 750ms2026-10-01 UTC: p95 671ms2026-10-02 UTC: p95 554ms2026-10-03 UTC: p95 556ms2026-10-04 UTC: p95 447ms2026-10-05 UTC: p95 481ms
Sep 6Sep 20Oct 5
US-Central
446msp95 · latest
1s500ms0ms
US-Central response time (p95) over the last 30 daysDaily 95th-percentile response time for US-Central, scaled to a maximum of 1s. Days with no samples are not plotted, not shown as zero.2026-09-06 UTC: p95 341ms2026-09-07 UTC: p95 670ms2026-09-08 UTC: p95 697ms2026-09-09 UTC: p95 686ms2026-09-10 UTC: p95 745ms2026-09-11 UTC: p95 577ms2026-09-12 UTC: p95 525ms2026-09-13 UTC: p95 731ms2026-09-14 UTC: p95 390ms2026-09-15 UTC: p95 405ms2026-09-16 UTC: p95 560ms2026-09-17 UTC: p95 666ms2026-09-18 UTC: p95 519ms2026-09-19 UTC: p95 578ms2026-09-20 UTC: p95 564ms2026-09-21 UTC: p95 553ms2026-09-22 UTC: p95 467ms2026-09-23 UTC: p95 458ms2026-09-24 UTC: p95 426ms2026-09-25 UTC: p95 502ms2026-09-26 UTC: p95 371ms2026-09-27 UTC: p95 343ms2026-09-28 UTC: p95 348ms2026-09-29 UTC: p95 401ms2026-09-30 UTC: p95 432ms2026-10-01 UTC: p95 286ms2026-10-02 UTC: p95 314ms2026-10-03 UTC: p95 549ms2026-10-04 UTC: p95 333ms2026-10-05 UTC: p95 446ms
Sep 6Sep 20Oct 5
Canada
715msp95 · latest
1s500ms0ms
Canada response time (p95) over the last 30 daysDaily 95th-percentile response time for Canada, scaled to a maximum of 1s. Days with no samples are not plotted, not shown as zero.2026-09-06 UTC: p95 633ms2026-09-07 UTC: p95 529ms2026-09-08 UTC: p95 537ms2026-09-09 UTC: p95 547ms2026-09-10 UTC: p95 476ms2026-09-11 UTC: p95 331ms2026-09-12 UTC: p95 342ms2026-09-13 UTC: p95 386ms2026-09-14 UTC: p95 488ms2026-09-15 UTC: p95 438ms2026-09-16 UTC: p95 406ms2026-09-17 UTC: p95 395ms2026-09-18 UTC: p95 382ms2026-09-19 UTC: p95 390ms2026-09-20 UTC: p95 380ms2026-09-21 UTC: p95 377ms2026-09-22 UTC: p95 426ms2026-09-23 UTC: p95 478ms2026-09-24 UTC: p95 485ms2026-09-25 UTC: p95 461ms2026-09-26 UTC: p95 744ms2026-09-27 UTC: p95 535ms2026-09-28 UTC: p95 611ms2026-09-29 UTC: p95 511ms2026-09-30 UTC: p95 408ms2026-10-01 UTC: p95 517ms2026-10-02 UTC: p95 432ms2026-10-03 UTC: p95 482ms2026-10-04 UTC: p95 486ms2026-10-05 UTC: p95 715ms
Sep 6Sep 20Oct 5
UK
301msp95 · latest
500ms250ms0ms
UK response time (p95) over the last 30 daysDaily 95th-percentile response time for UK, scaled to a maximum of 500ms. Days with no samples are not plotted, not shown as zero.2026-09-06 UTC: p95 319ms2026-09-07 UTC: p95 232ms2026-09-08 UTC: p95 199ms2026-09-09 UTC: p95 292ms2026-09-10 UTC: p95 336ms2026-09-11 UTC: p95 306ms2026-09-12 UTC: p95 292ms2026-09-13 UTC: p95 245ms2026-09-14 UTC: p95 230ms2026-09-15 UTC: p95 225ms2026-09-16 UTC: p95 249ms2026-09-17 UTC: p95 235ms2026-09-18 UTC: p95 271ms2026-09-19 UTC: p95 329ms2026-09-20 UTC: p95 347ms2026-09-21 UTC: p95 407ms2026-09-22 UTC: p95 456ms2026-09-23 UTC: p95 433ms2026-09-24 UTC: p95 390ms2026-09-25 UTC: p95 410ms2026-09-26 UTC: p95 499ms2026-09-27 UTC: p95 356ms2026-09-28 UTC: p95 485ms2026-09-29 UTC: p95 380ms2026-09-30 UTC: p95 364ms2026-10-01 UTC: p95 413ms2026-10-02 UTC: p95 346ms2026-10-03 UTC: p95 308ms2026-10-04 UTC: p95 303ms2026-10-05 UTC: p95 301ms
Sep 6Sep 20Oct 5
Southeast Asia
591msp95 · latest
2s1s0ms
Southeast Asia response time (p95) over the last 30 daysDaily 95th-percentile response time for Southeast Asia, scaled to a maximum of 2s. Days with no samples are not plotted, not shown as zero.2026-09-06 UTC: p95 1.1s2026-09-07 UTC: p95 999ms2026-09-08 UTC: p95 766ms2026-09-09 UTC: p95 687ms2026-09-10 UTC: p95 911ms2026-09-11 UTC: p95 1s2026-09-12 UTC: p95 891ms2026-09-13 UTC: p95 859ms2026-09-14 UTC: p95 824ms2026-09-15 UTC: p95 846ms2026-09-16 UTC: p95 1.0s2026-09-17 UTC: p95 1.0s2026-09-18 UTC: p95 1.1s2026-09-19 UTC: p95 1.3s2026-09-20 UTC: p95 1.3s2026-09-21 UTC: p95 1.3s2026-09-22 UTC: p95 1.3s2026-09-23 UTC: p95 937ms2026-09-24 UTC: p95 830ms2026-09-25 UTC: p95 1.1s2026-09-26 UTC: p95 982ms2026-09-27 UTC: p95 1.3s2026-09-28 UTC: p95 1.0s2026-09-29 UTC: p95 942ms2026-09-30 UTC: p95 859ms2026-10-01 UTC: p95 794ms2026-10-02 UTC: p95 788ms2026-10-03 UTC: p95 625ms2026-10-04 UTC: p95 781ms2026-10-05 UTC: p95 591ms
Sep 6Sep 20Oct 5
Australia
676msp95 · latest
2s1s0ms
Australia response time (p95) over the last 30 daysDaily 95th-percentile response time for Australia, scaled to a maximum of 2s. Days with no samples are not plotted, not shown as zero.2026-09-06 UTC: p95 661ms2026-09-07 UTC: p95 694ms2026-09-08 UTC: p95 615ms2026-09-09 UTC: p95 695ms2026-09-10 UTC: p95 664ms2026-09-11 UTC: p95 689ms2026-09-12 UTC: p95 582ms2026-09-13 UTC: p95 582ms2026-09-14 UTC: p95 552ms2026-09-15 UTC: p95 567ms2026-09-16 UTC: p95 614ms2026-09-17 UTC: p95 649ms2026-09-18 UTC: p95 564ms2026-09-19 UTC: p95 938ms2026-09-20 UTC: p95 717ms2026-09-21 UTC: p95 975ms2026-09-22 UTC: p95 551ms2026-09-23 UTC: p95 644ms2026-09-24 UTC: p95 583ms2026-09-25 UTC: p95 634ms2026-09-26 UTC: p95 1.2s2026-09-27 UTC: p95 480ms2026-09-28 UTC: p95 1.1s2026-09-29 UTC: p95 932ms2026-09-30 UTC: p95 1.1s2026-10-01 UTC: p95 746ms2026-10-02 UTC: p95 794ms2026-10-03 UTC: p95 784ms2026-10-04 UTC: p95 613ms2026-10-05 UTC: p95 676ms
Sep 6Sep 20Oct 5
South America
660msp95 · latest
1s500ms0ms
South America response time (p95) over the last 30 daysDaily 95th-percentile response time for South America, scaled to a maximum of 1s. Days with no samples are not plotted, not shown as zero.2026-09-06 UTC: p95 772ms2026-09-07 UTC: p95 652ms2026-09-08 UTC: p95 725ms2026-09-09 UTC: p95 729ms2026-09-10 UTC: p95 789ms2026-09-11 UTC: p95 658ms2026-09-12 UTC: p95 704ms2026-09-13 UTC: p95 661ms2026-09-14 UTC: p95 662ms2026-09-15 UTC: p95 688ms2026-09-16 UTC: p95 918ms2026-09-17 UTC: p95 944ms2026-09-18 UTC: p95 531ms2026-09-19 UTC: p95 526ms2026-09-20 UTC: p95 716ms2026-09-21 UTC: p95 810ms2026-09-22 UTC: p95 843ms2026-09-23 UTC: p95 670ms2026-09-24 UTC: p95 661ms2026-09-25 UTC: p95 732ms2026-09-26 UTC: p95 621ms2026-09-27 UTC: p95 702ms2026-09-28 UTC: p95 796ms2026-09-29 UTC: p95 716ms2026-09-30 UTC: p95 730ms2026-10-01 UTC: p95 645ms2026-10-02 UTC: p95 582ms2026-10-03 UTC: p95 884ms2026-10-04 UTC: p95 786ms2026-10-05 UTC: p95 660ms
Sep 6Sep 20Oct 5

Is it Anthropic, or is it you?

Watching an outage above does not tell you whether your own connection or site is also having a problem. Enter your own URL for one live check, right now, no signup. This checks the site you enter, not Anthropic -- it cannot diagnose Anthropic's own systems.

What we measured, function by function

Anthropic answers on more than one surface, and they can fail apart. Each row is one surface, checked from the same regions. The verdict above follows the auth row, because that is the surface we treat as this service's own; a failure on any other row is a partial outage, not a full one.

  • WebUS-East: OperationalUS-West: OperationalEurope: OperationalAsia-Pacific: OperationalUS-Central: OperationalCanada: OperationalUK: OperationalSoutheast Asia: OperationalAustralia: OperationalSouth America: Operational
  • APIUS-East: OperationalUS-West: OperationalEurope: OperationalAsia-Pacific: OperationalUS-Central: OperationalCanada: OperationalUK: OperationalSoutheast Asia: OperationalAustralia: OperationalSouth America: Operational
  • AuthprimaryUS-East: OperationalUS-West: OperationalEurope: OperationalAsia-Pacific: OperationalUS-Central: OperationalCanada: OperationalUK: OperationalSoutheast Asia: OperationalAustralia: OperationalSouth America: Operational

Get an email when we see Anthropic go down, and when it is back

Get told when we measure this

We will tell you when our probes stop reaching Anthropic, and again when they can reach it again. That is our own measurement from ten regions, not Anthropic's status page. No account, no card.

Delivery channel

Double opt-in: nothing is sent until you click the link in the confirmation email. One email when a measured outage opens, one when it closes, and a one-click unsubscribe in every one. We do not send anything else to this address.

What are you seeing? (optional)

No account needed, and we never store your IP address. Reports are counted separately from our own measurements and are always shown as unverified.

What we measured, and what people reported

  • North America
    OperationalUS-East, US-West, US-Central, Canada
    • US-East
      Operationallatency: 222msstatus code: 401checked: Oct 5, 2026, 8:18 PM UTC
      0 people in the last 5 minutesNot enough reports to sayOur US-East probes reach Anthropic normally. We do not have enough reports from US-East to say anything about what people there are seeing.
    • US-West
      Operationallatency: 192msstatus code: 401checked: Oct 5, 2026, 8:18 PM UTC
      0 people in the last 5 minutesNot enough reports to sayOur US-West probes reach Anthropic normally. We do not have enough reports from US-West to say anything about what people there are seeing.
    • US-Central
      Operationallatency: 214msstatus code: 401checked: Oct 5, 2026, 8:17 PM UTC
      0 people in the last 5 minutesNot enough reports to sayOur US-Central probes reach Anthropic normally. We do not have enough reports from US-Central to say anything about what people there are seeing.
    • Canada
      Operationallatency: 123msstatus code: 401checked: Oct 5, 2026, 8:18 PM UTC
      0 people in the last 5 minutesNot enough reports to sayOur Canada probes reach Anthropic normally. We do not have enough reports from Canada to say anything about what people there are seeing.
  • South America
    Operationallatency: 200msstatus code: 401checked: Oct 5, 2026, 8:17 PM UTC
    0 people in the last 5 minutesNot enough reports to sayOur South America probes reach Anthropic normally. We do not have enough reports from South America to say anything about what people there are seeing.
  • Europe
    OperationalEurope, UK
    • Europe
      Operationallatency: 143msstatus code: 401checked: Oct 5, 2026, 8:18 PM UTC
      0 people in the last 5 minutesNot enough reports to sayOur Europe probes reach Anthropic normally. We do not have enough reports from Europe to say anything about what people there are seeing.
    • UK
      Operationallatency: 149msstatus code: 401checked: Oct 5, 2026, 8:18 PM UTC
      0 people in the last 5 minutesNot enough reports to sayOur UK probes reach Anthropic normally. We do not have enough reports from UK to say anything about what people there are seeing.
  • Asia Pacific
    OperationalAsia-Pacific, Southeast Asia, Australia
    • Asia-Pacific
      Operationallatency: 193msstatus code: 401checked: Oct 5, 2026, 8:17 PM UTC
      0 people in the last 5 minutesNot enough reports to sayOur Asia-Pacific probes reach Anthropic normally. We do not have enough reports from Asia-Pacific to say anything about what people there are seeing.
    • Southeast Asia
      Operationallatency: 255msstatus code: 401checked: Oct 5, 2026, 8:17 PM UTC
      0 people in the last 5 minutesNot enough reports to sayOur Southeast Asia probes reach Anthropic normally. We do not have enough reports from Southeast Asia to say anything about what people there are seeing.
    • Australia
      Operationallatency: 560msstatus code: 401checked: Oct 5, 2026, 8:15 PM UTC
      0 people in the last 5 minutesNot enough reports to sayOur Australia probes reach Anthropic normally. We do not have enough reports from Australia to say anything about what people there are seeing.

Somewhere else or not sure: 0 people in the last 5 minutes

These are unverified reports from people using Anthropic, counted separately from what our own probes measure. Anyone can file one, no account is needed, and the region on a report is chosen by the person filing it. We never open, extend or close an outage in our record based on report volume: only our own measurements do that. We started counting reports for Anthropic on August 28, 2026.

Recent outages

Elevated errors for Claude Mythos 5.1 and Claude Fable 5.1, 16mdeclared on their status page2026-10-05
Delayed credits on the Claude Platform, 6h 16mdeclared on their status page2026-10-01
Elevated errors on claude.ai, Claude Code, Claude Cowork and the Claude API, 2h 6mdeclared on their status page2026-09-29
Elevated errors for multiple models, 1h 38mdeclared on their status page2026-09-22
Issues with Google Play subscriptions, 33mdeclared on their status page2026-09-16
Intermittent error spikes for Claude Mythos 5.1 and Claude Fable 5.1, 1h 26mdeclared on their status page2026-09-15
Elevated errors for Claude Mythos 5.1 and Claude Fable 5.1, 17mdeclared on their status page2026-09-11
Elevated latency on the Claude API for some users, 1h 41mdeclared on their status page2026-09-10

measured entries are our own probes' readings; declared entries are the vendor's. How this check works

We have been measuring Anthropic since August 20, 2026. We show nothing from before that date, and we never add an outage we did not observe ourselves, from any source.

Need this in writing? Generate an SLA evidence report for Anthropic covering any window you pick, with our measurements and Anthropic's own claim at the time, side by side.

Full availability history for Anthropic: 90-day availability by region, month-by-month uptime, and every incident on record.

Monitor your own site the same way

This page shows what we see when we check this service, using the same ten regions, for a site you run. RealUptime Monitor watches your own servers from inside your network, and it starts free.

Start monitoring your own servers

Put this badge in your README

Anthropic uptime measured by RealUptimeLive, from this page's own readings.
[![Anthropic uptime measured by RealUptime](https://realuptime.io/outages/anthropic/badge.svg?days=30)](https://realuptime.io/outages/anthropic)
<a href="https://realuptime.io/outages/anthropic"><img src="https://realuptime.io/outages/anthropic/badge.svg?days=30" alt="Anthropic uptime measured by RealUptime"></a>

The badge shows the share of our probes that succeeded over the last 30 days, and the window is printed on it so the number always says what period it covers. If our readings go stale it says stale, and if we have no readings it says so: it will not show green on data we cannot vouch for. Free, no account, and it links back here. See how the badge works for every window and the honesty rules behind it.

What Anthropic's SLA implies, from our measurement

At or above your target

We measured none of downtime for Anthropic over the last 30 days, which is 100% uptime by our reading. A 99.9% target allows 43 minutes over that period.

By our measurement there is no shortfall to claim for this period.

This is computed from our own probe measurements, not from Anthropic's SLA instrumentation. Their contract is normally measured against their own systems, with their own exclusions and a claim window, so their figure and ours will differ. Use this to start the conversation and ask for their number. It is not legal advice and it is not a determination of what you are owed.

Per-model status

No vendor publishes per-model status, so this is the closest thing available: a real, credentialed completion call to each model below, on our own schedule. A rejected credential of ours never renders as a Anthropic outage here -- see “Awaiting data” below.
claude-haiku-4-5Operational
Europe · 555ms · last verified completion Oct 5, 2026, 8:18 PM UTC
claude-haiku-4-5Operational
South America · 622ms · last verified completion Oct 5, 2026, 8:17 PM UTC
claude-haiku-4-5Operational
US-East · 725ms · last verified completion Oct 5, 2026, 8:18 PM UTC
claude-haiku-4-5Operational
UK · 600ms · last verified completion Oct 5, 2026, 8:18 PM UTC
claude-haiku-4-5Operational
Asia-Pacific · 1193ms · last verified completion Oct 5, 2026, 8:18 PM UTC
claude-haiku-4-5Operational
US-Central · 491ms · last verified completion Oct 5, 2026, 8:17 PM UTC
claude-haiku-4-5Operational
Southeast Asia · 659ms · last verified completion Oct 5, 2026, 8:17 PM UTC
claude-haiku-4-5Operational
US-West · 989ms · last verified completion Oct 5, 2026, 8:18 PM UTC
claude-haiku-4-5Operational
Australia · 949ms · last verified completion Oct 5, 2026, 8:15 PM UTC
claude-haiku-4-5Operational
Canada · 441ms · last verified completion Oct 5, 2026, 8:18 PM UTC

What we check

primaryfunctional: auth surface
https://api.anthropic.com/v1/models
secondary
https://platform.claude.com/
secondaryfunctional: live API
https://api.anthropic.com/v1/messages
RealUptime is not affiliated with Anthropic; the name identifies what we measured, and nothing here speaks for Anthropic's own team. We send a single web request to Anthropic from 10 regions on our own schedule and time the response. We do not see inside Anthropic's systems, do not use an account or real transaction, and are not the same signal Anthropic's own team has access to. Treat this as one external data point, not a verdict. At least one endpoint we check for Anthropic is a real functional API call (marked “functional” above), not just a landing page, so a clean read there is a stronger signal than reachability alone, though it still does not cover every feature of the service. Read the full methodology.