tickerr

Tickerr / Status / Claude

Claude

Is Claude down right now?

Authenticated API inference — 4 models monitored

Claude is currently operational — 43ms HTTP response. Last checked . 90-day uptime: 100%. Claude API: all 4 models responding — fastest TTFT 531ms.

Operational43ms response
Official: All Systems Operational

HTTP uptime (90d)

100%

20 incidents (90d)

HTTP response now

43ms

HTTP p50 (7d)

140ms

median ping response

HTTP p95 (7d)

263ms

tail ping response

Claude API Status

Live · every 5 min

Best TTFT (p50)

531ms

time to first token

Best throughput

79tok/s

output tokens/sec (24h avg)

Min success rate

100%

worst model (24h)

ModelStatusTTFT nowp50 TTFTp95 TTFT24h uptime
Haiku 4.5288 checks
946ms
531ms
1477ms
100%
Sonnet 4.6288 checks
2745ms
1022ms
2584ms
100%
Opus 4.796 checks
1208ms
1060ms
2422ms
100%
Opus 4.696 checks
1482ms
1487ms
2339ms
100%

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

Apr 20 11:50 AMNow

ⓘ 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.

HTTP endpoint response time (7 days)

p50 140ms·p95 263ms
Apr 14min 41ms · max 3235ms · median 140msNow

HTTP response times to Claude's status endpoint — measures infrastructure availability, not API inference speed. For TTFT and model-level API status, see the Claude API Status section above.

30-day uptime

Apr 26 100%
Mar 23Today
100%99–99.9%95–99%<95%
Checked every 5 min · 30 days · Outage = failed ping · Major outage = ≥15% of daily checks failed

90-day uptime comparison

100%
Independent by Tickerr
Jan 22Today
100%99–99.9%95–99%<95%
Official self-reportedstatus.anthropic.com
Jan 22Today
OperationalDegradedPartial OutageMajor Outage
Independent monitoring vs status.anthropic.com self-reported — 90 days

Independent monitoring catches issues faster — official pages sometimes lag by hours before acknowledging problems.

Service components

via status.anthropic.com
All Systems Operationalself-reported by Claude
claude.aiOperational
platform.claude.com (formerly console.anthropic.com)Operational
Claude API (api.anthropic.com)Operational
Claude CodeOperational
Claude CoworkOperational
Claude for GovernmentOperational

Incident history

DegradedResolvedOfficial
Apr 20, 2026
01:31 PM UTC
Elevated errors for uploading files

This incident has been resolved.

50m
Major OutageResolvedOfficial
Apr 20, 2026
06:14 AM UTC
Claude Sonnet 4.5 error spike

This incident has been resolved.

1h 11m
Partial OutageResolvedOfficial
Apr 19, 2026
10:44 PM UTC
Elevated errors on Opus 4.6

This incident has been resolved.

1h 15m
DegradedResolvedOfficial
Apr 17, 2026
06:59 PM UTC
Errors uploading documents to Google Drive in Claude.ai

The issue affecting uploads to Google Drive has been resolved.

56m
DegradedResolvedOfficial
Apr 16, 2026
10:26 PM UTC
Failures to add Credentials to Vaults

This incident has been resolved.

15m
Major OutageResolvedOfficial
Apr 16, 2026
07:24 PM UTC
Claude Cowork not starting for some users

This incident has been resolved in the v1.3109.0 release of Claude Desktop. Please "Check for Updates".

2h 4m
DegradedResolvedOfficial
Apr 16, 2026
06:50 AM UTC
Opus 4.6 elevated rate of errors

Earlier today we had an outage on Opus 4.6 that started at 23:03 PT / 6:03 UTC and ended at 00:26 PT / 7:26 UTC.

52m
Major OutageResolvedOfficial
Apr 15, 2026
02:53 PM UTC
Elevated errors on Claude.ai, API, Claude Code

This incident has been resolved.

2h 49m
DegradedResolvedOfficial
Apr 14, 2026
09:24 AM UTC
Degraded service on usage and analytics admin API endpoints

This incident has been resolved.

5h 56m
Major OutageResolvedOfficial
Apr 13, 2026
03:40 PM UTC
Claude.ai down

We have resolved the issue resulting in elevated errors on login for Claude.ai and Claude Code betwen 15:31 to 16:19 UTC.

55m
Major OutageResolvedOfficial
Apr 11, 2026
12:00 AM UTC
Email login down

Email login was broken between approximately 3:46 PM and 4:52 PM PDT on April 10, 2026.

0m
DegradedResolvedOfficial
Apr 10, 2026
04:30 PM UTC
Elevated errors on requests to Claude models

The issue affecting requests to non-Opus models has been resolved.

21m
DegradedResolvedOfficial
Apr 10, 2026
02:00 PM UTC
Some Claude.ai share links were inaccessible

Between April 2 and April 10, some users who were not signed in to Claude.ai (web, mobile, desktop) were not able to access some Claude.ai sharing links.

0m
DegradedResolvedOfficial
Apr 10, 2026
04:28 AM UTC
Degraded Performance on Vaults

This incident has been resolved.

9m
DegradedResolvedOfficial
Apr 9, 2026
04:54 PM UTC
Elevated Connector Error Rates

This incident has been resolved.

39m
DegradedResolvedOfficial
Apr 9, 2026
08:07 AM UTC
Sonnet 4.6 elevated rate of errors

This incident has been resolved.

45m
Major OutageResolvedSynthetic probe
Apr 9, 2026
07:05 AM UTC

Service disruption detected

29m
Partial OutageResolvedOfficial
Apr 8, 2026
11:57 PM UTC
Errors when connecting to Claude.ai

Some users experienced an error when trying to access Claude.ai on desktop and the web from 23:22–23:50 UTC. This issue has now been resolved.

0m
Partial OutageResolvedOfficial
Apr 8, 2026
07:22 PM UTC
Outage affecting Workspace Creation

The issue affecting API workspace creation has been resolved. Impact occurred from approximately 4:15 PM to 7:30 PM UTC.

17m
DegradedResolvedOfficial
Apr 8, 2026
05:46 PM UTC
Elevated errors on Claude.ai, API, Claude Code

From 17:25–17:44 UTC, we saw elevated errors on attempts to log into Claude.ai (mobile, web, and desktop) and platform.claude.com, as well as /login attempts via Claude Code. This issue is now resolve…

3m

Related pages

Claude API not working? Common error codes

If Claude'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.

ErrorWhat it means & what to do
HTTP 429Rate limit hit — check your plan tier, add exponential backoff
HTTP 529 (overload_error)Anthropic is overloaded — retry after 30–60 seconds
HTTP 500 (api_error)Unexpected server error — retry once, then check this page
HTTP 503Service unavailable — check for active incidents below

Note: Tickerr monitors Claude'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 Claude status

Claude is Anthropic's AI assistant and API, available in Haiku, Sonnet, and Opus tiers. This page tracks two independent signals: HTTP availability (is Anthropic's infrastructure reachable?) and live API inference (is the Claude API actually working for developers?). Tickerr makes authenticated API calls to all six Claude models — claude-haiku-4-5, claude-haiku-3-5, claude-sonnet-4-6, claude-sonnet-4, claude-opus-4-6, and claude-opus-4 — every 5 minutes, measuring TTFT (time-to-first-token) and output throughput. This catches model-layer failures that don't show up as HTTP outages, covering roughly 35% of incidents. Common Claude API errors: HTTP 529 overloaded_error (Anthropic at capacity — retry after 30–60s), HTTP 429 rate_limit_error (you've hit plan limits — check the rate limits page), HTTP 500 api_error (unexpected server error — retry once). If the Claude API is not working or returning 529 overloaded responses, check the live status above — Tickerr typically detects these within 5 minutes. Claude API latency (TTFT) typically runs 300–800ms for Haiku models and 600ms–2s for Opus under normal load. Anthropic's official status page at status.anthropic.com is updated within 15–30 minutes of a confirmed incident; Tickerr's independent inference monitoring surfaces issues faster.

You can also check the official Claude status page.

Weekly AI pricing & uptime digest

Join developers tracking AI tool costs and uptime — every Monday.