KovAPIKovAPI
AnnouncementsAll updates →
NoticeNezhaGate is now KovAPI — new address kovapi.com NoticeCompensation for recent video generation failures NewSeedance 2.0 Mini is back and 2.0 Fast adds 480P, at a launch price
简体中文English ✓Español한국어日本語Русский
Log in Get API Key
Status

Service status

Live status of every model, a daily record for the last 90 days, and the incident history. Every figure comes from real customer requests; internal tests are excluded.

5 models affected

The other 37 models are operating normally.


Refreshes every minute

All services

Customer request success rate
99.2%Last 24 hours
97.4%Last 90 days
90 days ago30 days agoToday
OperationalDegradedOutageMaintenanceNo data

Trends

Daily success rate

Per customer request · UTC days

Latency

Streaming requests, from sending to the first token (thinking included)

Medianp90

Models 90-day success rate

Chat models

DeepSeek V4 Flash 0731
Outagemost requests failing
99.5%
Gemini 3.1 Pro
MaintenanceTemporarily suspended. The model listing and documentation are retained; reopening plans will be announced separately
99.7%
GLM-5.3
99.8%
GPT-5.6 Luna
97.3%
GPT-5.6 Sol
98.5%
GPT-6 Astra
96.8%
GPT-6 Luna
97.9%
GPT-6 Sol
95.2%
GPT-6.1 Sol
93.8%
Grok 4.7
89.0%

Image models

GPT Image 2
99.1%

Video models

Grok Imagine Video 1.5
Maintenanceunder maintenance; we will announce when it is back
57.2%
MiniMax H3
91.4%
Seedance 2.0
64.4%
Seedance 2.0 · Clip
Maintenanceunder maintenance; we will announce when it is back
Seedance 2.5
78.8%
Seedance 2.5 · Special
Maintenanceunder maintenance; we will announce when it is back
46.8%
Wan 3.0
60.9%

Incident history

Outage

DeepSeek V4 Flash 0731: most requests failing

Ongoing
– Ongoing · ongoing for 1 h 51 min · Detected automatically

Failed requests rose noticeably; failed requests are not billed.

Maintenance

Seedance 2.5 · Special: Maintenance

Ongoing
– Ongoing · ongoing for 12 h 59 min

under maintenance; we will announce when it is back During maintenance the API answers “temporarily unavailable” right away; nothing is billed and no other model answers in its place.

Maintenance

kling-4.0: Maintenance

Ongoing
– Ongoing · ongoing for 12 h 59 min

under maintenance; we will announce when it is back During maintenance the API answers “temporarily unavailable” right away; nothing is billed and no other model answers in its place.

Maintenance

Grok Imagine Video 1.5: Maintenance

Ongoing
– Ongoing · ongoing for 12 h 59 min

under maintenance; we will announce when it is back During maintenance the API answers “temporarily unavailable” right away; nothing is billed and no other model answers in its place.

Maintenance

Gemini 3.1 Pro: Maintenance

Ongoing
– Ongoing · ongoing for 9 d 14 h

Temporarily suspended. The model listing and documentation are retained; reopening plans will be announced separately During maintenance the API answers “temporarily unavailable” right away; nothing is billed and no other model answers in its place.

Maintenance

Seedance 2.0 · Clip: Maintenance

Ongoing
– Ongoing · ongoing for 21 d 10 h

under maintenance; we will announce when it is back During maintenance the API answers “temporarily unavailable” right away; nothing is billed and no other model answers in its place.

Outage

GPT-6 Luna: most requests failing

– · lasted 1 min · Detected automatically

Failed requests rose noticeably; failed requests are not billed.

Degraded

Claude Sonnet 4.6: first token noticeably slower

– · lasted 35 min · Detected automatically

Response times ran well above this model's previous 7 days.

Outage

Grok 4.7: most requests failing

– · lasted 1 min · Detected automatically

Failed requests rose noticeably; failed requests are not billed.

Outage

Grok Imagine Image: most requests failing

– · lasted 1 h 48 min · Detected automatically

Failed requests rose noticeably; failed requests are not billed. Success rate during the incident: 0%.

Outage

Grok Imagine Image Quality: most requests failing

– · lasted 39 min · Detected automatically

Failed requests rose noticeably; failed requests are not billed. Success rate during the incident: 50.8%.

Outage

Grok 4.7: most requests failing

– · lasted 1 h 37 min · Detected automatically

Failed requests rose noticeably; failed requests are not billed.

How this page is measured

Success rate: each customer request counts once, and a request that succeeds after an automatic retry or is answered by another model counts as a success. Not counted: client-side errors (bad parameters, auth, balance and other 4xx), requests refused upstream for their content, requests still in flight, internal tests and banned accounts. A figure appears only once the sample is large enough, and it is truncated, never rounded up.

Degraded: within one hour, at least 3 failed requests and a success rate below 90% (video: 70%); or at least 3 requests with more than half answered by another model; or first-token or generation times well above the model's previous 7 days. Outage: within one hour, at least 3 failed requests and a success rate below 50%, or the model temporarily unavailable altogether. Maintenance: set by us. An incident ends once the model answers on its own again; with no new requests at all, a failure incident ends after 24 hours and an incident of answers from another model after at most 7 days.

Daily bars use UTC days; incident times are shown in your local time zone. The page refreshes every minute.

API endpoint availability 98.11% (last 30 days): the public health-check endpoint is probed every 2 minutes. It shows whether the endpoint is reachable, not whether models answer.

Machine-readable: /status.json · /health