Is Command down? Cohere status right now
Last 24 hours
API response time (24h)
Command reliability, last 50 days
Over the last 50 days ModelBank measured 100% uptime for Command (100% over the last 30 days); no check failed. In the same period the official status page posted 1 incidents (0 in the last 30 days), 0 of them major or critical; the median time from posting to resolution was about 4.4 h. The most recent official incident was “Multiple Endpoint Disruptions” on 2026-09-01, which lasted 4.4 h. The current status has held since 16d ago.
Model availability on Command
7 models · all healthySuccess rate of real API traffic routed to this platform (not our probe), refreshed every 10 minutes.
| Model | Daily success | 24 h | 30 min | |
|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 100% | 100% | ||
| Command A+ | 100% | 100% | ||
| MiMo-V2.6-Flash | 99.7% | 100% | ||
| DeepSeek V4.1 Flash | 100% | 100% | ||
| GLM 5.3 Flash | 98% | 100% | ||
| DeepSeek V4 Flash 0731 | 99.9% | 100% | ||
| Command A | 100% | — |
Each daily bar is the average success rate of that day: green ≥ 99.5 %, yellow ≥ 97 %, orange ≥ 90 %, red < 90 %, grey = no data (collected since v12).
90-day uptime history
Incident history Outage calendar →
Multiple Endpoint Disruptions
Documentation Content Loading Issues
Dashboard Login Service Disruption
/audio/transcriptions endpoint returns error for audio files with unexpected sampling rate
Docs Platform Degraded Performance
Multiple Model Disruptions
Scheduled DB Maintenance: Model authentication and API access momentarily affected
Some chat models are unresponsive or timing out
Chat models return 503 service error when /v1/chat requests omit message and chat_history while providing tool_results
logprobs param degeraded for `command-a-03-2025` and `command-a-reasoning-08-2025`
Command-a-vision-07-2025 degraded performance
Model serving infrastructure outage
GCP Outage
Degraded service affecting embed-v4.0
Degraded service affecting embedding models
Degraded Performance - Increased Latency - Command-a-03-2025/command-r-plus-08-2024
Degraded Performance: command-a-03-2025 - Increased Latency
High latency
Increased Latency
Increased Latency
Elevated Latency
CommandR / CommandR plus: Elevated Error Rate
Rerank Endpoint: Degraded Service
Chat Endpoint: Encountering Increased Error rate
Team has implementing a workaround to restore access to impacted accounts
FAQ
Is Command down?
No, Command is up and working normally. ModelBank checks Cohere every 2 minutes from our global monitoring network and also reads the official status page. Last check: 2m ago.
What is Command’s uptime?
Measured by ModelBank: 100% in the last 24 hours, 100% over 30 days and 100% over 90 days.
What should I do if Command is not working?
First check this page and the official status page. If Command is up for everyone else, try clearing cache, logging out and in, switching network, or checking your API key and rate limits (HTTP 429). If it is a real outage, switch to an alternative model — see the alternatives on this page — or use a router with automatic failover.
Get notified when Command goes down
We’ll notify you the moment ModelBank detects a Command outage, and again when it recovers.
Email · Browser push · Slack / Discord · Feishu / DingTalk / WeCom · RSS — free, no sign-up