Service Degradation for GLM 5.3
DegradedWe've resolved the incident and the affected service is now operational.
Is Fireworks AI down?
Fireworks AI is up and running. Fireworks AI hosts fast inference APIs for open-weight models.
Last 90 days
99.60%
Estimated uptime
Estimated uptime
90 days agoToday
Worked out from the incidents Fireworks AI reported, so it is an estimate and not a measurement.
Fireworks AI reliability, last 90 days
24Incidents reported
0Full outages
21 minTypical duration
3 h 5 minLongest incident
Last incident: “Service Degradation for GLM 5.3”, today.
Components
MiniMax M3.1 FlashOperational
DeepSeek V4.1 Flash 1017Operational
DeepSeek V4.1 Flash 1017 USOperational
Muse Spark Open USOperational
GLM 5.3 FlashOperational
GLM 5.3 Flash USOperational
GLM 5.3 Operational
GLM 5.3 FastOperational
GLM 5.3 USOperational
Ember-1Operational
Kimi K3 USOperational
Kimi K3 FastOperational
Kimi K3Operational
Qwen 3.8 MaxOperational
Deepseek V4.1 FlashOperational
Deepseek V4.1 Flash USOperational
Nemotron 3 Ultra USOperational
Nemotron 3.5 Lightning USOperational
Minimax M3 USOperational
MiniMax M3Operational
InklingOperational
GPT-OSS 120BOperational
Recent incidents
Service Degradation for DeepSeek V4.1 Flash 1017
DegradedWe've resolved the incident and the affected service is now operational.
Service Degradation for DeepSeek V4.1 Flash 1017
DegradedWe've resolved the incident and the affected service is now operational.
Service Degradation for DeepSeek V4.1 Flash 1017
DegradedWe've resolved the incident and the affected service is now operational.
Service Degradation for Deepseek V4.1 Flash
DegradedWe've resolved the incident and the affected service is now operational.
Questions
Is Fireworks AI down right now?
Fireworks AI’s official status page says: All Systems Operational. This page checks it again when you load it, at most every 5 minutes.
When was Fireworks AI last down?
The most recent incident Fireworks AI reported was “Service Degradation for GLM 5.3”, today (2026-10-23 13:33 UTC). None of its incidents in the last 90 days were a full outage.
Which parts of Fireworks AI are tracked here?
Fireworks AI reports 22 components on its status page, including MiniMax M3.1 Flash, DeepSeek V4.1 Flash 1017, DeepSeek V4.1 Flash 1017 US, Muse Spark Open US, GLM 5.3 Flash. Each is checked again whenever this page refreshes.
What should I do if Fireworks AI is down?
Retry with exponential backoff, fall back to another model or provider if your product allows it, and avoid hammering the API while it recovers.
One Fireworks model is slow — are the others affected?
Usually not — the status page tracks individual model deployments (GLM, Kimi, Deepseek, GPT-OSS and so on) as separate components. Check whether your model's row is the degraded one.
A degraded model on Fireworks — what's the quickest fallback?
The same OpenAI-compatible endpoint serves every hosted model — switching the model name to a healthy sibling model on Fireworks is usually faster than moving providers mid-incident.
How do I tell if Fireworks AI is down for everyone or only for me?
If the status above is operational but Fireworks AI still fails for you, the cause is probably on your side: try another network, clear the cache, or check your own connection. If it shows a degradation or an outage, others are affected too.
How can I get alerted when my own site goes down?
OpenUptime checks your site every minute and sends an alert to Slack, Telegram, email or a webhook the moment it stops responding. It is open source and free to start.