← Back to the carnage
FIREWORKS
🟡 Fireworks' Kimi K3.1 Pro decided to become a ghost—completely offline while the team frantically checks if they remembered to pay the electricity bill. Full outage, zero responses, maximum chaos. The 'investigating' phase is tech-speak for 'we're refreshing our résumés right now.'. (Auto-resolved: no updates in 24h)
// The official story
Service Outage for Kimi K3.1 Pro
// Status page says
Status: Investigating We are actively investigating an outage for Kimi K3.1 Pro Affected components Kimi K3.1 Pro (Full outage)
🔗 Official status page (for the PR-approved version)
https://status.fireworks.ai//incidents/01M7RNRPWNZXWMBQBNRS4WXHTXFireworks's Greatest Hits
🟢 FIREWORKS
Oct 14, 2026
🟡 Turns out the 'server' in serverless was doing all the heavy lifting—now it's on vacation. Multiple models (Ember, Kimi, GLM, Inkling) are limping along while engineers pretend this wasn't completely avoidable. (Auto-resolved: no updates in 24h)
🟢 FIREWORKS
Aug 18, 2026
🟠 Kimi K3 is having a regional identity crisis—elevated errors and degraded availability spreading like a bad wifi signal. Engineers are investigating why one region apparently ghosted the network. The mitigation is happening, but 'investigating' means they're still reading the error logs like tea leaves. (Auto-resolved: no updates in 24h)
🟢 FIREWORKS
Aug 11, 2026
🟡 Your favorite open-source LLMs are playing dead across the board—GPT-OSS, DeepSeek, Kimi, GLM, the whole squad ghosted. Fireworks is investigating why their serverless infrastructure decided to go full Sleeping Beauty. Apparently 'partial outage' is code for 'we're as confused as you are'. (Auto-resolved: no updates in 24h)
🟢 FIREWORKS
Jul 31, 2026
⚪ Update: Qwen3 Embedding 8B embeddings API recovered