Tickerr / Status / Fireworks AI
Is Fireworks AI down right now?
HTTP endpoint monitoring - checked every 5 minutes · How we classify outages
Weekly AI pricing & uptime digest
Price drops, new model releases, and incident summaries - every Monday. Free.
Fireworks AI is currently operational - 554ms HTTP response. Last checked . 90-day uptime: 99.9%.
Stay informed
Follow @tickerr_ai
We post when tier 1 LLM APIs go down - before the official status page updates.
Follow on X →Or get the weekly reliability digest:
Add a status badge
Show live Fireworks AI status on your site, README, or docs.
90-day uptime
99.9%
20 incidents (90d)
Response now
554ms
HTTP p50 (7d)
855ms
median ping response
HTTP p95 (7d)
2158ms
tail ping response
Response time (7 days)
p50 855ms·p95 2158msⓘ HTTP response times from Tickerr's monitoring server to Fireworks AI's status or homepage endpoint - not API inference latency or time-to-first-token (TTFT). For API benchmark data, see third-party sources like Artificial Analysis.
90-day uptime
Incident history
Status: Resolved We've resolved the incident and the affected service is now operational.
Status: Investigating We are seeing impacted performance for Kimi K3 US. We are actively investigating. Affected components Kimi K3 US (Degraded performance)
Status: Monitoring A GCP key for the Service Account inference@fw-ai-cp-prod had to be disabled for security reasons. Consumers and users of the key need to rotate to the new key to mitigate the issue…
Status: Investigating We are seeing impacted performance for Qwen 3.8 Max. We are actively investigating. Affected components Qwen 3.8 Max (Degraded performance)
Status: Investigating We are seeing impacted performance for one of our Serverless models. We are actively investigating.
Status: Investigating We are seeing impacted performance for Kimi K2.6. We are actively investigating. Affected components Kimi K2.6 (Degraded performance)
Status: Resolved We've resolved the incident and the affected service is now operational.
Status: Resolved We've resolved the incident and the affected service is now operational.
Status: Resolved We've resolved the incident and the affected service is now operational.
Status: Investigating We are seeing impacted performance for one of our Serverless models. We are actively investigating.
Status: Investigating We are seeing impacted performance for one of our Serverless models. We are actively investigating.
Status: Investigating We are seeing impacted performance for one of our Serverless models. We are actively investigating.
Status: Resolved We've resolved the incident and the affected service is now operational.
Status: Investigating We are seeing impacted performance for Minimax M2.7. We are actively investigating. Affected components MiniMax M2.7 (Degraded performance)
Status: Resolved We've resolved the incident and the affected service is now operational.
Status: Resolved We've resolved the incident and the affected service is now operational.
Status: Resolved We've resolved the incident and the affected service is now operational.
Status: Investigating We are seeing impacted performance for one of our Serverless models. We are actively investigating.
Status: Investigating We are seeing impacted performance for one of our Serverless models. We are actively investigating.
Status: Investigating We are seeing impacted performance for one of our Serverless models. We are actively investigating.
Related pages
About Fireworks AI status
Fireworks AI is a fast inference platform for open-source models with a focus on latency and throughput. When Fireworks AI is down, API calls to hosted models fail. Fireworks AI is used by developers who need fast, cost-effective inference for Llama, Mistral, and other models.
You can also check the official Fireworks AI status page.