🟢 Is Fireworks AI Down?

No — Fireworks AI is operational

Last checked: 3m ago · Uptime: 99.51% · AIWatch Score: 72 (Fair)

Last incident: Oct 15, 08:09 UTC — Service Degradation for Qwen 3.8 Max (1h 17m)

Fireworks AI is ranked #26 of 36 AI services by AIWatch reliability score · Monthly Reports →

Get notified the next time Fireworks AI goes down.

Add to Slack

Can't install Slack apps?

Prefer Discord push alerts? Set up here →

Component Status
Serverless 19 components
Muse Spark Open US
GLM 5.3 Flash
GLM 5.3 Flash US
GLM 5.3
GLM 5.3 Fast
GLM 5.3 US
Ember-1
Kimi K3 US
Kimi K3 Fast
Kimi K3
Qwen 3.8 Max
Deepseek V4.1 Flash
Deepseek V4.1 Flash US
Nemotron 3 Ultra US
Nemotron 3.5 Lightning US
Minimax M3 US
MiniMax M3
Inkling
GPT-OSS 120B

Recent Incidents · Last 7 days

Service Degradation for Qwen 3.8 Max
Oct 15, 08:09 UTC · Resolved · 1h 17m · minor
Timeline · 2 updates
Investigating · Oct 15, 08:09 UTC
We are seeing impacted performance for Qwen 3.8 Max. We are actively investigating.
Resolved · Oct 15, 09:25 UTC
We've resolved the incident and the affected service is now operational.
Service Degradation for Kimi K3
Oct 15, 08:48 UTC · Resolved · 18m · minor
Timeline · 2 updates
Investigating · Oct 15, 08:48 UTC
We are seeing impacted performance for Kimi K3. We are actively investigating.
Resolved · Oct 15, 09:05 UTC
We've resolved the incident and the affected service is now operational.
Service Degradation for Kimi K3
Oct 15, 06:45 UTC · Resolved · 1h 21m · minor
Timeline · 2 updates
Investigating · Oct 15, 06:45 UTC
We are seeing impacted performance for Kimi K3. We are actively investigating.
Resolved · Oct 15, 08:05 UTC
We've resolved the incident and the affected service is now operational.
CSP outage affecting multiple serverless models
Oct 14, 23:06 UTC · Resolved · 2h 48m · minor
Timeline · 4 updates
Investigating · Oct 14, 23:06 UTC
We are experiencing a cloud service provider (CSP) outage affecting multiple serverless models. Requests to affected models may fail. We are investigating the impact.
Monitoring · Oct 14, 23:15 UTC
Error rates for affected serverless models are beginning to recover. We are monitoring the recovery; some requests may still fail.
Monitoring · Oct 15, 00:59 UTC
We are starting to see recovery across the board. We are continuing to actively monitor the situation.
Resolved · Oct 15, 01:53 UTC
Service has been restored for all affected serverless models. This incident is resolved.
Service Degradation for Deepseek V4.1 Flash
Oct 14, 22:33 UTC · Resolved · 14m · minor
Timeline · 2 updates
Investigating · Oct 14, 22:33 UTC
We are seeing impacted performance for Deepseek V4.1 Flash. We are actively investigating.
Resolved · Oct 14, 22:46 UTC
We've resolved the incident and the affected service is now operational.
Service Degradation for GLM 5.3 Fast
Oct 14, 21:24 UTC · Resolved · 3m · minor
Timeline · 2 updates
Investigating · Oct 14, 21:24 UTC
We are seeing impacted performance for GLM 5.3 Fast. We are actively investigating.
Resolved · Oct 14, 21:26 UTC
We've resolved the incident and the affected service is now operational.
Service Degradation for GLM 5.3
Oct 14, 01:26 UTC · Resolved · 4m · minor
Timeline · 2 updates
Investigating · Oct 14, 01:26 UTC
We are seeing impacted performance for GLM 5.3. We are actively investigating.
Resolved · Oct 14, 01:29 UTC
We've resolved the incident and the affected service is now operational.
Service Degradation for GLM 5.3
Oct 13, 09:37 UTC · Resolved · 4m · minor
Timeline · 2 updates
Investigating · Oct 13, 09:37 UTC
We are seeing impacted performance for GLM 5.3. We are actively investigating.
Resolved · Oct 13, 09:40 UTC
We've resolved the incident and the affected service is now operational.
Service Degradation for GLM 5.3
Oct 13, 05:09 UTC · Resolved · 2h 45m · minor
Timeline · 2 updates
Investigating · Oct 13, 05:09 UTC
We are seeing impacted performance for GLM 5.3. We are actively investigating.
Resolved · Oct 13, 07:54 UTC
We've resolved the incident and the affected service is now operational.
Service Degradation for GLM 5.3
Oct 12, 12:48 UTC · Resolved · 5h 19m · minor
Timeline · 3 updates
Investigating · Oct 12, 12:48 UTC
We are seeing impacted performance for GLM 5.3. We are actively investigating.
Monitoring · Oct 12, 15:01 UTC
We have implemented a fix for the performance degradation affecting GLM 5.3 and are monitoring the results.
Resolved · Oct 12, 18:06 UTC
We've resolved the incident and the affected service is now operational.
Service Degradation for GLM 5.3
Oct 12, 12:33 UTC · Resolved · 1m · minor
Timeline · 2 updates
Investigating · Oct 12, 12:33 UTC
We are seeing impacted performance for GLM 5.3. We are actively investigating.
Resolved · Oct 12, 12:33 UTC
We've resolved the incident and the affected service is now operational.
Service Degradation for Kimi K3
Oct 12, 11:39 UTC · Resolved · 2m · minor
Timeline · 2 updates
Investigating · Oct 12, 11:39 UTC
We are seeing impacted performance for Kimi K3. We are actively investigating.
Resolved · Oct 12, 11:40 UTC
We've resolved the incident and the affected service is now operational.
Service Degradation for GLM 5.3
Oct 12, 09:59 UTC · Resolved · 24m · minor
Timeline · 2 updates
Investigating · Oct 12, 09:59 UTC
We are seeing impacted performance for GLM 5.3. We are actively investigating.
Resolved · Oct 12, 10:22 UTC
We've resolved the incident and the affected service is now operational.
Service Degradation for GLM 5.3
Oct 12, 01:00 UTC · Resolved · 9m · minor
Timeline · 2 updates
Investigating · Oct 12, 01:00 UTC
We are seeing impacted performance for GLM 5.3. We are actively investigating.
Resolved · Oct 12, 01:08 UTC
We've resolved the incident and the affected service is now operational.
Service Degradation for GLM 5.3
Oct 11, 13:34 UTC · Resolved · 31m · minor
Timeline · 2 updates
Investigating · Oct 11, 13:34 UTC
We are seeing impacted performance for GLM 5.3. We are actively investigating.
Resolved · Oct 11, 14:04 UTC
We've resolved the incident and the affected service is now operational.
Service Degradation for Qwen 3.8 Max
Oct 10, 11:00 UTC · Resolved · 1h 46m · minor
Timeline · 2 updates
Investigating · Oct 10, 11:00 UTC
We are seeing impacted performance for Qwen 3.8 Max. We are actively investigating.
Resolved · Oct 10, 12:45 UTC
We've resolved the incident and the affected service is now operational.
Service Degradation for Qwen 3.8 Max
Oct 10, 10:06 UTC · Resolved · 2m · minor
Timeline · 2 updates
Investigating · Oct 10, 10:06 UTC
We are seeing impacted performance for Qwen 3.8 Max. We are actively investigating.
Resolved · Oct 10, 10:08 UTC
We've resolved the incident and the affected service is now operational.

View 30-day history →

About Fireworks AI

AIWatch Data: Fireworks AI's reported uptime is 99.51%. Based on AIWatch data from the last 30 days, it experienced 39 incidents with an average recovery time of 39 minutes.

Fireworks AI offers fast, scalable inference for popular open-source LLMs and image models, plus fine-tuning and dedicated deployments. It is positioned as a high-performance alternative to Together AI.

When Fireworks AI is down, developers lose hosted inference for open-source models. Production apps relying on Fireworks for serverless or dedicated endpoints will see request failures.

This page provides real-time status and recent incident details; uptime history is shown only when the official source publishes sufficient comparable records — updated every 5 minutes by AIWatch.

Frequently Asked Questions

Is Fireworks AI down right now?

Check the live status indicator at the top of this page. AIWatch monitors Fireworks every 5 minutes and shows real-time operational status.

How do I check Fireworks AI status?

You can check Fireworks status on this page, on the official Fireworks status page at status.fireworks.ai, or on the AIWatch dashboard at ai-watch.dev.

What are alternatives to Fireworks AI?

Based on current AIWatch data, Cohere API (Score: 88) and Groq Cloud (Score: 83) are the most reliable alternatives right now. Together AI, Groq Cloud, and Hugging Face Inference offer similar hosted open-source model inference. AIWatch shows current availability and reliability rankings.

Is Fireworks faster than Together AI?

Both target low-latency inference but optimize differently. Check AIWatch ranking at ai-watch.dev/#ranking to compare uptime and probe response times.

Alternatives When Fireworks AI is Down

Cohere API Score: 88   🟢 Operational
Open ↗
Groq Cloud Score: 83   🟢 Operational
Open ↗

Open ↗ goes to the provider site · ranked by AIWatch Score, not paid.

Reliability rankings → Monthly reports →

Embed this status badge

Show your users Fireworks AI's live status — drop this badge in your README, docs, or status page. It links back to this live page.

Fireworks AI status

View Full Dashboard

Detailed service page · Monthly reports · Set up alerts · How we measure this

Related: Is Together AI down? · Is Groq Cloud down? · Is Cerebras Inference down?

Also check:LLM APIs: Is Claude API down? Is Gemini API down? Is OpenAI API down? Is Mistral API down? Is Cohere API down? Is Perplexity down? Is SpaceXAI API down? Is DeepSeek API down? Is Kimi (Moonshot AI) down? Is OpenRouter down?Coding Agents: Is GitHub Copilot down? Is Cursor down? Is Claude Code down? Is Windsurf (Devin Desktop) down? Is Codex down? Is Junie down?Voice: Is ElevenLabs down? Is AssemblyAI down? Is Deepgram down? Is Fish Audio down?Inference & Infra: Is Hugging Face down? Is Replicate down? Is fal.ai down? Is Pinecone down? Is turbopuffer down? Is Voyage AI down? Is Jina AI down? Is Modal down? Is Twelve Labs down?Observability: Is LangChain (LangSmith) down? Is Helicone down? Is Langfuse down?Video: Is Runway down? Is Luma (Dream Machine) down?Image: Is Stability AI down? Is Black Forest Labs (FLUX) down?AI Apps: Is ChatGPT down? Is claude.ai down? Is Character.AI down? Is DeepSeek App down? Is Grok down?

© 2026 AIWatch. Real-time AI service status monitoring.