Where does this status come from?

From Fireworks AI's own status page API at https://status.fireworks.ai. UpButler reads it once for everyone (not once per visitor) every 120 seconds with conditional requests, and shows it unchanged: incident titles and component names are Fireworks AI's words.

How can my agent or app check Fireworks AI status?

Fetch https://upbutler.com/status/fireworks/status.agent.json: a small JSON document with a verdict (proceed, retry, fallback or pause) and retryAfterSec. No key is needed. The same answer is an MCP tool, upstream_status {"service":"fireworks"}, on https://upbutler.com/mcp/public.

How do I know whether an outage is mine or Fireworks AI's?

Add "fireworks" to the dependencies of your UpButler workspace. When one of your monitors fails while Fireworks AI has an incident that began around the same time, your incident is tagged "likely upstream" with their incident linked, and your on-call agent is told not to change code.

Is Fireworks AI down?

Right now

No. Fireworks AI is operational.

No incidents reported.

Read from status.fireworks.ai 3 min ago · every 120s

For agents

proceed

Proceed.

GET upbutler.com/status/fireworks/status.agent.json

MCP: upstream_status {"service":"fireworks"}

Serverless and on-demand inference for open models.

What Fireworks AI reports

Operational

Taken as is from Fireworks AI's own status page API. Incident titles and component names below are theirs.

Open status.fireworks.ai

UpButler's independent probe

There is no keyless endpoint of Fireworks AI that says anything useful, so UpButler does not probe it. To check your own Fireworks AI account, add a monitor with your key: it is yours alone and catches what a shared probe cannot.

Fireworks AI components

18 operational

GLM 5.3 FlashOperational
GLM 5.3 Flash USOperational
GLM 5.3Operational
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 UltraOperational
Nemotron 3.5 LightningOperational
Minimax M3 USOperational
MiniMax M3Operational
InklingOperational
GPT-OSS 120BOperational

Fireworks AI incidents, last 90 days

12 finished incidents seen since UpButler started tracking on 2026-10-10. A typical one lasted 11 min; the longest 1 h 47 min.

Started (UTC)	Incident	Impact	Lasted
2026-10-08 20:49	Service Degradation for GLM 5.3 Flash	minor	1 h 47 min
2026-10-08 19:17	Service Degradation for GLM 5.3 Flash	minor	13 min
2026-10-07 21:29	Service Degradation for GLM 5.3	minor	11 min
2026-10-07 19:02	Service Degradation for Qwen 3.8 Max	minor	11 min
2026-10-07 12:16	Service Degradation for GLM 5.3 Flash	minor	under a minute
2026-10-05 18:51	Service Degradation for GLM 5.3	minor	24 min
2026-10-05 17:15	Service Degradation for Kimi K3 US	minor	26 min
2026-10-05 14:32	Service Degradation for Qwen 3.8 Max	minor	1 min
2026-10-05 06:21	Service Degradation for Deepseek V4.1 Flash	minor	3 min
2026-10-04 16:29	Service Degradation for Deepseek V4.1 Flash	minor	under a minute
2026-10-02 22:35	Service Degradation for GLM 5.3 Fast	minor	14 min
2026-10-01 05:57	Service Degradation for Deepseek V4.1 Flash	minor	8 min

Tell your outage from Fireworks AI's

Declare that your project depends on Fireworks AI. When one of your monitors fails while Fireworks AI has an incident that began around the same time, UpButler tags your incident "likely upstream" with their incident linked, says so in the alert and the AI report, and tells your on-call agent not to change code.

npx upbutler init finds the dependency from your env var names and packages. The catalog, dependencies and upstream-aware incidents are on every plan, including Free.

Start free How it works

upbutler.yaml

# upbutler.yaml
dependencies:
  - fireworks

Ask before you retry

curl -s https://upbutler.com/status/fireworks/status.agent.json

status.agent.json (live)

{
  "schema": "upbutler.upstream-status/v1",
  "service": "fireworks",
  "verdict": "proceed",
  "status": "operational",
  "reason": "No incidents reported",
  "retryAfterSec": null,
  "incident": null,
  "probe": null
}

Questions

Is Fireworks AI down right now?: No. As of 2026-10-10 05:09 UTC, Fireworks AI is operational. This page reads the status again every 2 minutes.
Where does this status come from?: From Fireworks AI's own status page API at https://status.fireworks.ai. UpButler reads it once for everyone (not once per visitor) every 120 seconds with conditional requests, and shows it unchanged: incident titles and component names are Fireworks AI's words.
How can my agent or app check Fireworks AI status?: Fetch https://upbutler.com/status/fireworks/status.agent.json: a small JSON document with a verdict (proceed, retry, fallback or pause) and retryAfterSec. No key is needed. The same answer is an MCP tool, upstream_status {"service":"fireworks"}, on https://upbutler.com/mcp/public.
How do I know whether an outage is mine or Fireworks AI's?: Add "fireworks" to the dependencies of your UpButler workspace. When one of your monitors fails while Fireworks AI has an incident that began around the same time, your incident is tagged "likely upstream" with their incident linked, and your on-call agent is told not to change code.

More in ai models and tooling

UpButler is not affiliated with Fireworks AI. Status and incident text belong to Fireworks AI and are read from their public status source; the probe result is UpButler's own measurement.