Skip to content

Is Tavily down?

Right now

No. Tavily is operational.

No incidents reported.

Read from status.tavily.com · every 120s

For agents

proceed

Proceed.

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

MCP: upstream_status {"service":"tavily"}

Search API built for agents.

What Tavily reports

Operational

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

Open status.tavily.com

UpButler's independent probe

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

Open at Tavily

Text written by Tavily, shown unchanged.

Tavily components

3 operational

  • Tavily API ServiceOperational
  • Tavily MCPOperational
  • Tavily WebsiteOperational

Tavily incidents, last 90 days

No finished incidents on record yet. UpButler keeps what Tavily publishes for 90 days from the day it starts tracking a service.

Tell your outage from Tavily's

Declare that your project depends on Tavily. When one of your monitors fails while Tavily 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.

upbutler.yaml
# upbutler.yaml
dependencies:
  - tavily
Ask before you retry
curl -s https://upbutler.com/status/tavily/status.agent.json
status.agent.json (live)
{
  "schema": "upbutler.upstream-status/v1",
  "service": "tavily",
  "verdict": "proceed",
  "status": "operational",
  "reason": "No incidents reported",
  "retryAfterSec": null,
  "incident": null,
  "probe": null
}

Questions

Is Tavily down right now?
No. As of 2026-10-10 05:11 UTC, Tavily is operational. This page reads the status again every 2 minutes.
Where does this status come from?
From Tavily's own status page API at https://status.tavily.com. 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 Tavily's words.
How can my agent or app check Tavily status?
Fetch https://upbutler.com/status/tavily/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":"tavily"}, on https://upbutler.com/mcp/public.
How do I know whether an outage is mine or Tavily's?
Add "tavily" to the dependencies of your UpButler workspace. When one of your monitors fails while Tavily 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 search and web data

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