Elevated errors on chat when using Claude Sonnet or Opus 4.5
minor- Started
- Jan 12, 1:19 PM EST
- Resolved
- Jan 15, 5:04 AM EST
- Duration
- 63h 45m
Granola's updates (5)
- investigating · Jan 12, 1:19 PM EST
We're seeing higher than usual error rates when generating chat responses if you've selected Claude Sonnet 4.5 or Claude Opus 4.5. This is due to an outage on Claude models. We'll continue to provide updates, and Anthropic are providing updates on their status page: [https://status.claude.com/incidents/zt2q0ltqcvbx](https://status.claude.com/incidents/zt2q0ltqcvbx "https://status.claude.com/incidents/zt2q0ltqcvbx") You should be able to work around this by switching to another model in Granola chat (e.g. Gemini or GPT).
- monitoring · Jan 12, 1:51 PM EST
Anthropic are reporting that a fix has been implemented - we're monitoring error rates to make sure this is fully resolved on our side.
- identified · Jan 14, 5:51 AM EST
Anthropic are reporting further errors on Claude models, so some chat queries are failing in Granola. If you're having issues, please switch to 'Auto', Gemini or GPT models.
- monitoring · Jan 14, 8:35 AM EST
Anthropic have reported a fix is in place for Claude 4.5 Sonnet and Open, and we're seeing error rates falling again in Granola Chat. If you do continue to hit errors, please try using an alternative model for now.
- resolved · Jan 15, 5:04 AM EST
We're no longer seeing higher error rates across Claude models - get in touch at [hey@granola.so](mailto:hey@granola.so "hey@granola.so") if you're still having issues though!
Updates are Granola's own words from its status page (status: resolved); we never add an inferred cause.