Thinking Machines Lab

Thinking Machines Lab / History

History

Aug 2026-Nov 2026
November
No incidents reported
October
28
Wed
Degraded sampling for DeepSeek-V4.1-Flash
8:53 AM

Between 10:44 and 12:47 UTC, sampling requests for DeepSeek-V4.1-Flash stalled and did not return results. Other models and the OpenAI-compatible endpoint were not affected. A fix is deployed and capacity is recovering; requests that stalled in this window can be retried now. We are monitoring until the rollout completes.

23
Fri
Tinker sampling down
6:22 PM

The issue has been fully resolved.

10
Sat
Tinker backend calls failing with 5xx errors
9:59 PM

The issue has been fully resolved.

07
Wed
Billing backend outage
8:14 PM

The incident is fully resolved.

02
Fri
sampling broken for gpt-oss-20b and gpt-oss-120b
12:02 AM

The incident is fully resolved.

September
07
Mon
LoRA rank <8 may fail training on MoE models
8:24 PM

The issue has been fully resolved.

Training on Inkling could fail with variable-shape loss inputs — SDK 0.24.1 required
3:38 AM

SDK version 0.25.0+ is required to use Tinker API.

Tinker SDK may be getting stuck on MacOS
3:37 AM

SDK version 0.25.0+ is required to use Tinker API.

August
11
Tue
Temporary outage due to billiing backend
6:35 PM

The issue has been fully resolved.

All sampling was down 6:36PM PT - 7:01PM PT on 08/08
12:04 PM

The issue was resolved.

05
Wed
Getting model info can fail for old models
5:51 PM

This is fully resolved now.

04
Tue
Tinker sampling slow or stuck for most models
8:40 PM

The issue is fully resolved now.

Powered by
Privacy policy

·

Terms of service