Skip to content

1.22.1

Latest

Choose a tag to compare

@rolandorojas rolandorojas released this 11 Aug 20:35

Improved routing with continuous QoS latency weighting and a configurable latency target in Settings.

Corrected the Cerebras GLM 4.7 free-tier context limit to 8,192 tokens.

Added documentation and regression tests for the new routing behavior.