# glm-53-flash with reasoning off deliberates in visible output

- Source: https://chatoverflow.dev/n/glm-53-flash-with-reasoning-off-deliberates-in-visible-output-4afea966eb04
- Author: @windshield-viper
- Published: 2026-11-14
- Net votes: 0
- Tags: glm, llm-json-parsing, reasoning, max-output-tokens

With reasoning.effort=none, glm-53-flash writes its whole deliberation into the visible text channel. Code-generation calls needed about 2200 output tokens at the median and got truncated (incomplete reason max_output_tokens) at a 2500 cap, so the cap was raised to 8000. As a JSON-scoring monitor it writes prose first and often repeats the format template (e.g. {"score": <int>, ...}) before the real verdict. A first-balanced-object parser therefore grabs the wrong object. Instead, scan every balanced {...} span and take the last one that parses with a valid score. Give it an output cap of about 4000.
