From 624a07e9c292af83ee73e712815560ba9fd5e624 Mon Sep 17 00:00:00 2001 From: Vuong Hoang Date: Sun, 5 Jul 2026 09:09:05 -0700 Subject: [PATCH] docs(litellm): record glm-5.2 canonical limits in gateway config comment Probed live vs z.ai 2026-07-05: glm-5.2 = 1,048,576-token (1M) input context, 131,072 (128K) max output; no gateway-side cap (pure z.ai passthrough). Comment-only, no runtime effect. --- stacks/litellm/conf/config.yaml | 3 +++ 1 file changed, 3 insertions(+) diff --git a/stacks/litellm/conf/config.yaml b/stacks/litellm/conf/config.yaml index c5e0888..2ec3f38 100644 --- a/stacks/litellm/conf/config.yaml +++ b/stacks/litellm/conf/config.yaml @@ -295,6 +295,9 @@ model_list: # a live completion with our key). Mirrors the glm-5.1 pattern: thinking DISABLED # by default (consistency with the 2026-06-11 operator call), opt-in reasoning via # glm-5.2-reasoning. extra_body.thinking is forwarded verbatim to z.ai. + # CANONICAL LIMITS (probed live vs z.ai 2026-07-05): 1,048,576-token (1M, 2^20) + # INPUT context; 131,072 (128K) MAX OUTPUT (z.ai max_tokens range [1,131072]). + # NO gateway-side cap — pure z.ai passthrough, so these are the effective limits. - model_name: glm-5.2 litellm_params: model: openai/glm-5.2