From 040afbeff4bbed9afbe8f2306652916f6ab8bbd5 Mon Sep 17 00:00:00 2001 From: "opencode-agent[bot]" Date: Fri, 4 Sep 2026 04:29:23 +0000 Subject: [PATCH 1/2] chore(sync): update Baseten model catalog --- .../baseten/models/zai-org/GLM-5.3-Fast.toml | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) create mode 100644 providers/baseten/models/zai-org/GLM-5.3-Fast.toml diff --git a/providers/baseten/models/zai-org/GLM-5.3-Fast.toml b/providers/baseten/models/zai-org/GLM-5.3-Fast.toml new file mode 100644 index 00000000000..d4eb851d9dc --- /dev/null +++ b/providers/baseten/models/zai-org/GLM-5.3-Fast.toml @@ -0,0 +1,16 @@ +base_model = "zhipuai/glm-5.3" +name = "GLM 5.3 Fast" +description = "GLM vision model for visual reasoning, documents, and multimodal agents" +attachment = true +reasoning_options = [] + +[cost] +input = 2.1 +output = 6.6 + +[limit] +context = 1_048_576 +output = 262_144 + +[modalities] +input = ["text", "image"] From 3b44580f2b3354a9fcd46ef63f9ba6f40c1fe528 Mon Sep 17 00:00:00 2001 From: rekram1-node Date: Fri, 4 Sep 2026 05:22:51 +0000 Subject: [PATCH 2/2] fix(baseten): add GLM 5.3 Fast reasoning effort options --- providers/baseten/models/zai-org/GLM-5.3-Fast.toml | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/providers/baseten/models/zai-org/GLM-5.3-Fast.toml b/providers/baseten/models/zai-org/GLM-5.3-Fast.toml index d4eb851d9dc..bbee46d8d36 100644 --- a/providers/baseten/models/zai-org/GLM-5.3-Fast.toml +++ b/providers/baseten/models/zai-org/GLM-5.3-Fast.toml @@ -1,8 +1,12 @@ +# Effort: top-level reasoning_effort = none|low|high|max (default high). +# none requests a direct answer but may still return short reasoning_content; +# chat_template_args.enable_thinking=false is rejected, so no separate toggle. +# https://docs.baseten.co/inference/model-apis/reasoning base_model = "zhipuai/glm-5.3" name = "GLM 5.3 Fast" description = "GLM vision model for visual reasoning, documents, and multimodal agents" attachment = true -reasoning_options = [] +reasoning_options = [{ type = "effort", values = ["none", "low", "high", "max"] }] [cost] input = 2.1