# Zhipu AI GLM LLM Node (`llm_glm`) Connects RocketRide pipelines to Zhipu AI's **GLM** family of open-weight hybrid-reasoning models, served through the OpenAI-compatible Z.ai cloud API ([z.ai](https://z.ai)) or self-hosted with vLLM or SGLang. - **Lane:** `questions → answers` - **Endpoint (cloud, international):** `https://api.z.ai/api/paas/v4` - **Endpoint (cloud, mainland China):** `https://open.bigmodel.cn/api/paas/v4` ## Models The GLM-4.5 through GLM-5 generations are hybrid-reasoning MoE models with thinking and non-thinking modes and strong agentic/coding performance. The profile set matches the live Z.ai `/models` catalog (verified 2026-08). | Profile | Model ID | Context | Notes | | --- | --- | --- | --- | | GLM-5.2 *(default)* | `glm-5.2` | 1M | Frontier long-context reasoning and coding | | GLM-5.1 | `glm-5.1` | 200K | Previous flagship | | GLM-5 | `glm-5` | 200K | First GLM-5 generation | | GLM-5 Turbo | `glm-5-turbo` | 200K | Fast cost-effective tier | | GLM-4.7 | `glm-4.7` | 200K | Enhanced-reasoning 4.x flagship | | GLM-4.6 | `glm-4.6` | 200K | Open-weight 4.x flagship | | GLM-4.5 | `glm-4.5` | 128K | Open-weight | | GLM-4.5 Air | `glm-4.5-air` | 128K | Open-weight, efficient cost/quality balance | | Custom Model | (user-defined) | (user-defined) | Any model on an OpenAI-compatible endpoint | The vision variants (GLM-4V / GLM-4.5V), embedding, CogView (image), CogVideoX (video), rerank, and audio lines are out of scope for this chat node. ## Reasoning output GLM-4.5+ models are reasoning models. The Z.ai cloud returns reasoning in a separate `reasoning_content` field, and for endpoints that inline `...` blocks in `content` the engine's shared LangChain adapter strips them and routes the reasoning to the thinking lane — the node needs no stripping of its own. Budget generous output tokens for reasoning-heavy prompts. ## Self-hosting GLM weights are openly published on Hugging Face under MIT-style licenses (`zai-org/GLM-5.2`, `zai-org/GLM-4.5-Air`, ...). To use a self-hosted vLLM or SGLang deployment, select the **Custom Model** profile and point its server base URL at your OpenAI-compatible endpoint; the API key may be left empty (the node passes a dummy token — local servers accept any). ## Authentication Cloud profiles require a Z.ai / Zhipu AI API key in `apikey`. The key requirement is enforced by base-URL match: if `serverbase` contains `api.z.ai` or `bigmodel.cn` and no key is set, the node raises `GLM API key is required for cloud profiles.` at startup. Key format is not validated beyond presence. ## Model sync Profiles are maintained by the `sync_models` tooling (`llm_glm` provider, `ROCKETRIDE_GLM_KEY`). The include filter keeps only the `glm-*` text chat models; vision (4V/4.5V), embedding, rerank, audio, and reward variants are excluded (they belong in dedicated nodes). --- ## Schema | Field | Type | Description | Default | |---|---|---|---| | `glm.profile` | `string` | **Model**
Zhipu AI GLM LLM model | `"glm-5-2"` | | `glm.serverbase` | `string` | **Server base URL**
OpenAI-compatible base URL for the GLM endpoint (e.g. https://api.z.ai/api/paas/v4 for the Z.ai cloud API, http://localhost:8000/v1 for a self-hosted vLLM / SGLang server). | `"https://api.z.ai/api/paas/v4"` | | `model` | `string` | **Model**
Zhipu AI GLM model | | | `modelTotalTokens` | `number` | **Tokens**
Total Tokens | | ## Dependencies - `openai` - `langchain-openai` - `langchain-core` - `langchain` ## Source [ View source](https://github.com/rocketride-org/rocketride-server/tree/develop/nodes/src/nodes/llm_glm)