@@ -1,37 +1,61 @@
11---
2-summary: "GLM model family overview + how to use it in OpenClaw"
2+summary: "GLM model family overview and how to use it in OpenClaw"
33read_when:
44 - You want GLM models in OpenClaw
55 - You need the model naming convention and setup
66title: "GLM (Zhipu)"
77---
889-# GLM models
9+GLM is a model family (not a company) available through the [Z.AI](https://z.ai) platform. In OpenClaw, GLM models are accessed through the bundled `zai` provider with refs like `zai/glm-5.1`.
101011-GLM is a **model family** (not a company) available through the Z.AI platform. In OpenClaw, GLM
12-models are accessed via the `zai` provider and model IDs like `zai/glm-5`.
11+| Property | Value |
12+| ------------------- | --------------------------------------------------------------------------- |
13+| Provider id | `zai` |
14+| Plugin | bundled, `enabledByDefault: true` |
15+| Auth env vars | `ZAI_API_KEY` or `Z_AI_API_KEY` |
16+| Onboarding choices | `zai-api-key`, `zai-coding-global`, `zai-coding-cn`, `zai-global`, `zai-cn` |
17+| API | OpenAI-compatible |
18+| Default base URL | `https://api.z.ai/api/paas/v4` |
19+| Suggested default | `zai/glm-5.1` |
20+| Default image model | `zai/glm-4.6v` |
13211422## Getting started
15231624<Steps>
1725<Step title="Choose an auth route and run onboarding">
18-Pick the onboarding choice that matches your Z.AI plan and region:
26+Pick the onboarding choice that matches your Z.AI plan and region. The generic `zai-api-key` choice auto-detects the matching endpoint from the key shape; use the explicit regional choices when you want to force a specific Coding Plan or general API surface.
192720-| Auth choice | Best for |
21-| ----------- | -------- |
22-| `zai-api-key` | Generic API-key setup with endpoint auto-detection |
23-| `zai-coding-global` | Coding Plan users (global) |
24-| `zai-coding-cn` | Coding Plan users (China region) |
25-| `zai-global` | General API (global) |
26-| `zai-cn` | General API (China region) |
28+| Auth choice | Best for |
29+| ------------------- | --------------------------------------------------- |
30+| `zai-api-key` | Generic API key with endpoint auto-detection |
31+| `zai-coding-global` | Coding Plan users (global) |
32+| `zai-coding-cn` | Coding Plan users (China region) |
33+| `zai-global` | General API (global) |
34+| `zai-cn` | General API (China region) |
273528-```bash
29-# Example: generic auto-detect
30-openclaw onboard --auth-choice zai-api-key
36+<CodeGroup>
313732-# Example: Coding Plan global
33-openclaw onboard --auth-choice zai-coding-global
34-```
38+```bash Auto-detect
39+openclaw onboard --auth-choice zai-api-key
40+```
41+42+```bash Coding Plan (global)
43+openclaw onboard --auth-choice zai-coding-global
44+```
45+46+```bash Coding Plan (China)
47+openclaw onboard --auth-choice zai-coding-cn
48+```
49+50+```bash General API (global)
51+openclaw onboard --auth-choice zai-global
52+```
53+54+```bash General API (China)
55+openclaw onboard --auth-choice zai-cn
56+```
57+58+</CodeGroup>
35593660</Step>
3761<Step title="Set GLM as the default model">
@@ -56,45 +80,42 @@ models are accessed via the `zai` provider and model IDs like `zai/glm-5`.
5680```
57815882<Tip>
59-`zai-api-key` lets OpenClaw detect the matching Z.AI endpoint from the key and
60-apply the correct base URL automatically. Use the explicit regional choices when
61-you want to force a specific Coding Plan or general API surface.
83+`zai-api-key` lets OpenClaw detect the matching Z.AI endpoint from the key shape and apply the correct base URL automatically. Use the explicit regional choices when you want to pin a specific Coding Plan or general API surface.
6284</Tip>
63856486## Built-in catalog
658766-OpenClaw currently seeds the bundled `zai` provider with these GLM refs:
67-68-| Model | Model |
69-| --------------- | ---------------- |
70-| `glm-5.1` | `glm-4.7` |
71-| `glm-5` | `glm-4.7-flash` |
72-| `glm-5-turbo` | `glm-4.7-flashx` |
73-| `glm-5v-turbo` | `glm-4.6` |
74-| `glm-4.5` | `glm-4.6v` |
75-| `glm-4.5-air` | |
76-| `glm-4.5-flash` | |
77-| `glm-4.5v` | |
88+The bundled `zai` provider seeds 13 GLM model refs. All entries support reasoning unless marked otherwise; `glm-5v-turbo` and `glm-4.6v` accept image input as well as text.
89+90+| Model ref | Notes |
91+| -------------------- | -------------------------------------------------- |
92+| `zai/glm-5.1` | Default model. Reasoning, text only, 202k context. |
93+| `zai/glm-5` | Reasoning, text only, 202k context. |
94+| `zai/glm-5-turbo` | Reasoning, text only, 202k context. |
95+| `zai/glm-5v-turbo` | Reasoning, text + image, 202k context. |
96+| `zai/glm-4.7` | Reasoning, text only, 204k context. |
97+| `zai/glm-4.7-flash` | Reasoning, text only, 200k context. |
98+| `zai/glm-4.7-flashx` | Reasoning, text only. |
99+| `zai/glm-4.6` | Reasoning, text only. |
100+| `zai/glm-4.6v` | Reasoning, text + image. Default image model. |
101+| `zai/glm-4.5` | Reasoning, text only. |
102+| `zai/glm-4.5-air` | Reasoning, text only. |
103+| `zai/glm-4.5-flash` | Reasoning, text only. |
104+| `zai/glm-4.5v` | Reasoning, text + image. |
7810579106<Note>
80-The default bundled model ref is `zai/glm-5.1`. GLM versions and availability
81-can change; check Z.AI's docs for the latest.
107+ GLM versions and availability can change. Run `openclaw models list --provider zai` to see the catalog rows known to your installed version, and check Z.AI's docs for newly added or deprecated models.
82108</Note>
8310984110## Advanced configuration
8511186112<AccordionGroup>
87113<Accordion title="Endpoint auto-detection">
88-When you use the `zai-api-key` auth choice, OpenClaw inspects the key format
89-to determine the correct Z.AI base URL. Explicit regional choices
90-(`zai-coding-global`, `zai-coding-cn`, `zai-global`, `zai-cn`) override
91-auto-detection and pin the endpoint directly.
114+When you use the `zai-api-key` auth choice, OpenClaw inspects the key shape to determine the correct Z.AI base URL. Explicit regional choices (`zai-coding-global`, `zai-coding-cn`, `zai-global`, `zai-cn`) override auto-detection and pin the endpoint directly.
92115</Accordion>
9311694117<Accordion title="Provider details">
95-GLM models are served by the `zai` runtime provider. For full provider
96-configuration, regional endpoints, and additional capabilities, see
97-[Z.AI provider docs](/providers/zai).
118+GLM models are served by the `zai` runtime provider. For full provider configuration, regional endpoints, and additional capabilities, see the [Z.AI provider page](/providers/zai).
98119</Accordion>
99120</AccordionGroup>
100121@@ -104,7 +125,13 @@ can change; check Z.AI's docs for the latest.
104125<Card title="Z.AI provider" href="/providers/zai" icon="server">
105126Full Z.AI provider configuration and regional endpoints.
106127</Card>
107-<Card title="Model selection" href="/concepts/model-providers" icon="layers">
128+<Card title="Model providers" href="/concepts/model-providers" icon="layers">
108129Choosing providers, model refs, and failover behavior.
109130</Card>
131+<Card title="Thinking modes" href="/tools/thinking" icon="brain">
132+`/think` levels for the reasoning-capable GLM family.
133+</Card>
134+<Card title="Models FAQ" href="/help/faq-models" icon="circle-question">
135+Auth profiles, switching models, and resolving "no profile" errors.
136+</Card>
110137</CardGroup>
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。