---
title: "OpenClaw x GLM guide"
url: "https://runapi.ai/openclaw-glm.md"
canonical: "https://runapi.ai/openclaw-glm"
locale: "en"
model_line: "glm"
---

# OpenClaw x GLM

GLM models from Z.ai are MIT-licensed MoE LLMs spanning 128K–200K context. GLM-5.1 leads open-weight models on SWE-bench Pro. Through RunAPI they share a single API key with pay-as-you-go token billing, callable from the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages surfaces.

## Public versions and endpoints

| Model ID | Version | Endpoints | Starting price |
| --- | --- | --- | --- |
| `glm-4.5` | 355B / 32B active; 128K context; flagship open-weight MoE baseline | /v1/chat/completions | $0.0004 |
| `glm-4.5-air` | Lighter GLM-4.5 tier for fast, lower-cost everyday work | /v1/chat/completions | $0.0001 |
| `glm-4.6` | 200K context; first GLM on Cambricon chips; sharper code generation | /v1/chat/completions | $0.0006 |
| `glm-4.7` | 200K context; 73.8% SWE-bench; persistent thinking across turns | /v1/chat/completions | $0.0006 |
| `glm-5` | 744B / 40B active; 200K context; 77.8% SWE-bench Verified | /v1/chat/completions | $0.0010 |
| `glm-5-turbo` | Speed-optimized GLM-5 tier for lower latency | /v1/chat/completions | $0.0012 |
| `glm-5.1` | 754B / 40B active; 58.4% SWE-bench Pro — top open-weight score | /v1/chat/completions | $0.0014 |
| `glm-5.2` | Current flagship foundation model for text generation | /v1/chat/completions | $0.0007 |

## Configuration

Select `<model-id>` before using a command. This page does not select a default model.
Use `runapi/<model-id>` with OpenClaw, or configure the RunAPI custom endpoint and select `<model-id>` with Hermes Agent.

`/v1/chat/completions`

```
{
  models: {
    mode: "merge",
    providers: {
      runapi: {
        baseUrl: "https://runapi.ai/v1",
        apiKey: "${RUNAPI_API_KEY}",
        api: "openai-completions",
        models: [{ id: "<model-id>", name: "RunAPI <model-id>" }],
      },
    },
  },
}
```

```
openclaw models status
openclaw models set runapi/<model-id>
```

## Additional operations


## How it works

1. **Choose a model ID.** Select a public catalog model ID and review its endpoint and current starting price.
2. **Configure RunAPI.** Add the provider configuration for this agent.
3. **Verify the result.** Run the agent status and model-selection commands shown below.

## FAQ

### Which model ID should I use?

Choose a public model ID from the version table. Each ID exposes the endpoints shown for that version.

### Does this guide configure a chat model?

Yes. This Model Line supports a client-facing LLM protocol.


## Links

- [OpenClaw](https://runapi.ai/openclaw)
- [GLM - Catalog](https://runapi.ai/models/glm)
- [glm-4.5](https://runapi.ai/models/glm/4.5)
- [glm-4.5-air](https://runapi.ai/models/glm/4.5-air)
- [glm-4.6](https://runapi.ai/models/glm/4.6)
- [glm-4.7](https://runapi.ai/models/glm/4.7)
- [glm-5](https://runapi.ai/models/glm/5)
- [glm-5-turbo](https://runapi.ai/models/glm/5-turbo)
- [glm-5.1](https://runapi.ai/models/glm/5.1)
- [glm-5.2](https://runapi.ai/models/glm/5.2)

```json
{
  "@context": "https://schema.org",
  "@type": "SoftwareApplication",
  "name": "OpenClaw x GLM",
  "url": "https://runapi.ai/openclaw-glm"
}
```