[Integrations](https://spiral.ai/integrations) › [Claude](https://spiral.ai/integrations/claude-desktop) › [GLM-5.3](https://spiral.ai/integrations/claude-desktop/glm-5-3)

# How to Use GLM-5.3 in Claude

GLM-5.3 is built for complex coding, debugging, and tasks that require many steps. Compared with GLM-5.2, Z.ai reports stronger coding and extended-task performance.

|  |  |
| --- | --- |
| Model | GLM-5.3 |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.019174 per run at the default inputs. $0.1092 per 1M input tokens, $4.68 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with GLM-5.3 in Claude

- Use GLM-5.3 with maximum reasoning to analyze the code and error text above. Rank likely causes and suggest a distinguishing check.
- Use GLM-5.3 to compare the two architecture proposals above against our requirements. State assumptions and unresolved tradeoffs.
- Use GLM-5.3 to review the pasted function for security flaws. Explain each finding and propose a corrected version.
- Use GLM-5.3 to turn our feature discussion into an implementation plan with acceptance criteria and edge cases.
- Use GLM-5.3 to extract decisions from this conversation as JSON. Include decision, owner, and evidence; use null for missing owners.

## How to set up GLM-5.3 in Claude

Pick the way that suits you. Each takes about two minutes.

### Use the Claude connector

1. **Add Spiral to Claude**: Click Add Spiral in Claude above. Claude opens Add custom connector with Spiral and its URL filled in; check them and click Continue. Without the link: in Claude open Customize › Connectors › Add › Add custom connector and paste this URL:

```text
https://api.spiral.ai/mcp
```

2. **Keep the detected sign-in and click Add**: Claude finds Spiral's sign-in by itself: leave Sign in now and Use Claude's published identity selected.

3. **Click Connect**: The connector page opens. Connect takes you to Spiral in your browser.

### Use the Spiral skill

1. **Send Claude this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run GLM-5.3**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "openrouter",
    "model": "z-ai/glm-5.3",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Claude finds GLM-5.3 on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/claude-desktop

## GLM-5.3 tools and prices

- [Z.ai: GLM 5.3](https://spiral.ai/tools/openrouter/z-ai/glm-5.3) (OpenRouter): Up to $0.007459 per run at the default inputs. $0.09087 per 1M input tokens, $1.82 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| stop |  | — |  |
| min_p | 0 to 1 | — |  |
| tools |  | — |  |
| top_k | 0 to … | — |  |
| top_p | 0 to 1 | — |  |

## What can you do with GLM-5.3 in Claude?

GLM-5.3 can turn a technical problem into a concrete diagnosis or implementation plan. Supply code, error text, and constraints directly in the conversation.

### Repair a difficult bug

Ask GLM-5.3 to trace a failure, propose a minimal patch, and define a regression check.

### Plan a code migration

Use GLM-5.3 to identify dependencies, order changes, and define compatibility checks.

### Implement a feature

Give GLM-5.3 requirements and acceptance criteria, then request an implementation and verification report.

### Investigate performance problems

Have GLM-5.3 examine code and measurements, propose a bottleneck hypothesis, and design a comparison.

### Review code for vulnerabilities

Ask GLM-5.3 to inspect your code for security flaws and suggest fixes with supporting evidence.

### Evaluate a technical design

Use GLM-5.3 to compare architectures against stated constraints and identify unresolved decisions.

### Extract structured records

Ask GLM-5.3 to turn supplied text into JSON with explicit rules for missing information.

## Overview

- [OpenRouter](https://spiral.ai/providers/openrouter)
- [All Claude guides](https://spiral.ai/integrations/claude-desktop)

## GLM-5.3 in other agents

- [Amp](https://spiral.ai/integrations/amp/glm-5-3)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/glm-5-3)
- [Claude Code](https://spiral.ai/integrations/claude-code/glm-5-3)
- [Cline](https://spiral.ai/integrations/cline/glm-5-3)
- [Codex](https://spiral.ai/integrations/codex/glm-5-3)
- [Cursor](https://spiral.ai/integrations/cursor/glm-5-3)
- [Devin](https://spiral.ai/integrations/devin/glm-5-3)
- [dots](https://spiral.ai/integrations/dots/glm-5-3)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/glm-5-3)
- [Gemini](https://spiral.ai/integrations/gemini/glm-5-3)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/glm-5-3)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/glm-5-3)
- [goose](https://spiral.ai/integrations/goose/glm-5-3)
- [Grok](https://spiral.ai/integrations/grok/glm-5-3)
- [Grok Build](https://spiral.ai/integrations/grok-build/glm-5-3)
- [Hermes](https://spiral.ai/integrations/hermes/glm-5-3)
- [Instinct](https://spiral.ai/integrations/instinct/glm-5-3)
- [Manus](https://spiral.ai/integrations/manus/glm-5-3)
- [Muse](https://spiral.ai/integrations/muse/glm-5-3)
- [Muse Code](https://spiral.ai/integrations/muse-code/glm-5-3)
- [n8n](https://spiral.ai/integrations/n8n/glm-5-3)
- [Notion](https://spiral.ai/integrations/notion/glm-5-3)
- [OpenClaw](https://spiral.ai/integrations/openclaw/glm-5-3)
- [opencode](https://spiral.ai/integrations/opencode/glm-5-3)
- [Perplexity](https://spiral.ai/integrations/perplexity/glm-5-3)
- [Raycast](https://spiral.ai/integrations/raycast/glm-5-3)
- [VS Code](https://spiral.ai/integrations/vscode/glm-5-3)
- [Windsurf](https://spiral.ai/integrations/windsurf/glm-5-3)
- [Zapier](https://spiral.ai/integrations/zapier/glm-5-3)

## More Claude guides

- [GLM-5.2](https://spiral.ai/integrations/claude-desktop/glm-5-2)
- [GLM-5V-Turbo](https://spiral.ai/integrations/claude-desktop/glm-5v-turbo)
- [GLM-5 Turbo](https://spiral.ai/integrations/claude-desktop/glm-5-turbo)
- [GPT Astra](https://spiral.ai/integrations/claude-desktop/gpt-astra)
- [GLM-5](https://spiral.ai/integrations/claude-desktop/glm-5)
- [GPT Chat Latest](https://spiral.ai/integrations/claude-desktop/gpt-chat-latest)

## Questions about GLM-5.3 in Claude

**Can Claude use GLM-5.3?**

Yes. Add Spiral to Claude as an MCP server, and Claude can find and run GLM-5.3 like any built-in tool.

**How much does GLM-5.3 cost in Claude?**

Up to $0.019174 per run at the default inputs. $0.1092 per 1M input tokens, $4.68 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude plan is separate.

**Do I need an OpenRouter account to use GLM-5.3 in Claude?**

No. Spiral runs GLM-5.3 on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up GLM-5.3 in Claude?**

About two minutes: add Spiral to Claude, then keep the detected sign-in and click Add, then click Connect.

**Does Claude wait while GLM-5.3 runs?**

GLM-5.3 runs in the background. Claude starts the run, checks on it and gives you the text, json when it's ready.

**What is GLM-5.3 good at?**

Complex coding and tasks that require sustained work across several steps are its main focus. Try it for debugging, refactoring, and implementing changes with explicit acceptance criteria.

**Can GLM-5.3 understand screenshots or video?**

GLM-5.3 accepts text only. Provide a written description, extracted text, or logs when the original evidence is visual.

**How much text can GLM-5.3 handle?**

Z.ai documents a 1 million-token context window and a maximum output length of 128K tokens. Keep requested answers focused even when supplying extensive context.

**Can I turn off GLM-5.3's reasoning?**

No. Thinking stays enabled; use low reasoning effort for simpler work and start with maximum reasoning for difficult problems.

**Where does GLM-5.3 fall short?**

Its coding results are not uniformly best: Z.ai reports that Claude Fable 5 scores higher on its Code Bench. Treat generated patches as candidates to test against your own requirements.

