[Integrations](https://spiral.ai/integrations) › [Muse](https://spiral.ai/integrations/muse) › [GLM 5.3 Prime](https://spiral.ai/integrations/muse/glm-5-3-prime)

# How to Use GLM 5.3 Prime in Muse

GLM 5.3 Prime is built for coding, technical conversations, and tasks that need several rounds of tool use. It retains GLM 5.3’s capabilities while accelerating output generation, with a reported 1.5–2× increase in output throughput.

|  |  |
| --- | --- |
| Model | GLM 5.3 Prime |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.046986 per run at the default inputs. $3.64 per 1M input tokens, $11.44 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with GLM 5.3 Prime in Muse

- Use GLM 5.3 Prime with maximum reasoning to compare a queue-based worker and a synchronous service for processing customer exports. Evaluate retries, duplicate jobs, failure recovery, and operational complexity. State your assumptions.
- Use GLM 5.3 Prime to analyze the error messages pasted above. Rank three possible causes, cite the evidence for each, and give me the next check that would distinguish them.
- Use GLM 5.3 Prime to turn the API documentation pasted above into a Python client example. Include pagination and documented error handling, and identify any behavior the documentation leaves unclear.
- Use GLM 5.3 Prime to extract action items from the conversation above as JSON. Give each item an action, owner, deadline, and supporting excerpt. Use null when the owner or deadline is absent.
- Use GLM 5.3 Prime to review the code pasted above for boundary-condition errors. Explain each confirmed issue with a small input example and propose regression tests.

## How to set up GLM 5.3 Prime in Muse

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

### Use the Muse connector

1. **Create an API key**: Create one under API keys in the Spiral console.

2. **Send Muse this message**: Muse reads Spiral's skill and asks for an API key.

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

3. **Give Muse the key**: Paste the key when Muse asks for it, never in the chat itself.

### Use the Spiral skill

1. **Send Muse 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 Prime**: 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-prime",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

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

Setup guide in the docs: https://spiral.ai/docs/quickstarts/muse

## GLM 5.3 Prime tools and prices

- [Z.ai: GLM 5.3 Prime](https://spiral.ai/tools/openrouter/z-ai/glm-5.3-prime) (OpenRouter): Up to $0.028192 per run at the default inputs. $2.184 per 1M input tokens, $6.864 per 1M output tokens.

## Settings you can ask for

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

## What can you do with GLM 5.3 Prime in Muse?

GLM 5.3 Prime can turn a technical conversation into code, a diagnostic plan, or an implementation decision. Supply the relevant text and ask for a concrete deliverable with supporting evidence.

### Fix a reproducible bug

Give GLM 5.3 Prime the failure, relevant code, and expected behavior. Ask for a reproduction, a focused correction, and evidence that the correction works.

### Plan a code migration

Ask GLM 5.3 Prime to map dependencies, identify compatibility risks, and divide a migration into changes with explicit acceptance checks.

### Design regression tests

Have GLM 5.3 Prime turn a bug report or behavior specification into test cases covering ordinary inputs, boundary conditions, and failure paths.

### Draft an API client

Provide a textual API specification and ask GLM 5.3 Prime for client code, response handling, and tests tied to documented behavior.

### Triage technical incidents

Give GLM 5.3 Prime timestamped logs and deployment notes. Request an evidence-based timeline, competing explanations, and the next diagnostic checks.

### Extract structured records

Ask GLM 5.3 Prime to convert supplied text into JSON using an explicit structure. Validate required properties and types before passing the records onward.

### Compare implementation approaches

Ask GLM 5.3 Prime to evaluate technical approaches against stated requirements and explain which assumptions could change the recommendation.

## Overview

- [OpenRouter](https://spiral.ai/providers/openrouter)
- [All Muse guides](https://spiral.ai/integrations/muse)

## GLM 5.3 Prime in other agents

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

## More Muse guides

- [GLM 5.3 FlashX Legal](https://spiral.ai/integrations/muse/glm-5-3-flashx-legal)
- [GLM Flash Latest](https://spiral.ai/integrations/muse/glm-flash-latest)
- [GLM 5.3 FlashX](https://spiral.ai/integrations/muse/glm-5-3-flashx)
- [GLM Latest](https://spiral.ai/integrations/muse/glm-latest)
- [GLM 5.3 Flash](https://spiral.ai/integrations/muse/glm-5-3-flash)
- [GLM-4.5](https://spiral.ai/integrations/muse/glm-4-5)

## Questions about GLM 5.3 Prime in Muse

**Can Muse use GLM 5.3 Prime?**

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

**How much does GLM 5.3 Prime cost in Muse?**

Up to $0.046986 per run at the default inputs. $3.64 per 1M input tokens, $11.44 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Muse plan is separate.

**Do I need an OpenRouter account to use GLM 5.3 Prime in Muse?**

You need no OpenRouter account. Muse uses one Spiral API key for every tool, and Spiral runs GLM 5.3 Prime on its own OpenRouter account.

**How long does it take to set up GLM 5.3 Prime in Muse?**

About two minutes: create an API key, then send Muse this message, then give Muse the key.

**Does Muse wait while GLM 5.3 Prime runs?**

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

**How does GLM 5.3 Prime differ from GLM 5.3?**

Prime accelerates output generation while retaining GLM 5.3’s capabilities. The reported improvement is 1.5–2× output throughput, rather than a separate increase in reasoning quality.

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

It supports a 1M-token context window and up to 128K output tokens. For a large task, ask for a specific deliverable, such as a migration plan or a focused patch, rather than an unrestricted response.

**Can GLM 5.3 Prime read screenshots or generate images?**

GLM 5.3 Prime accepts text and produces text. Provide error messages, extracted text, or a written description when the original material is visual.

**Can I turn reasoning off?**

Reasoning stays enabled. You can choose low, high, or maximum reasoning effort; maximum is the default.

**Can GLM 5.3 Prime return reliable JSON?**

It can return JSON, but JSON-schema enforcement is not supported. Describe the required structure, then validate the result before using it in an automated workflow.

