[Integrations](https://spiral.ai/integrations) › [Grok](https://spiral.ai/integrations/grok) › [GLM 5.3 FlashX](https://spiral.ai/integrations/grok/glm-5-3-flashx)

# How to Use GLM 5.3 FlashX in Grok

GLM 5.3 FlashX suits coding, visual checks, and document analysis in tool-using workflows. Compared with GLM 5.3 Flash, it emphasizes faster inference while retaining multimodal capabilities.

|  |  |
| --- | --- |
| Model | GLM 5.3 FlashX |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.006673 per run at the default inputs. $0.481 per 1M input tokens, $1.625 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 FlashX in Grok

- Use GLM 5.3 FlashX to turn the business notes I paste next into a six-slide outline for managers. Give each slide one conclusion, supporting evidence, and speaker notes; flag missing evidence.
- Use GLM 5.3 FlashX to review the interface screenshots I provide. Rank the five most consequential layout problems and explain a specific correction for each.
- Use GLM 5.3 FlashX with maximum reasoning effort to compare the two research summaries I paste next. Separate agreement, conflicting claims, and assumptions, and cite the passages behind your findings.
- Use GLM 5.3 FlashX to extract decisions and action items from the meeting transcript I paste next. Return JSON containing the action, owner, deadline, and supporting excerpt; use null for missing details.
- Use GLM 5.3 FlashX to draft a product brief for a team scheduling tool. Include the main user flow, interaction states, and acceptance checks, and keep the final brief under 800 words.

## How to set up GLM 5.3 FlashX in Grok

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

### Use the Grok connector

1. **Add a custom connector**: In Grok open Settings › Connect Apps, then Add a custom connector. Name it Spiral, paste this URL, leave Headers empty and click Add MCP.

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

2. **Sign in to Spiral and approve**: Grok opens Spiral: sign in, pick the organization and click Authorize. Spiral gives the connection its own API key; Grok never sees it, and you can remove the connection under Settings › Connected apps.

3. **Check that it is connected**: Connect Apps › Custom shows Spiral as Connected. It works in every Grok chat and Grok bot.

### Use the Spiral skill

1. **Send Grok 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 FlashX**: 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-flashx",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

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

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

## GLM 5.3 FlashX tools and prices

- [Z.ai: GLM 5.3 FlashX](https://spiral.ai/tools/openrouter/z-ai/glm-5.3-flashx) (OpenRouter): Up to $0.006673 per run at the default inputs. $0.481 per 1M input tokens, $1.625 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| tools |  | — |  |
| top_k | 0 to … | — |  |
| top_p | 0 to 1 | — |  |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| max_tokens | 1 to 131072 | — | The most output tokens to generate. |
| temperature | 0 to 2 | — |  |

## What can you do with GLM 5.3 FlashX in Grok?

GLM 5.3 FlashX can turn supplied evidence into structured analysis and review visible work. State the audience, desired length, and checks the answer must pass.

### Implement a product interface

Turn a written product brief into frontend code, then use browser tools to inspect the result and revise visible problems.

### Review a rendered interface

Compare interface screenshots with the intended design and produce a prioritized list of layout and interaction fixes.

### Build a management presentation

Organize supplied business material into a slide narrative, then use document tools to create an editable presentation.

### Check report layout

Inspect rendered report pages for cropped content, overlapping elements, and inconsistent alignment before revising the document.

### Synthesize source material

Combine public information and supplied evidence into a research brief that separates reported facts, assumptions, and conclusions.

### Extract document data

Convert document text into a specified JSON structure, with explicit handling for missing values and source excerpts for verification.

## Overview

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

## GLM 5.3 FlashX in other agents

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

## More Grok guides

- [GLM 5.3 Flash](https://spiral.ai/integrations/grok/glm-5-3-flash)
- [GLM 5.3 FlashX Legal](https://spiral.ai/integrations/grok/glm-5-3-flashx-legal)
- [GLM 5.2 (batch)](https://spiral.ai/integrations/grok/glm-5-2-batch)
- [GLM 5.3 Prime](https://spiral.ai/integrations/grok/glm-5-3-prime)
- [GLM 4.7 Flash](https://spiral.ai/integrations/grok/glm-4-7-flash)
- [GLM Flash Latest](https://spiral.ai/integrations/grok/glm-flash-latest)

## Questions about GLM 5.3 FlashX in Grok

**Can Grok use GLM 5.3 FlashX?**

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

**How much does GLM 5.3 FlashX cost in Grok?**

Up to $0.006673 per run at the default inputs. $0.481 per 1M input tokens, $1.625 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Grok plan is separate.

**Do I need an OpenRouter account to use GLM 5.3 FlashX in Grok?**

No. Spiral runs GLM 5.3 FlashX 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 FlashX in Grok?**

About two minutes: add a custom connector, then sign in to Spiral and approve, then check that it is connected.

**Does Grok wait while GLM 5.3 FlashX runs?**

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

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

Use it for coding, visual review, and document workflows that involve several tool-assisted steps. Tasks with a clear result to inspect, such as a rendered interface or report, fit its visual feedback approach.

**How does GLM 5.3 FlashX differ from GLM 5.3 Flash?**

GLM 5.3 FlashX emphasizes faster inference for the multimodal coding model. Treat speed as the main documented distinction when choosing between them.

**How much can GLM 5.3 FlashX read and write?**

Z.ai lists a 1M-token context window and up to 128K output tokens. Its native output is text; workflows producing presentations or spreadsheets require tools to create those files.

**Can GLM 5.3 FlashX skip reasoning?**

Z.ai documents forced thinking for GLM 5.3 Flash, including the FlashX offering described on its model page. For brief tasks, request a concise final answer instead of assuming reasoning can be switched off.

**Which settings should I start with?**

Start with Z.ai's recommended temperature of 1, top-p of 0.95, and maximum reasoning effort. Judge the result against a concrete task before changing those settings.

