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

# How to Use GLM 5.3 FlashX in Cursor

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 Cursor

- Use GLM 5.3 FlashX to implement the settings page described in this project's product brief. Follow the existing components, test the main interactions, and inspect the rendered page before reporting remaining issues.
- Use GLM 5.3 FlashX to compare the reference screenshots in this repository with the running app. Fix the three largest layout differences and capture the result for review.
- Use GLM 5.3 FlashX with maximum reasoning effort to trace the failing checkout flow. Read the relevant code, reproduce the failure, make a focused fix, and verify the full interaction.
- Use GLM 5.3 FlashX to build a document extraction workflow in this project. Define the expected JSON structure, preserve source excerpts, and validate required fields before accepting a result.
- Use GLM 5.3 FlashX to create a presentation from the research notes in this repository. Use the available document tools, render each slide, and fix overflow or overlapping elements.

## How to set up GLM 5.3 FlashX in Cursor

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

### Use Spiral's MCP server

1. **Add the hosted server**: Use Add to Cursor on the console's Agents & MCP page, or add this to `.cursor/mcp.json` (one project) or `~/.cursor/mcp.json` (every project):

```json
{
  "mcpServers": {
    "spiral": { "url": "https://api.spiral.ai/mcp" }
  }
}
```

2. **Sign in**: Open Cursor Settings › MCP, click Connect next to spiral, sign in to Spiral and click Authorize. No API key. Spiral then shows as connected, with its tools listed.

### Use the Spiral skill

1. **Send Cursor 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: Cursor finds GLM 5.3 FlashX on Spiral, shows the price and runs it.

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

## 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 Cursor?

GLM 5.3 FlashX can take a coding task through implementation and visual review. Give the agent project context and clear acceptance checks, then ask it to inspect the running result.

### 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 Cursor guides](https://spiral.ai/integrations/cursor)

## 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)
- [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](https://spiral.ai/integrations/grok/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 Cursor guides

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

## Questions about GLM 5.3 FlashX in Cursor

**Can Cursor use GLM 5.3 FlashX?**

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

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

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 Cursor plan is separate.

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

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 Cursor?**

About two minutes: add the hosted server, then sign in.

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

GLM 5.3 FlashX runs in the background. Cursor 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.

