How to Use GLM 5.3 Flash in Windsurf
GLM 5.3 Flash suits coding, document analysis, and tasks that require several tool calls. Its 1M-token context supports large reference sets, while adjustable reasoning helps tailor the work to the task.
Prompts to try with GLM 5.3 Flash in Windsurf
Copy an example into Windsurf, or ask in your own words.
Use GLM 5.3 Flash with maximum reasoning effort to implement the checkout form described in this project's requirements. Cover validation, submission, success, and failure states, then run the relevant checks.
Use GLM 5.3 Flash to build a playable Godot prototype in this repository: move a character, collect five objects, track the score, and show a completion screen. Verify one complete playthrough.
Use GLM 5.3 Flash to write a Blender script for a desk scene with a lamp, notebook, and mug. Use meters, define one camera, render a preview with the available tools, and report anything you could not verify.
Use GLM 5.3 Flash to turn this repository's reporting requirements into a script that creates an editable spreadsheet. Include formulas, sample data clearly labeled as examples, and checks for broken references.
Use GLM 5.3 Flash to extract requirements from the project's specification into JSON. For each requirement, include its source section, acceptance condition, and unresolved questions; validate the result against a schema.
How to set up GLM 5.3 Flash in Windsurf
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Open the Customize page from the Agents window and click MCPs. Under This computer, open the config file, or edit it directly: ~/.config/devin/mcp_config.json on macOS and Linux, %APPDATA%\devin\mcp_config.json on Windows. Add this:
{ "mcpServers": { "spiral": { "url": "https://api.spiral.ai/mcp" } } } - Sign in
Click Authenticate on the Spiral server in Customize › MCPs, or let the agent call Spiral once: your browser opens. Sign in to Spiral, pick the organization and click Authorize. No API key.
devin mcp login spiral
- Check it
Spiral is listed under This computer in Customize › MCPs. From the terminal:
devin mcp list
Use the Spiral skill
- Send Windsurf this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run GLM 5.3 Flash
One request; the result comes back by polling or a webhook.
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-flash", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Windsurf finds GLM 5.3 Flash on Spiral, shows the price and runs it.
GLM 5.3 Flash providers and prices
Spiral runs GLM 5.3 Flash through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.00042 per run at the default inputs. $0.05187 per 1M input tokens, $0.10192 per 1M output tokens.
Settings you can ask for
Ask Windsurf for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Min p | 0 to 1 | ||
| Top k | a whole number from 0 | ||
| Top p | 0 to 1 | ||
| Logprobs | on or off | ||
| Max tokens | 1 to 943717 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Top logprobs | 0 to 20 | ||
| Presence penalty | -2 to 2 | ||
| Reasoning effort | low, high, or max | max | How much the model reasons. |
| Frequency penalty | -2 to 2 | ||
| Repetition penalty | 0 to 2 | ||
| Parallel tool calls | on or off |
Every API field of Z.ai: GLM 5.3 Flash is on its tool page: open its card above.
What can you do with GLM 5.3 Flash in Windsurf?
GLM 5.3 Flash can turn a project brief into code and use tool results to guide revisions. Give it a small deliverable with clear acceptance checks.
Frontend implementation
Use GLM 5.3 Flash to turn a written product brief into a working interface, with explicit requirements for navigation, forms, and error states.
Playable game prototypes
Ask GLM 5.3 Flash to implement a small game with movement, scoring, and a complete win or loss condition.
Blender scene scripts
Have GLM 5.3 Flash write scene-building code from a description of the objects, dimensions, lighting, and camera position.
Management presentation drafts
Use GLM 5.3 Flash to organize supplied business information into slide titles, supporting evidence, chart specifications, and speaker notes.
Earnings research
Ask GLM 5.3 Flash to compare supplied earnings disclosures, separating reported numbers from assumptions and proposed explanations.
Document comparison
Use GLM 5.3 Flash to compare two supplied texts and list changed requirements, conflicting statements, and questions requiring clarification.
Structured information extraction
Have GLM 5.3 Flash turn supplied text into JSON records with source excerpts and explicit missing values.
More on GLM 5.3 Flash and Windsurf
Overview
GLM 5.3 Flash in other agents
Questions about GLM 5.3 Flash in Windsurf
Can Windsurf use GLM 5.3 Flash?
Yes. Add Spiral to Windsurf as an MCP server, and Windsurf can find and run GLM 5.3 Flash like any built-in tool.
How much does GLM 5.3 Flash cost in Windsurf?
Up to $0.00042 per run at the default inputs. $0.05187 per 1M input tokens, $0.10192 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Windsurf plan is separate.
Do I need an OpenRouter account to use GLM 5.3 Flash in Windsurf?
No. Spiral runs GLM 5.3 Flash 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 Flash in Windsurf?
About two minutes: add the server, then sign in, then check it.
Does Windsurf wait while GLM 5.3 Flash runs?
GLM 5.3 Flash runs in the background. Windsurf starts the run, checks on it and gives you the text, json when it's ready.
What is GLM 5.3 Flash useful for?
Z.ai documents coding, Office work, financial research, and document processing. Start with a concrete deliverable, such as a working page, a report outline, or extracted records.
How much text can GLM 5.3 Flash handle?
Published specifications list a 1M-token context and up to 128K output tokens. Treat these as separate limits; a large reference set does not mean the response can be equally long.
Can I turn off reasoning?
No. GLM 5.3 Flash always uses reasoning; choose low, high, or maximum effort to control its reasoning budget.
Can GLM 5.3 Flash create finished spreadsheets or presentations?
Its direct output is text. An agent needs document creation tools to turn that output into a spreadsheet or presentation.
How should I request structured results?
Specify the JSON structure, required values, and how to represent missing information. Include a small example when the format has rules that could be interpreted differently.
Start using GLM 5.3 Flash in Windsurf
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Windsurf:
set up https://spiral.ai/SKILL.md


