How to Use GLM-5 Turbo in Muse Code
GLM-5 Turbo is tuned for tasks that combine tool calls, detailed instructions, and sustained execution. Compared with GLM-5's broader engineering focus, it puts more emphasis on scheduled work and long sequences of actions.
Prompts to try with GLM-5 Turbo in Muse Code
Copy an example into Muse Code, or ask in your own words.
Use GLM-5 Turbo to implement pagination for the project's existing list endpoint. Follow the current conventions, check empty and final pages, and summarize the behavior you verified.
Use GLM-5 Turbo with thinking enabled to refactor the project's repeated validation code. Preserve existing behavior, work in small steps, and run relevant checks after each change.
Ask GLM-5 Turbo through Spiral to review the diff on this branch and list the three riskiest changes. Save the result in ./assets.
Get a second opinion from GLM-5 Turbo on this function, then tell me what the call cost.
Summarize these release notes with GLM-5 Turbo in five bullet points.
How to set up GLM-5 Turbo in Muse Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Install Muse Code
curl -fsSL https://dev.meta.ai/install.sh | bash
- Ask Muse to add the server
Start muse and ask:
Add the Spiral MCP server at https://api.spiral.ai/mcp
- Sign in
In your terminal, run:
muse mcp login spiral
Use the Spiral skill
- Send Muse Code 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 Turbo
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-turbo", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Muse Code finds GLM-5 Turbo on Spiral, shows the price and runs it.
GLM-5 Turbo providers and prices
Spiral runs GLM-5 Turbo through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.021354 per run at the default inputs. $1.56 per 1M input tokens, $5.20 per 1M output tokens.
Settings you can ask for
Ask Muse Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Top k | a whole number from 0 | ||
| Top p | 0 to 1 | ||
| Max tokens | 1 to 131072 | The most output tokens to generate. | |
| Temperature | 0 to 2 |
Every API field of Z.ai: GLM 5 Turbo is on its tool page: open its card above.
What can you do with GLM-5 Turbo in Muse Code?
Turn a project requirement or bug report into code changes with checks that demonstrate the result. GLM-5 can help trace dependencies and plan work across several files.
Reproduce and fix a backend bug
Give the agent a failing request, relevant logs, and expected behavior. Ask it to trace the cause, make a focused patch, and demonstrate the fix.
Plan a backend refactor
Map dependencies, identify behavior that must stay consistent, and divide the change into reviewable steps with acceptance checks.
Implement a feature from requirements
Turn a feature brief into an implementation plan, code changes, and a record of completed checks. State the expected user behavior before work begins.
Research a technical decision
Have the agent retrieve documentation, compare options against stated requirements, and produce a recommendation with supporting links and unresolved questions.
Extract records from text
Turn pasted notices, support requests, or meeting notes into consistently structured records. Define the expected structure and a rule for missing information.
Prepare a recurring operations brief
Combine recent tool results into a short report covering changes, unresolved problems, and next actions. Carry a compact summary between runs.
Investigate a data discrepancy
Ask the agent to compare reported totals, inspect relevant records through available tools, and explain which checks support its conclusion.
More on GLM-5 Turbo and Muse Code
Overview
GLM-5 Turbo in other agents
Questions about GLM-5 Turbo in Muse Code
Can Muse Code use GLM-5 Turbo?
Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run GLM-5 Turbo like any built-in tool.
How much does GLM-5 Turbo cost in Muse Code?
Up to $0.021354 per run at the default inputs. $1.56 per 1M input tokens, $5.20 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 Code plan is separate.
Do I need an OpenRouter account to use GLM-5 Turbo in Muse Code?
No. Spiral runs GLM-5 Turbo 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 Turbo in Muse Code?
About two minutes: install Muse Code, then ask Muse to add the server, then sign in.
Does Muse Code wait while GLM-5 Turbo runs?
GLM-5 Turbo runs in the background. Muse Code starts the run, checks on it and gives you the text, json when it's ready.
What is GLM-5 best suited for?
Use GLM-5 for software engineering and tasks that require planning, tool use, and several rounds of checking. GLM-5 emphasizes complex systems work; GLM-5 Turbo emphasizes persistent workflows with many actions.
How much text can GLM-5 handle?
Z.ai lists a 200K context window and a maximum output of 128K tokens for both GLM-5 and GLM-5 Turbo. Those figures describe capacity, so choose an answer length that fits the task.
When should I enable thinking?
Enable thinking for debugging, complex planning, and decisions with several constraints. Ask for a concise conclusion and verification evidence so the final answer stays useful.
How do I get useful JSON responses?
Specify the exact structure, required information, and how to handle missing values. Include a small example so the requested result is unambiguous.
How should I handle long research conversations?
Keep the current question, constraints, and relevant evidence in a compact working summary. The GLM-5 technical report found that accuracy can decline in extremely long contexts, so avoid carrying every old tool result forward.
Start using GLM-5 Turbo in Muse Code
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Muse Code:
set up https://spiral.ai/SKILL.md


