Spiral gives your agent every tool with one account. Browse the tools →

Instinct · LLMReleased 2025-07-25

How to Use GLM-4.5 in Instinct

GLM-4.5 suits code fixes, complex reasoning, and tasks that require tools. Compared with GLM-4.5-Air, it uses a larger model; it offers thinking for harder tasks and direct responses for simpler requests.

Prompts to try with GLM-4.5 in Instinct

Copy an example into Instinct, or ask in your own words.

Each morning, use GLM-4.5 to review newly collected product release notes. Produce a brief with changed behavior, affected users, source links, and unanswered questions; omit repeated announcements.

GLM-4.5Instinct
Try asking
  • Each week, use GLM-4.5 to summarize incoming customer feedback by recurring problem. Include supporting quotations and counts from the supplied records, and distinguish requests from reported failures.

  • Every Friday, use GLM-4.5 to draft a six-slide team update from the week's status messages. Include completed work, blockers, next steps, and speaker notes without inventing progress.

  • Each day, use GLM-4.5 to extract action items from new meeting transcripts. Return JSON containing the action, owner, due date, and supporting quotation, with null for unstated details.

  • Each week, use GLM-4.5 with thinking enabled to compare new policy announcements with the previous announcements supplied to this run. Report conflicting statements with dates and source links.

How to set up GLM-4.5 in Instinct

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

Use the Spiral skill

  1. Send Instinct 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 Spiral's MCP server

  1. Create an API key

    In the console, open API keys and create a key for Instinct. Copy it.

  2. Send Instinct this message

    Instinct reads Spiral's skill and asks for your API key.

    set up https://spiral.ai/SKILL.md
  3. Give Instinct the key

    When Instinct asks for the key, add it where Instinct keeps secrets, never in the chat itself.

Use the Spiral CLI

  1. 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

  1. Create an API key

    In the console, under API keys.

  2. Run GLM-4.5

    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-4.5",
        "input": {
          "messages": [
            {
              "role": "system"
            }
          ]
        }
      }'

Then paste one of the prompts above: Instinct finds GLM-4.5 on Spiral, shows the price and runs it.

GLM-4.5 providers and prices

Spiral runs GLM-4.5 through OpenRouter. Open a card for today's price, with every fee included.

OpenRouterDeprecatedLLM
Z.ai: GLM 4.5
z-ai/glm-4.5

Settings you can ask for

Ask Instinct for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Top ka whole number from 0
Top p0 to 1
Max tokens1 to 98304

The most output tokens to generate.

Temperature0 to 2

Every API field of Z.ai: GLM 4.5 is on its tool page: open its card above.

What can you do with GLM-4.5 in Instinct?

Convert recurring information into consistent briefs and structured records with GLM-4.5. Define the evidence to inspect and the required output so each run answers the same practical question.

Fix a reproducible bug

Give GLM-4.5 the failing behavior, relevant code, and expected result. Ask for a focused fix and a regression check.

Build a working web prototype

Ask GLM-4.5 to turn a written specification into a web prototype with explicit user interactions and acceptance criteria.

Compare plans with competing constraints

Give GLM-4.5 the requirements and available choices. Request a comparison that identifies conflicts, assumptions, and unresolved questions.

Research a question across sources

Use GLM-4.5 with an agent's search tools to gather evidence, compare claims, and draft an answer with source links.

Extract structured records

Ask GLM-4.5 to turn supplied text into JSON using an explicit structure, required values, and a rule for missing information.

Draft a presentation

Give GLM-4.5 an audience, source material, and slide count. Request slide titles, supporting points, and speaker notes.

Review a long specification

Ask GLM-4.5 to identify conflicting requirements and unanswered questions in supplied text, citing the relevant sections.

Questions about GLM-4.5 in Instinct

Can Instinct use GLM-4.5?

Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run GLM-4.5 like any built-in tool.

How much does GLM-4.5 cost in Instinct?

Up to $0.011743 per run at the default inputs. $0.78 per 1M input tokens, $2.86 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Instinct plan is separate.

Do I need an OpenRouter account to use GLM-4.5 in Instinct?

You need no OpenRouter account. Instinct uses one Spiral API key for every tool, and Spiral runs GLM-4.5 on its own OpenRouter account.

How long does it take to set up GLM-4.5 in Instinct?

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

Does Instinct wait while GLM-4.5 runs?

GLM-4.5 runs in the background. Instinct starts the run, checks on it and gives you the text, json when it's ready.

What is GLM-4.5 useful for?

Use GLM-4.5 for code changes, complex reasoning, and tasks that combine analysis with tools. It also suits drafting presentation content and producing structured text.

How much text can GLM-4.5 handle?

Z.ai documents a 128K context window and up to 96K output tokens. Treat these as limits, and request a specific answer length for the task.

When should I use thinking mode?

Choose thinking for debugging, complex reasoning, and decisions involving tools. Use direct responses for straightforward requests such as rewriting a paragraph.

Where does GLM-4.5 fall short?

Code generation still needs verification. In Z.ai's CC-Bench comparison with Claude Sonnet 4, GLM-4.5 won 40.4%, tied 9.6%, and lost 50% of comparisons; ask for checks that demonstrate the requested behavior.

Can GLM-4.5 work in English and Chinese?

Yes. Z.ai's evaluation included English, Chinese, and other-language prompts; it does not establish equal performance across every language or task.

Get started

Start using GLM-4.5 in Instinct

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into Instinct:

Set up Instinct

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options