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

Instinct · LLMReleased 2026-02-11

How to Use GLM-5 in Instinct

GLM-5 is built for complex software engineering, including backend architecture, debugging, and tasks with several stages. Compared with GLM-5 Turbo's focus on persistent tool workflows, GLM-5 targets broader systems engineering.

Prompts to try with GLM-5 in Instinct

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

Use GLM-5 every Monday to review the latest CI results and open bug reports. Identify repeated failures, cite the relevant runs, and propose the three most useful investigations.

GLM-5Instinct
Try asking
  • Use GLM-5 each Friday to review new official release notes for the dependencies we track. Summarize relevant changes with source links and retain a short list of unanswered compatibility questions.

  • Every Monday at 9am: ask GLM-5 through Spiral to review the diff on this branch and list the three riskiest changes.

  • Get a second opinion from GLM-5 on this function, then tell me what the call cost.

  • Summarize these release notes with GLM-5 in five bullet points.

How to set up GLM-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-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-5",
        "input": {
          "messages": [
            {
              "role": "system"
            }
          ]
        }
      }'

Then paste one of the prompts above: Instinct finds GLM-5 on Spiral, shows the price and runs it.

GLM-5 providers and prices

Spiral runs GLM-5 through OpenRouter. Open a card for today's price, with every fee included.

OpenRouterLLM
Z.ai: GLM 5
z-ai/glm-5

Settings you can ask for

Ask Instinct for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Seeda whole number
Top ka whole number from 0
Top p0 to 1
Logprobson or off
Max tokens1 to 131072

The most output tokens to generate.

Temperature0 to 2
Top logprobs0 to 20
Presence penalty-2 to 2
Frequency penalty-2 to 2
Repetition penalty0 to 2

Every API field of Z.ai: GLM 5 is on its tool page: open its card above.

What can you do with GLM-5 in Instinct?

Produce recurring briefs from tool results and carry unfinished work into the next run. Give GLM-5 a clear reporting period, a compact record of prior findings, and a specific stopping point.

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.

Questions about GLM-5 in Instinct

Can Instinct use GLM-5?

Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run GLM-5 like any built-in tool.

How much does GLM-5 cost in Instinct?

Up to $0.017086 per run at the default inputs. $1.30 per 1M input tokens, $4.16 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-5 in Instinct?

You need no OpenRouter account. Instinct uses one Spiral API key for every tool, and Spiral runs GLM-5 on its own OpenRouter account.

How long does it take to set up GLM-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-5 runs?

GLM-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-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.

Get started

Start using GLM-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