[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [GLM 4.5 Air](https://spiral.ai/integrations/instinct/glm-4-5-air)

# How to Use GLM 4.5 Air in Instinct

GLM 4.5 Air handles coding, tool use, and reasoning tasks. It uses a smaller design than GLM 4.5, with 106 billion total parameters and 12 billion active parameters.

|  |  |
| --- | --- |
| Model | GLM 4.5 Air |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.005867 per run at the default inputs. $0.26 per 1M input tokens, $1.43 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with GLM 4.5 Air in Instinct

- Every Monday, use GLM 4.5 Air to check the official PostgreSQL release notes for updates published in the previous seven days. Report the version, date, source link, and changes that may affect application behavior.
- Each morning, use GLM 4.5 Air with thinking enabled to compare newly received incident summaries with the previous day's summaries. Group recurring symptoms and separate observed evidence from proposed causes.
- Every Friday, use GLM 4.5 Air to review the week's incoming feature requests. Group requests by user need, include supporting quotations, and return at most five themes.
- Each day, use GLM 4.5 Air without thinking to label newly received support messages as bug, feature request, or question. Flag messages that do not clearly fit a label.
- Every Monday, use GLM 4.5 Air with thinking enabled to check the current task list for dependency conflicts and overlapping deadlines. Return a report under 500 words with the evidence behind each conflict.

## How to set up GLM 4.5 Air 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.

```text
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.

```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 4.5 Air**: 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-4.5-air",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

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

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

## GLM 4.5 Air tools and prices

- [Z.ai: GLM 4.5 Air](https://spiral.ai/tools/openrouter/z-ai/glm-4.5-air) (OpenRouter): Up to $0.004534 per run at the default inputs. $0.169 per 1M input tokens, $1.105 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| stop |  | — |  |
| tools |  | — |  |
| top_k | 0 to … | — |  |
| top_p | 0 to 1 | — |  |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |

## What can you do with GLM 4.5 Air in Instinct?

Turn recurring technical research and text review into scheduled reports. GLM 4.5 Air can use an agent's tools to gather evidence and reason through what changed.

### Fix a reproducible bug

Give GLM 4.5 Air the failure, relevant code, and expected behavior. Ask for a focused patch and a regression check.

### Build an interface from a written brief

Ask GLM 4.5 Air to turn requirements into working front-end code, including loading, empty, and error states.

### Explain code before changing it

Have GLM 4.5 Air trace a request through the relevant functions and identify where a proposed change belongs.

### Research a technical decision

Give GLM 4.5 Air a specific question and access to search tools. Request a comparison supported by primary sources.

### Check a plan against constraints

Ask GLM 4.5 Air to evaluate dependencies, capacity, and deadlines, then identify which assumptions could make the plan fail.

### Extract consistent records

Give GLM 4.5 Air a target JSON structure and source text. Require evidence for each extracted value and null for missing information.

## Overview

- [OpenRouter](https://spiral.ai/providers/openrouter)
- [All Instinct guides](https://spiral.ai/integrations/instinct)

## GLM 4.5 Air in other agents

- [Amp](https://spiral.ai/integrations/amp/glm-4-5-air)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/glm-4-5-air)
- [Claude](https://spiral.ai/integrations/claude-desktop/glm-4-5-air)
- [Claude Code](https://spiral.ai/integrations/claude-code/glm-4-5-air)
- [Cline](https://spiral.ai/integrations/cline/glm-4-5-air)
- [Codex](https://spiral.ai/integrations/codex/glm-4-5-air)
- [Cursor](https://spiral.ai/integrations/cursor/glm-4-5-air)
- [Devin](https://spiral.ai/integrations/devin/glm-4-5-air)
- [dots](https://spiral.ai/integrations/dots/glm-4-5-air)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/glm-4-5-air)
- [Gemini](https://spiral.ai/integrations/gemini/glm-4-5-air)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/glm-4-5-air)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/glm-4-5-air)
- [goose](https://spiral.ai/integrations/goose/glm-4-5-air)
- [Grok](https://spiral.ai/integrations/grok/glm-4-5-air)
- [Grok Build](https://spiral.ai/integrations/grok-build/glm-4-5-air)
- [Hermes](https://spiral.ai/integrations/hermes/glm-4-5-air)
- [Manus](https://spiral.ai/integrations/manus/glm-4-5-air)
- [Muse](https://spiral.ai/integrations/muse/glm-4-5-air)
- [Muse Code](https://spiral.ai/integrations/muse-code/glm-4-5-air)
- [n8n](https://spiral.ai/integrations/n8n/glm-4-5-air)
- [Notion](https://spiral.ai/integrations/notion/glm-4-5-air)
- [OpenClaw](https://spiral.ai/integrations/openclaw/glm-4-5-air)
- [opencode](https://spiral.ai/integrations/opencode/glm-4-5-air)
- [Perplexity](https://spiral.ai/integrations/perplexity/glm-4-5-air)
- [Raycast](https://spiral.ai/integrations/raycast/glm-4-5-air)
- [VS Code](https://spiral.ai/integrations/vscode/glm-4-5-air)
- [Windsurf](https://spiral.ai/integrations/windsurf/glm-4-5-air)
- [Zapier](https://spiral.ai/integrations/zapier/glm-4-5-air)

## More Instinct guides

- [Fugu Ultra v2](https://spiral.ai/integrations/instinct/fugu-ultra-v2)
- [GLM 4.7 Flash](https://spiral.ai/integrations/instinct/glm-4-7-flash)
- [Fugu Ultra](https://spiral.ai/integrations/instinct/fugu-ultra)
- [GLM 5.2 (batch)](https://spiral.ai/integrations/instinct/glm-5-2-batch)
- [Fugu Max](https://spiral.ai/integrations/instinct/fugu-max)
- [GLM 5.3 Flash](https://spiral.ai/integrations/instinct/glm-5-3-flash)

## Questions about GLM 4.5 Air in Instinct

**Can Instinct use GLM 4.5 Air?**

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

**How much does GLM 4.5 Air cost in Instinct?**

Up to $0.005867 per run at the default inputs. $0.26 per 1M input tokens, $1.43 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 Air in Instinct?**

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

**How long does it take to set up GLM 4.5 Air 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 Air runs?**

GLM 4.5 Air 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 Air good at?**

Its documented strengths include software engineering, front-end development, reasoning, and tool use. Try it for debugging, building a working interface from a written brief, or researching a question through an agent's search tools.

**How much text can GLM 4.5 Air handle?**

Z.ai documents a 128K context window and up to 96K output tokens. Treat these as ceilings; give each task a shorter target, such as a 500-word brief or one patch.

**When should I use thinking mode?**

Use thinking mode for difficult debugging, reasoning, and tasks involving several tools. Use non-thinking mode for straightforward requests such as labeling a short message or rewriting a sentence.

**Can GLM 4.5 Air analyze images or generate video?**

Z.ai documents text input and text output. For a visual task, provide a written description or extracted text and ask for code, analysis, or a script.

**Which languages should I start with?**

The model card lists English and Chinese. Start evaluations in those languages and check terminology against examples from your own work.

