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

Instinct · LLMReleased 2026-04-01

How to Use GLM-5V-Turbo in Instinct

GLM-5V-Turbo turns screenshots and designs into frontend code and helps diagnose visual bugs. It adds visual understanding to the text-based coding capabilities of GLM-5-Turbo.

Prompts to try with GLM-5V-Turbo in Instinct

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

Each morning, use GLM-5V-Turbo to compare the supplied dashboard capture with the previous capture. Report visible changes in labeled metrics, preserve their units, and flag unreadable values.

GLM-5V-TurboInstinct
Try asking
  • After each release, use GLM-5V-Turbo to compare the supplied checkout screenshots with the approved reference. Report visible layout differences by screen and rank them by impact on readability.

  • Every Friday, use GLM-5V-Turbo to review the supplied product screen captures. List overlapping components, clipped text, and alignment differences, with the image label for each observation.

  • For each new report supplied to this task, use GLM-5V-Turbo to draft a 300-word brief covering the main claim, supporting evidence, and limitations. Include page references and unanswered questions.

  • For each supplied interface recording, use GLM-5V-Turbo to summarize visible screen states in order. Keep observations separate from suspected problems and request further evidence where needed.

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

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

GLM-5V-Turbo providers and prices

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

OpenRouterLLM
Z.ai: GLM 5V Turbo
z-ai/glm-5v-turbo

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 131072

The most output tokens to generate.

Temperature0 to 2

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

What can you do with GLM-5V-Turbo in Instinct?

Turn recurring visual reviews into consistent reports with GLM-5V-Turbo. Use a fixed reference and reporting format to compare dashboard captures or interface screenshots across runs.

Implement a design reference

Use GLM-5V-Turbo to turn a screen design into frontend code. Specify which layout details must match and which interactions need implementation.

Diagnose visual interface bugs

Give GLM-5V-Turbo a broken screen and the expected appearance. Ask for visible defects, likely causes, and a focused repair plan.

Review a dashboard

Ask GLM-5V-Turbo to explain a dashboard screenshot, identify visible trends, and separate readable values from estimates.

Draft a document brief

Use GLM-5V-Turbo to turn a supplied report into a brief organized around a specific question. Request supporting page references and a list of unanswered questions.

Locate objects in visual evidence

Ask GLM-5V-Turbo to identify a described object in an image and return its bounding box. State the coordinate convention and ask it to flag ambiguous matches.

Compare a prototype with its design

Have GLM-5V-Turbo compare reference and implementation screenshots. Request a prioritized list of differences in spacing, alignment, colors, and component placement.

Summarize a recorded interface walkthrough

Use GLM-5V-Turbo to analyze a supplied screen recording and describe visible interface states. Request a concise sequence of observations and questions for further testing.

Questions about GLM-5V-Turbo in Instinct

Can Instinct use GLM-5V-Turbo?

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

How much does GLM-5V-Turbo cost in Instinct?

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 Instinct plan is separate.

Do I need an OpenRouter account to use GLM-5V-Turbo in Instinct?

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

How long does it take to set up GLM-5V-Turbo in Instinct?

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

Does Instinct wait while GLM-5V-Turbo runs?

GLM-5V-Turbo runs in the background. Instinct starts the run, checks on it and gives you the text, json when it's ready.

What is GLM-5V-Turbo best suited for?

Start with work that connects visual evidence to a concrete result: implementing a design, diagnosing a broken interface, or explaining a chart. Z.ai also identifies document analysis as a use.

Does GLM-5V-Turbo generate images or video?

Its documented output modality is text. It can analyze visual inputs and return explanations or code.

How much context and output does GLM-5V-Turbo support?

Z.ai documents a 200K context window and up to 128K output tokens. For practical tasks, request the specific deliverable you need instead of aiming for the maximum length.

What should I watch for during long visual tasks?

Images and video consume context more aggressively than text, and retaining visual details remains a challenge in long workflows. As a practical precaution, keep the key reference images available at verification checkpoints.

How should I prompt GLM-5V-Turbo for visual debugging?

Provide the broken screen, describe the expected behavior, and ask for observed defects before proposed causes. Request a separate check of the corrected screen against the reference.

Get started

Start using GLM-5V-Turbo 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