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

Claude Code · LLMReleased 2026-09-23

How to Use GLM 5.3 Prime in Claude Code

GLM 5.3 Prime is built for coding, technical conversations, and tasks that need several rounds of tool use. It retains GLM 5.3’s capabilities while accelerating output generation, with a reported 1.5–2× increase in output throughput.

Prompts to try with GLM 5.3 Prime in Claude Code

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

Use GLM 5.3 Prime with maximum reasoning to investigate the failing tests in this repository. Reproduce one failure, fix its cause, and run the relevant checks. Summarize the change and test results.

GLM 5.3 PrimeClaude Code
Try asking
  • Use GLM 5.3 Prime to inspect this project's authentication code. Trace session expiration, identify inconsistent behavior, and add a regression test for any confirmed bug before fixing it.

  • Use GLM 5.3 Prime to review the API specification in this repository and implement a typed client. Cover documented errors and pagination, and test against the existing fixtures.

  • Use GLM 5.3 Prime to plan a migration from the deprecated library used in this project. Inspect its actual usage, list compatibility risks, and propose a sequence of changes with acceptance checks.

  • Use GLM 5.3 Prime to analyze the benchmark results and relevant code in this project. Identify one measurable bottleneck, implement a focused improvement, and compare correctness and performance before and after.

How to set up GLM 5.3 Prime in Claude Code

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

Use Spiral's MCP server

  1. Add the hosted server

    This adds Spiral to the current project. Add --scope user to use it in every project.

    claude mcp add --transport http spiral https://api.spiral.ai/mcp
  2. Sign in

    Start claude, type /mcp, choose spiral and Authenticate. Sign in to Spiral in the browser and click Authorize. No API key.

Use the Spiral skill

  1. Send Claude Code 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 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 5.3 Prime

    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-5.3-prime",
        "input": {
          "messages": [
            {
              "role": "system"
            }
          ]
        }
      }'

Then paste one of the prompts above: Claude Code finds GLM 5.3 Prime on Spiral, shows the price and runs it.

GLM 5.3 Prime providers and prices

Spiral runs GLM 5.3 Prime through OpenRouter. Open a card for today's price, with every fee included.

OpenRouterLLM
Z.ai: GLM 5.3 Prime
z-ai/glm-5.3-prime

Settings you can ask for

Ask Claude Code 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
Reasoning effortlow, high, or maxmax

How much the model reasons.

Frequency penalty-2 to 2

Every API field of Z.ai: GLM 5.3 Prime is on its tool page: open its card above.

What can you do with GLM 5.3 Prime in Claude Code?

GLM 5.3 Prime can help carry a code change through investigation, implementation, and verification. Give it the relevant project files and acceptance checks so the work ends with a reviewable result.

Fix a reproducible bug

Give GLM 5.3 Prime the failure, relevant code, and expected behavior. Ask for a reproduction, a focused correction, and evidence that the correction works.

Plan a code migration

Ask GLM 5.3 Prime to map dependencies, identify compatibility risks, and divide a migration into changes with explicit acceptance checks.

Design regression tests

Have GLM 5.3 Prime turn a bug report or behavior specification into test cases covering ordinary inputs, boundary conditions, and failure paths.

Draft an API client

Provide a textual API specification and ask GLM 5.3 Prime for client code, response handling, and tests tied to documented behavior.

Triage technical incidents

Give GLM 5.3 Prime timestamped logs and deployment notes. Request an evidence-based timeline, competing explanations, and the next diagnostic checks.

Extract structured records

Ask GLM 5.3 Prime to convert supplied text into JSON using an explicit structure. Validate required properties and types before passing the records onward.

Compare implementation approaches

Ask GLM 5.3 Prime to evaluate technical approaches against stated requirements and explain which assumptions could change the recommendation.

Questions about GLM 5.3 Prime in Claude Code

Can Claude Code use GLM 5.3 Prime?

Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run GLM 5.3 Prime like any built-in tool.

How much does GLM 5.3 Prime cost in Claude Code?

Up to $0.046986 per run at the default inputs. $3.64 per 1M input tokens, $11.44 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude Code plan is separate.

Do I need an OpenRouter account to use GLM 5.3 Prime in Claude Code?

No. Spiral runs GLM 5.3 Prime 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 5.3 Prime in Claude Code?

About two minutes: add the hosted server, then sign in.

Does Claude Code wait while GLM 5.3 Prime runs?

GLM 5.3 Prime runs in the background. Claude Code starts the run, checks on it and gives you the text, json when it's ready.

How does GLM 5.3 Prime differ from GLM 5.3?

Prime accelerates output generation while retaining GLM 5.3’s capabilities. The reported improvement is 1.5–2× output throughput, rather than a separate increase in reasoning quality.

How much text can GLM 5.3 Prime handle?

It supports a 1M-token context window and up to 128K output tokens. For a large task, ask for a specific deliverable, such as a migration plan or a focused patch, rather than an unrestricted response.

Can GLM 5.3 Prime read screenshots or generate images?

GLM 5.3 Prime accepts text and produces text. Provide error messages, extracted text, or a written description when the original material is visual.

Can I turn reasoning off?

Reasoning stays enabled. You can choose low, high, or maximum reasoning effort; maximum is the default.

Can GLM 5.3 Prime return reliable JSON?

It can return JSON, but JSON-schema enforcement is not supported. Describe the required structure, then validate the result before using it in an automated workflow.

Get started

Start using GLM 5.3 Prime in Claude Code

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

Paste this into Claude Code:

Set up Claude Code

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