How to Use GLM Flash Latest in Claude Code
Use GLM Flash Latest for coding, document analysis, and structured extraction. It currently points to GLM 5.3 Flash and follows future Flash releases, so its behavior can change over time.
Prompts to try with GLM Flash Latest in Claude Code
Copy an example into Claude Code, or ask in your own words.
Use GLM Flash Latest to inspect this project's failing tests, trace one reproducible defect, implement a focused fix, and run the relevant tests.
Use GLM Flash Latest to build the settings page described in the project brief. Follow existing components, render the page, and test saving and validation.
Use GLM Flash Latest to implement a small Godot game from the gameplay specification. Verify movement, scoring, and a complete win or loss sequence.
Use GLM Flash Latest to add a contact-extraction function to this project. Return typed JSON, handle missing details explicitly, and test malformed input.
Use GLM Flash Latest to review the report-generation code. Trace source data into the output, check calculations, and identify unsupported conclusions.
How to set up GLM Flash Latest in Claude Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- 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
- 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
- Send Claude Code this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- 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
- Create an API key
In the console, under API keys.
- Run GLM Flash Latest
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-flash-latest", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Claude Code finds GLM Flash Latest on Spiral, shows the price and runs it.
GLM Flash Latest providers and prices
Spiral runs GLM Flash Latest through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.00042 per run at the default inputs. $0.05187 per 1M input tokens, $0.10192 per 1M output tokens.
Settings you can ask for
Ask Claude Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Min p | 0 to 1 | ||
| Top k | a whole number from 0 | ||
| Top p | 0 to 1 | ||
| Logprobs | on or off | ||
| Max tokens | 1 to 131072 | The most output tokens to generate. On a reasoning model the reasoning tokens count toward it: a cap too low for the effort can end with no answer (finish_reason length). | |
| Temperature | 0 to 2 | ||
| Top logprobs | 0 to 20 | ||
| Presence penalty | -2 to 2 | ||
| Reasoning effort | low, high, or max | max | How much the model reasons. |
| Frequency penalty | -2 to 2 | ||
| Repetition penalty | 0 to 2 | ||
| Parallel tool calls | on or off |
Every API field of Z.ai: GLM Flash Latest is on its tool page: open its card above.
What can you do with GLM Flash Latest in Claude Code?
Build and revise working software with GLM Flash Latest using the project's code and test results. For interfaces and games, include rendering and interaction checks before accepting the result.
Investigate a code defect
Use GLM Flash Latest to trace a reported failure, propose a focused patch, and check it against a reproducible test.
Build an interface from a written brief
Turn page requirements into frontend code, then inspect the rendered pages and test the requested interactions.
Prototype a playable game
Start with written gameplay rules and a small scope. Ask for movement, scoring, and win or loss conditions, followed by a complete playthrough.
Prepare a management report
Organize supplied business material into conclusions, supporting evidence, and unresolved questions for a named audience.
Extract records from text
Convert contact details, product descriptions, or event announcements into structured JSON with explicit missing-value rules.
Compare financial disclosures
Analyze supplied earnings material, distinguish disclosed figures from assumptions, and trace conclusions back to their sources.
More on GLM Flash Latest and Claude Code
Overview
GLM Flash Latest in other agents
More Claude Code guides
Questions about GLM Flash Latest in Claude Code
Can Claude Code use GLM Flash Latest?
Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run GLM Flash Latest like any built-in tool.
How much does GLM Flash Latest cost in Claude Code?
Up to $0.00042 per run at the default inputs. $0.05187 per 1M input tokens, $0.10192 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 Flash Latest in Claude Code?
No. Spiral runs GLM Flash Latest 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 Flash Latest in Claude Code?
About two minutes: add the hosted server, then sign in.
Does Claude Code wait while GLM Flash Latest runs?
GLM Flash Latest runs in the background. Claude Code starts the run, checks on it and gives you the text, json when it's ready.
Is GLM Flash Latest a fixed model?
No. It currently points to GLM 5.3 Flash and follows future GLM Flash releases. Recheck important workflows when that target changes.
What is GLM Flash good at?
The current GLM 5.3 Flash target is designed for coding and agent tasks. Z.ai also documents document processing, Office work, and financial research.
How much text can GLM Flash handle?
The current GLM 5.3 Flash target has a 1,048,576-token context window and supports up to 131,072 completion tokens. These limits can change when GLM Flash Latest moves to another release.
Can I turn off GLM Flash's thinking?
Thinking cannot be disabled in the current GLM 5.3 Flash target. It offers low, high, and max reasoning effort, with max as the default.
Can GLM Flash return structured JSON?
Yes, the current GLM 5.3 Flash target supports structured output using a JSON schema. Define the expected fields, types, and rules, then validate the result before using it.
Start using GLM Flash Latest 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 https://spiral.ai/SKILL.md


