How to Use GLM 5.3 Prime in Instinct
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 Instinct
Copy an example into Instinct, or ask in your own words.
Each morning, use GLM 5.3 Prime to review the incident records available through your connected tools. Summarize new failures, recurring symptoms, and unresolved questions, with record identifiers supporting every finding.
Every weekday, use GLM 5.3 Prime to review newly reported bugs through your connected issue tracker. Identify likely duplicates, explain the shared symptoms, and draft reproduction steps where the reports contain enough detail.
Each week, use GLM 5.3 Prime with maximum reasoning to compare dependency release notes against the service inventory available through your connected tools. Report relevant breaking changes and propose verification checks.
Every evening, use GLM 5.3 Prime to analyze the day's test-run summaries available through your connected tools. Separate repeat failures from new failures and suggest the next diagnostic step for each new pattern.
Each Friday, use GLM 5.3 Prime to turn the week's technical discussion records into a decision summary. Include decisions, unresolved tradeoffs, owners, and supporting excerpts. Mark missing owners as unknown.
How to set up GLM 5.3 Prime in Instinct
Pick the way that suits you. Each takes about two minutes.
Use the Spiral skill
- Send Instinct 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 Spiral's MCP server
- Create an API key
In the console, open API keys and create a key for Instinct. Copy it.
- Send Instinct this message
Instinct reads Spiral's skill and asks for your API key.
set up https://spiral.ai/SKILL.md
- 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
- 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 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: Instinct 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.
Up to $0.028192 per run at the default inputs. $2.184 per 1M input tokens, $6.864 per 1M output tokens.
Settings you can ask for
Ask Instinct for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| 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. | |
| 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 |
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 Instinct?
GLM 5.3 Prime can support recurring technical reviews that turn fresh text into findings and next actions. Define the evidence to inspect and the report structure so each run produces comparable results.
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.
More on GLM 5.3 Prime and Instinct
Overview
GLM 5.3 Prime in other agents
More Instinct guides
Questions about GLM 5.3 Prime in Instinct
Can Instinct use GLM 5.3 Prime?
Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run GLM 5.3 Prime like any built-in tool.
How much does GLM 5.3 Prime cost in Instinct?
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 Instinct plan is separate.
Do I need an OpenRouter account to use GLM 5.3 Prime in Instinct?
You need no OpenRouter account. Instinct uses one Spiral API key for every tool, and Spiral runs GLM 5.3 Prime on its own OpenRouter account.
How long does it take to set up GLM 5.3 Prime in Instinct?
About two minutes: create an API key, then send Instinct this message, then give Instinct the key.
Does Instinct wait while GLM 5.3 Prime runs?
GLM 5.3 Prime runs in the background. Instinct 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.
Start using GLM 5.3 Prime in Instinct
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Instinct:
set up https://spiral.ai/SKILL.md


