How to Use Grok 4.20 in Instinct
Grok 4.20 fits document analysis, coding, and questions that require several logical steps. Enable reasoning for difficult problems; disable it for straightforward extraction or routine Q&A.
Prompts to try with Grok 4.20 in Instinct
Copy an example into Instinct, or ask in your own words.
Every weekday, use Grok 4.20 to summarize the operational updates supplied for the previous 24 hours. Return decisions, blockers, and next actions with source references; leave an owner unspecified when none is stated.
Each week, use Grok 4.20 with reasoning enabled to compare the supplied product announcements with the previous week's summary. Report substantive changes, supporting dates, and unresolved questions in under 600 words.
Each morning, use Grok 4.20 to extract order details from the newly supplied message text. Return consistent JSON records, preserve stated quantities, and mark missing values rather than inferring them.
Every Friday, use Grok 4.20 to summarize the supplied English and Spanish customer feedback. Keep a source reference for each theme, include contradictory feedback, and draft the report in English.
Each week, use Grok 4.20 with reasoning enabled to review the supplied migration status updates against the stated acceptance criteria. Identify unmet dependencies, rollback gaps, and evidence needed before the next milestone.
How to set up Grok 4.20 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 Grok 4.20
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": "x-ai/grok-4.20", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Instinct finds Grok 4.20 on Spiral, shows the price and runs it.
Grok 4.20 providers and prices
Spiral runs Grok 4.20 through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.01337 per run at the default inputs. $1.625 per 1M input tokens, $3.25 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 p | a number up to 1 | ||
| Max tokens | 1 to 1800000 | The most output tokens to generate. | |
| Temperature | 0 to 2 |
Every API field of SpaceXAI: Grok 4.20 is on its tool page: open its card above.
What can you do with Grok 4.20 in Instinct?
Grok 4.20 can turn recurring batches of supplied updates into consistent summaries and structured records. Define the reporting window, evidence requirements, and treatment of missing information so each run answers the same questions.
Compare technical proposals
Ask Grok 4.20 to compare competing proposals against explicit requirements, identify tradeoffs, and cite the passages supporting each conclusion.
Investigate a software defect
Use Grok 4.20 to trace a reported failure through relevant code, propose a cause, and design a regression test that would distinguish it from other explanations.
Extract document records
Have Grok 4.20 turn supplied invoice or order text into JSON records, preserving source values and marking missing information explicitly.
Synthesize research evidence
Give Grok 4.20 dated excerpts and ask for findings, disagreements, and unanswered questions, with a source reference beside each finding.
Check quantitative reasoning
Ask Grok 4.20 to examine a calculation, identify assumptions, check units, and explain which inputs would change the conclusion.
Translate support content
Use Grok 4.20 to draft translations in English, Spanish, Chinese, Arabic, or Hindi while preserving product names and a supplied glossary.
Draft evidence-based reports
Have Grok 4.20 turn supplied operational updates into a report with decisions, unresolved issues, and supporting evidence.
Review a migration plan
Ask Grok 4.20 to check dependencies, sequence work, identify rollback gaps, and propose acceptance checks against the stated requirements.
More on Grok 4.20 and Instinct
Overview
Grok 4.20 in other agents
More Instinct guides
Questions about Grok 4.20 in Instinct
Can Instinct use Grok 4.20?
Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run Grok 4.20 like any built-in tool.
How much does Grok 4.20 cost in Instinct?
Up to $0.01337 per run at the default inputs. $1.625 per 1M input tokens, $3.25 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 Grok 4.20 in Instinct?
You need no OpenRouter account. Instinct uses one Spiral API key for every tool, and Spiral runs Grok 4.20 on its own OpenRouter account.
How long does it take to set up Grok 4.20 in Instinct?
About two minutes: create an API key, then send Instinct this message, then give Instinct the key.
Does Instinct wait while Grok 4.20 runs?
Grok 4.20 runs in the background. Instinct starts the run, checks on it and gives you the text, json when it's ready.
What is Grok 4.20 useful for?
Grok 4.20 supports research, writing, coding, translation, and reasoning over supplied material. Good starting tasks include comparing technical proposals, explaining unfamiliar code, and turning document text into structured records.
How much context can Grok 4.20 handle?
The exact catalog listing reports 2 million tokens, while xAI's model page lists 1 million. These published limits disagree, so use 1 million tokens as a conservative planning ceiling; neither figure promises an answer of that length.
Which languages does Grok 4.20 support?
xAI names English, Chinese, Arabic, Hindi, and Spanish, plus several dozen others. Capability varies by language, so review terminology and meaning before publishing a translation.
How should I prompt Grok 4.20?
State the task, constraints, and required output directly. For example, ask for a comparison of three proposals using named criteria, a word limit, and a separate list of missing evidence.
Which settings are worth testing first?
Compare reasoning enabled and disabled on representative tasks. For sampling, xAI recommends temperature 0.7 and top-p 0.95; use those as a starting point.
Start using Grok 4.20 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


