How to Use Grok 4.7 in dots
Grok 4.7 suits difficult coding tasks and document work that require several passes and verification. Compared with Grok 4.6, it has stronger self-checking and more training on tasks that take hours to complete.
Prompts to try with Grok 4.7 in dots
Copy an example into dots, or ask in your own words.
Every Monday, use Grok 4.7 to compare the supplied weekly project updates with the previous review. Return completed work, new blockers, and decisions needed in under 500 words. Cite the dated update behind each point.
Each morning, use Grok 4.7 to review the supplied incident summaries. Group repeated symptoms, identify possible shared causes, and separate evidence from hypotheses. Return the three investigations most worth pursuing.
Each Friday, use Grok 4.7 to turn the supplied product research summaries into a six-slide review outline. Include one decision per slide and the evidence needed to support it. Flag missing evidence.
Every night, use Grok 4.7 with high reasoning effort to compare the supplied requirements updates with the current approved specification. Report contradictions, affected requirements, and decisions needed in a consistent table.
Each week, use Grok 4.7 to review the supplied engineering progress summaries against the milestone plan. Draft a brief covering completed milestones, dependencies at risk, and questions for the next review.
How to set up Grok 4.7 in dots
Pick the way that suits you. Each takes about two minutes.
Use the Spiral skill
- Send dots 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 your dot. Copy it.
- Send your dot this message
Your dot reads Spiral's skill and asks for your API key.
set up https://spiral.ai/SKILL.md
- Give your dot the key
When your dot asks for the key, add it where your dot 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 4.7
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-4.7", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: dots finds Grok 4.7 on Spiral, shows the price and runs it.
Grok 4.7 providers and prices
Spiral runs Grok 4.7 through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.03204 per run at the default inputs. $2.60 per 1M input tokens, $7.80 per 1M output tokens.
Settings you can ask for
Ask dots 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 450000 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Reasoning effort | low, medium, high, or xhigh | high | How much the model reasons. |
Every API field of SpaceXAI: Grok 4.7 is on its tool page: open its card above.
What can you do with Grok 4.7 in dots?
Grok 4.7 can turn recurring updates into consistent reviews of progress, blockers, and unresolved requirements. Give each run dated inputs and a fixed reporting structure so changes remain easy to compare.
Fix a bug across several files
Use Grok 4.7 to trace a failure through related code, propose a focused patch, and check the result against a regression test.
Plan and carry out a code migration
Give Grok 4.7 the old behavior, target requirements, and compatibility constraints. Ask for staged changes with checks after each stage.
Review a technical design
Ask Grok 4.7 to compare a proposed design against explicit requirements, identify unresolved decisions, and explain which evidence supports each concern.
Turn source material into a decision brief
Have Grok 4.7 organize supplied research into options, supporting evidence, tradeoffs, and a recommendation with stated assumptions.
Draft a presentation from a report
Ask Grok 4.7 for slide titles, evidence, and speaker notes tailored to a named audience. Require every factual point to trace back to the supplied report.
Reconcile conflicting requirements
Use Grok 4.7 to compare lengthy specifications, locate contradictions, and draft a decision log that separates agreed requirements from open questions.
Prepare a recurring project review
Give Grok 4.7 dated progress updates and the previous review. Ask for changes, unresolved blockers, and decisions needed, with evidence for each entry.
More on Grok 4.7 and dots
Overview
Grok 4.7 in other agents
More dots guides
Questions about Grok 4.7 in dots
Can dots use Grok 4.7?
Yes. Add Spiral to dots as an MCP server, and dots can find and run Grok 4.7 like any built-in tool.
How much does Grok 4.7 cost in dots?
Up to $0.03204 per run at the default inputs. $2.60 per 1M input tokens, $7.80 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your dots plan is separate.
Do I need an OpenRouter account to use Grok 4.7 in dots?
You need no OpenRouter account. dots uses one Spiral API key for every tool, and Spiral runs Grok 4.7 on its own OpenRouter account.
How long does it take to set up Grok 4.7 in dots?
About two minutes: create an API key, then send your dot this message, then give your dot the key.
Does dots wait while Grok 4.7 runs?
Grok 4.7 runs in the background. dots starts the run, checks on it and gives you the text, json when it's ready.
What is Grok 4.7 best suited for?
Difficult coding tasks and knowledge work that require multiple steps and verification. The maker also reports improvements in creating documents and presentations.
How does Grok 4.7 differ from Grok 4.6?
Grok 4.7 uses a larger base model and received more training on harder tasks that take hours to complete. Its documented improvements include stronger self-checking and more reliable handling of long context.
How much context can Grok 4.7 handle?
The maker documents a 500,000-token context window. For a long review, ask for a concise result with references to the supplied material.
How long can a Grok 4.7 answer be?
The maker's guide lists no separate text-output limit. Context and request limits still apply, so specify the length you need instead of asking for the longest possible answer.
Does Grok 4.7 know current events?
Its documented knowledge cutoff is May 2026, and training alone does not provide real-time information. Supply dated evidence when a task depends on recent changes.
Start using Grok 4.7 in dots
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into dots:
set up https://spiral.ai/SKILL.md


