How to Use Mistral Large 4 in Grok Build
Mistral Large 4 suits repository work, defensive security investigations, and questions across long documents. Its adjustable reasoning and 1 million-token context support tasks that need several steps and substantial source material.
Prompts to try with Mistral Large 4 in Grok Build
Copy an example into Grok Build, or ask in your own words.
Use Mistral Large 4 with high reasoning to trace this project's authentication flow. Cite the relevant files and functions, then identify where an expired session is rejected.
Use Mistral Large 4 to investigate the failing test in this repository. Explain the cause, make a focused fix, and run the relevant checks.
Use Mistral Large 4 with high reasoning to review this project's upload handler for path traversal. Report the evidence and propose a patch with a regression test.
Use Mistral Large 4 to compare the API documentation with the implementation. List discrepancies with file references and suggest corrections.
Use Mistral Large 4 with medium reasoning to explain the changed code in this branch. Return a concise reviewer guide covering behavior, assumptions, and verification.
How to set up Mistral Large 4 in Grok Build
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Add --scope project to add Spiral to the current repository only. No header and no client ID or secret: Grok registers itself with Spiral.
grok mcp add --transport http spiral https://api.spiral.ai/mcp
- Sign in
Start grok and run /mcps. Select Spiral and press i. Your browser opens: sign in to Spiral, pick the organization and click Authorize. No API key.
- Check it
grok mcp doctor spiral
Use the Spiral skill
- Send Grok Build 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 Mistral Large 4
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": "mistralai/mistral-large-4-0", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Grok Build finds Mistral Large 4 on Spiral, shows the price and runs it.
Mistral Large 4 providers and prices
Spiral runs Mistral Large 4 through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.011216 per run at the default inputs. $0.91 per 1M input tokens, $2.73 per 1M output tokens.
Settings you can ask for
Ask Grok Build for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Top p | 0 to 1 | ||
| Logprobs | on or off | ||
| Max tokens | 1 to 262144 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Top logprobs | 0 to 20 | ||
| Presence penalty | -2 to 2 | ||
| Reasoning effort | none or high | high | How much the model reasons. |
| Frequency penalty | -2 to 2 |
Every API field of Mistral: Mistral Large 4 is on its tool page: open its card above.
What can you do with Mistral Large 4 in Grok Build?
Turn repository context into explanations, proposed patches, and targeted checks with Mistral Large 4. Use it to trace behavior across files and develop a reviewable change.
Explain an unfamiliar repository
Trace a request through the code, identify the relevant modules, and produce an explanation with file references.
Investigate a software defect
Compare a bug report with the implementation, propose a focused patch, and identify tests that distinguish the fix from the previous behavior.
Review defensive security findings
Analyze supplied findings and code excerpts, explain the suspected weakness, and draft remediation steps for review.
Answer questions across documents
Compare supplied policy or technical documents and return answers with supporting passages and unresolved contradictions.
Extract consistent records
Turn supplied correspondence or document text into structured records, with missing values marked explicitly.
Prepare multilingual summaries
Summarize material written in several languages in one requested language, preserving names, dates, and specified terminology.
Compare financial explanations
Read supplied financial report excerpts, summarize changes between reporting periods, and separate stated explanations from proposed interpretations.
More on Mistral Large 4 and Grok Build
Overview
Mistral Large 4 in other agents
Questions about Mistral Large 4 in Grok Build
Can Grok Build use Mistral Large 4?
Yes. Add Spiral to Grok Build as an MCP server, and Grok Build can find and run Mistral Large 4 like any built-in tool.
How much does Mistral Large 4 cost in Grok Build?
Up to $0.011216 per run at the default inputs. $0.91 per 1M input tokens, $2.73 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Grok Build plan is separate.
Do I need an OpenRouter account to use Mistral Large 4 in Grok Build?
No. Spiral runs Mistral Large 4 on its own OpenRouter account. You sign in to Spiral once and never paste a key.
How long does it take to set up Mistral Large 4 in Grok Build?
About two minutes: add the server, then sign in, then check it.
Does Grok Build wait while Mistral Large 4 runs?
Mistral Large 4 runs in the background. Grok Build starts the run, checks on it and gives you the text, json when it's ready.
What is Mistral Large 4 useful for?
Use it for repository questions, coding tasks, document analysis, and workflows that combine evidence with tool results. Finance and legal document review are documented applications.
How much context can Mistral Large 4 handle?
Mistral documents a 1 million-token context window. That figure describes context capacity, rather than the length of the final answer.
Can I turn off reasoning?
Mistral Large 4 always reasons. Choose low effort for simple requests, medium for everyday work, and high for difficult analysis.
Why might a response end before the answer?
Reasoning consumes the generation budget alongside the final answer. If the budget is too small, the response can finish during reasoning; allow more room or use less reasoning for a simpler task.
Can Mistral Large 4 work across languages?
Its training covered more than 160 languages, including every official EU language. For multilingual work, specify the desired answer language and supply a glossary for terms that must stay consistent.
Start using Mistral Large 4 in Grok Build
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Grok Build:
set up https://spiral.ai/SKILL.md


