How to Use GPT-6 Sol in Cursor
GPT-6 Sol handles everyday coding, research, and tasks with several steps. Unlike GPT-6 Sol Pro, it uses standard reasoning mode, making it the starting choice for routine work.
Prompts to try with GPT-6 Sol in Cursor
Copy an example into Cursor, or ask in your own words.
Use GPT-6 Sol to investigate the failing tests in this repository. Find the cause, make the smallest justified fix, run the affected tests, and summarize the evidence that the fix works.
Use GPT-6 Sol to trace the checkout flow through this project's files. Explain where validation happens and identify the code that would need to change to support partial refunds.
Use GPT-6 Sol to implement the issue described in this project's task brief. Follow the existing conventions, check the acceptance criteria, and report any requirement the available code does not resolve.
Ask GPT-6 Sol through Spiral to review the diff on this branch and list the three riskiest changes. Save the result in ./assets.
Get a second opinion from GPT-6 Sol on this function, then tell me what the call cost.
How to set up GPT-6 Sol in Cursor
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
Use Add to Cursor on the console's Agents & MCP page, or add this to .cursor/mcp.json (one project) or ~/.cursor/mcp.json (every project):
{ "mcpServers": { "spiral": { "url": "https://api.spiral.ai/mcp" } } } - Sign in
Open Cursor Settings › MCP, click Connect next to spiral, sign in to Spiral and click Authorize. No API key. Spiral then shows as connected, with its tools listed.
Use the Spiral skill
- Send Cursor 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 GPT-6 Sol
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": "openai", "model": "openai/gpt-6-sol", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Cursor finds GPT-6 Sol on Spiral, shows the price and runs it.
GPT-6 Sol providers and prices
Spiral runs GPT-6 Sol through OpenAI. Open a card for today's price, with every fee included.
Up to $0.053363 per run at the default inputs. $2.60 per 1M input tokens, $0.26 per 1M cached input tokens, $3.25 per 1M cache write tokens, $13.00 per 1M output tokens.
Settings you can ask for
Ask Cursor for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Top p | a number up to 1 | Taken only with reasoning effort "none". | |
| Logprobs | on or off | Taken only with reasoning effort "none". | |
| Max tokens | 16 to 128000 | The most output tokens to generate. | |
| Temperature | 0 to 2 | Taken only with reasoning effort "none". | |
| Top logprobs | 0 to 20 | Taken only with reasoning effort "none". | |
| Presence penalty | -2 to 2 | Taken only with reasoning effort "none". | |
| Reasoning effort | none, low, medium, high, xhigh, or max | medium | How much the model reasons. |
| Frequency penalty | -2 to 2 | Taken only with reasoning effort "none". | |
| Parallel tool calls | on or off |
Every API field of GPT-6 Sol is on its tool page: open its card above.
What can you do with GPT-6 Sol in Cursor?
GPT-6 Sol can turn a bug report or feature brief into code changes and a reviewable explanation. Give the agent relevant project context, clear acceptance criteria, and a defined scope for verification.
Debug a recurring software failure
Trace a failure from its reproduction steps and logs, propose a focused fix, and identify the checks that would demonstrate it works.
Review a database migration
Examine a migration plan for data loss, compatibility problems, and rollback gaps. Ask for failure scenarios and the evidence needed before proceeding.
Turn requirements into an implementation plan
Convert a product brief into engineering tasks, dependencies, acceptance criteria, and questions that block implementation.
Compare technical proposals
Evaluate competing designs against stated requirements. Request a recommendation with tradeoffs and references to the supplied proposals.
Explain unfamiliar code
Map the responsibilities and data flow in supplied code, then identify the places a proposed change would affect.
Review an incident timeline
Compare logs, observations, and a response timeline to separate established facts from possible causes. Produce follow-up investigations with clear evidence requirements.
Check a specification for contradictions
Review a detailed specification for conflicting requirements, missing cases, and ambiguous behavior. Return concrete questions and proposed acceptance criteria.
More on GPT-6 Sol and Cursor
Overview
GPT-6 Sol in other agents
Questions about GPT-6 Sol in Cursor
Can Cursor use GPT-6 Sol?
Yes. Add Spiral to Cursor as an MCP server, and Cursor can find and run GPT-6 Sol like any built-in tool.
How much does GPT-6 Sol cost in Cursor?
Up to $0.053363 per run at the default inputs. $2.60 per 1M input tokens, $0.26 per 1M cached input tokens, $3.25 per 1M cache write tokens, $13.00 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Cursor plan is separate.
Do I need an OpenAI account to use GPT-6 Sol in Cursor?
No. Spiral runs GPT-6 Sol on its own OpenAI account. You sign in to Spiral once and never paste a key.
How long does it take to set up GPT-6 Sol in Cursor?
About two minutes: add the hosted server, then sign in.
Does Cursor wait while GPT-6 Sol runs?
GPT-6 Sol runs in the background. Cursor starts the run, checks on it and gives you the text, json when it's ready.
What is GPT-6 Sol useful for?
GPT-6 Sol is designed for complex coding and agent workflows. Practical tasks include debugging, comparing technical proposals, and turning a detailed brief into an implementation plan.
How does GPT-6 Sol Pro differ from GPT-6 Sol?
GPT-6 Sol Pro uses the same underlying model with pro reasoning enabled. Start with GPT-6 Sol for routine work; consider GPT-6 Sol Pro for difficult analysis or coding that warrants additional model work.
How much context and output can GPT-6 Sol handle?
The underlying model has a 1,050,000-token context window and a maximum output allowance of 128,000 tokens. Internal reasoning shares the output allowance, so the readable response can be shorter.
Does GPT-6 Sol know about recent events?
Its knowledge cutoff is April 20, 2026. Supply current source material when a task depends on later events, product changes, or new documentation.
How should I prompt GPT-6 Sol?
Give a clear task, the relevant evidence, explicit constraints, and the response format you want. For example, ask for a recommendation under 300 words that cites the supplied evidence and lists unresolved questions.
Start using GPT-6 Sol in Cursor
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Cursor:
set up https://spiral.ai/SKILL.md


