How to Use GPT-6.1 Sol in Windsurf
Use GPT-6.1 Sol for debugging code, analyzing documents, and completing multistep business tasks. It uses standard reasoning mode, while Sol Pro applies more model work to difficult questions.
Prompts to try with GPT-6.1 Sol in Windsurf
Copy an example into Windsurf, or ask in your own words.
Use GPT-6.1 Sol with medium reasoning to investigate the failing tests in this repository. Reproduce one failure, apply the smallest fix, and run a regression check. Summarize the cause and result.
Use GPT-6.1 Sol with high reasoning to audit stale feature flags in this project. Trace direct references, wrappers, aliases, and dependencies between flags. Return evidence for each removal candidate.
Use GPT-6.1 Sol to examine this project's recent CI failures. Separate flaky tests from consistent failures, propose one focused repair, and verify it with the relevant test.
Use GPT-6.1 Sol to review this repository's CI history for unnecessary work. Rank three changes by measured time savings and implementation scope, and identify the evidence needed to verify each estimate.
Ask GPT-6.1 Sol through Spiral to review the diff on this branch and list the three riskiest changes. Save the result in ./assets.
How to set up GPT-6.1 Sol in Windsurf
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Open the Customize page from the Agents window and click MCPs. Under This computer, open the config file, or edit it directly: ~/.config/devin/mcp_config.json on macOS and Linux, %APPDATA%\devin\mcp_config.json on Windows. Add this:
{ "mcpServers": { "spiral": { "url": "https://api.spiral.ai/mcp" } } } - Sign in
Click Authenticate on the Spiral server in Customize › MCPs, or let the agent call Spiral once: your browser opens. Sign in to Spiral, pick the organization and click Authorize. No API key.
devin mcp login spiral
- Check it
Spiral is listed under This computer in Customize › MCPs. From the terminal:
devin mcp list
Use the Spiral skill
- Send Windsurf 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-6.1 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-6.1-sol", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Windsurf finds GPT-6.1 Sol on Spiral, shows the price and runs it.
GPT-6.1 Sol providers and prices
Spiral runs GPT-6.1 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, $0.13 per 1M cached input tokens, $3.25 per 1M cache write tokens, $13.00 per 1M output tokens.
Settings you can ask for
Ask Windsurf for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Max tokens | 16 to 128000 | The most output tokens to generate. | |
| Reasoning effort | low, medium, high, xhigh, or max | medium | How much the model reasons. |
| Parallel tool calls | on or off |
Every API field of GPT-6.1 Sol is on its tool page: open its card above.
What can you do with GPT-6.1 Sol in Windsurf?
Turn repository evidence into targeted fixes and maintenance proposals. Ask the agent to reproduce problems, trace dependencies, and show the checks behind each change.
Diagnose a failing test
Ask for the smallest reproducible failure, a targeted fix, and a regression check that demonstrates the change.
Reconcile a complex report
Compare the narrative with its tables and footnotes. Request a short list of discrepancies with supporting passages.
Prepare an operations brief
Turn status updates into decisions, unresolved questions, and next actions. Require evidence for each recommendation.
Review stale feature flags
Ask for candidate removals with direct and indirect dependencies traced. Review the evidence before accepting a cleanup.
Examine a difficult decision
Use Sol Pro to compare competing explanations, test assumptions, and identify what evidence would change the recommendation.
Evaluate reasoning settings
Run the same examples at two reasoning efforts. Compare correctness and completeness, then retain the lighter setting if it meets your requirements.
More on GPT-6.1 Sol and Windsurf
Overview
GPT-6.1 Sol in other agents
Questions about GPT-6.1 Sol in Windsurf
Can Windsurf use GPT-6.1 Sol?
Yes. Add Spiral to Windsurf as an MCP server, and Windsurf can find and run GPT-6.1 Sol like any built-in tool.
How much does GPT-6.1 Sol cost in Windsurf?
Up to $0.053363 per run at the default inputs. $2.60 per 1M input tokens, $0.13 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 Windsurf plan is separate.
Do I need an OpenAI account to use GPT-6.1 Sol in Windsurf?
No. Spiral runs GPT-6.1 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-6.1 Sol in Windsurf?
About two minutes: add the server, then sign in, then check it.
Does Windsurf wait while GPT-6.1 Sol runs?
GPT-6.1 Sol runs in the background. Windsurf starts the run, checks on it and gives you the text, json when it's ready.
What is the difference between GPT-6.1 Sol and Sol Pro?
They use the same underlying model. Sol Pro selects pro reasoning mode, which applies more model work to difficult tasks; it is separate from the reasoning effort setting.
What work is GPT-6.1 Sol good at?
Its documented strengths include debugging code, understanding complex documents, and completing multistep business workflows. Useful tasks include investigating a failing test or reconciling conflicting passages in a report.
How much text can GPT-6.1 Sol handle?
OpenAI lists a 1,050,000-token context window, with separate ceilings of 922,000 input tokens and 128,000 output tokens. These are token limits, not word counts.
Can GPT-6.1 Sol generate audio or video?
Its native output is text, and audio and video are unsupported modalities. Ask it for a script or storyboard when planning media.
Which reasoning effort should I use?
Start with medium or high for debugging, diagnosis, planning, or comparing options. Compare results on the same representative tasks before choosing a heavier setting.
Start using GPT-6.1 Sol in Windsurf
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Windsurf:
set up https://spiral.ai/SKILL.md


