How to Use GPT-5.1 in Windsurf
GPT-5.1 fits code changes, debugging, and workflows that take several steps. Compared with GPT-5, it improves code quality and produces more functional frontend designs, especially at low reasoning effort.
Prompts to try with GPT-5.1 in Windsurf
Copy an example into Windsurf, or ask in your own words.
Use GPT-5.1 with high reasoning effort to investigate the failing tests in this project. Reproduce one failure, trace its cause, implement a focused fix, and run the relevant tests. Finish with the cause, changed files, and actual test results.
Use GPT-5.1 with low reasoning effort to implement client-side validation for this project's signup form. Follow existing components and error styles. Check empty input, invalid email, and successful submission before reporting the result.
Use GPT-5.1 to review the current diff for correctness. Return only actionable findings with file locations, a concrete failure scenario, and a suggested regression test. If you find no defects, say so.
Use GPT-5.1 with high reasoning effort to trace how this project handles duplicate webhook deliveries. Add a regression test for repeated delivery, fix any confirmed defect, and verify the behavior. Continue until the fix is checked or a specific blocker is documented.
Use GPT-5.1 to extract this project's public endpoint contracts into JSON records containing method, path, request requirements, response shape, and source location. Mark missing documentation explicitly and check each record against the implementation.
How to set up GPT-5.1 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-5.1
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-5.1", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Windsurf finds GPT-5.1 on Spiral, shows the price and runs it.
GPT-5.1 providers and prices
Spiral runs GPT-5.1 through OpenAI. Open a card for today's price, with every fee included.
Up to $0.053306 per run at the default inputs. $1.625 per 1M input tokens, $0.1625 per 1M cached input 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 | ||
| Top p | a number up to 1 | Taken only at reasoning effort "none", this model's default. | |
| Logprobs | on or off | Taken only at reasoning effort "none", this model's default. | |
| Max tokens | 16 to 128000 | The most output tokens to generate. | |
| Temperature | 0 to 2 | Taken only at reasoning effort "none", this model's default. | |
| Top logprobs | 0 to 20 | Taken only at reasoning effort "none", this model's default. | |
| Presence penalty | -2 to 2 | Taken only at reasoning effort "none", this model's default. | |
| Reasoning effort | none, low, medium, or high | none | How much the model reasons. |
| Frequency penalty | -2 to 2 | Taken only at reasoning effort "none", this model's default. | |
| Parallel tool calls | on or off |
Every API field of GPT-5.1 is on its tool page: open its card above.
What can you do with GPT-5.1 in Windsurf?
Turn a bug report or feature request into an implemented code change with GPT-5.1. Give the agent acceptance criteria and require verification so the task continues through a checked result.
Fix a reproducible bug
Use GPT-5.1 to trace a failing behavior, implement a focused patch, and check the result against a regression test.
Implement a frontend interaction
Give GPT-5.1 an interaction specification and acceptance criteria to turn a static screen into a working form, filter, or navigation flow.
Review a proposed code change
Ask GPT-5.1 to inspect a diff for behavior changes, missing edge cases, and tests that would expose a defect.
Extract research details
Use GPT-5.1 to turn supplied research text into records containing methods, findings, and supporting passages for review.
Prepare support reply drafts
Give GPT-5.1 the conversation and relevant policy text to draft a concise response and identify information still needed.
Compare proposals against requirements
Ask GPT-5.1 to evaluate supplied proposals against explicit constraints, cite the relevant passages, and flag unanswered requirements.
Produce a recurring change digest
Use GPT-5.1 to compare newly supplied updates with the previous run and draft a brief that separates changes from unresolved questions.
More on GPT-5.1 and Windsurf
Overview
GPT-5.1 in other agents
More Windsurf guides
Questions about GPT-5.1 in Windsurf
Can Windsurf use GPT-5.1?
Yes. Add Spiral to Windsurf as an MCP server, and Windsurf can find and run GPT-5.1 like any built-in tool.
How much does GPT-5.1 cost in Windsurf?
Up to $0.053306 per run at the default inputs. $1.625 per 1M input tokens, $0.1625 per 1M cached input 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-5.1 in Windsurf?
No. Spiral runs GPT-5.1 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-5.1 in Windsurf?
About two minutes: add the server, then sign in, then check it.
Does Windsurf wait while GPT-5.1 runs?
GPT-5.1 runs in the background. Windsurf starts the run, checks on it and gives you the text, json when it's ready.
What is GPT-5.1 useful for?
GPT-5.1 fits debugging, code edits, frontend implementation, and workflows that require several steps. Compared with GPT-5, OpenAI reports improvements in code quality and frontend functionality, especially at low reasoning effort.
How much text can GPT-5.1 handle?
GPT-5.1 has a 400,000-token context window and a maximum output of 128,000 tokens. Treat these as ceilings when planning long document reviews or large code tasks.
When should I increase reasoning effort?
Use the default no-reasoning mode for straightforward requests where speed matters. For difficult debugging or decisions with several constraints, OpenAI recommends high reasoning effort when reliability matters more than speed.
Why can GPT-5.1 stop before finishing a task?
OpenAI observed premature stopping on long agent tasks. Define completion explicitly, such as implementing the change, checking it, and reporting any unresolved work.
Can I trust the contents of structured JSON?
Structured formatting does not guarantee factual accuracy. For extraction tasks, request supporting text for each value and check the results against the source.
Start using GPT-5.1 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


