How to Use Claude Haiku 5.5 in Windsurf
Claude Haiku 5.5 suits repetitive summaries, classification, extraction, and focused code edits. For complex coding tasks, Anthropic recommends Claude Sonnet 5.5 or Claude Opus 5.5.
Prompts to try with Claude Haiku 5.5 in Windsurf
Copy an example into Windsurf, or ask in your own words.
Use Claude Haiku 5.5 to rename the settings page heading from Preferences to Settings. Find the relevant component, make the edit, and run a check that exercises it.
Use Claude Haiku 5.5 to summarize the staged diff in five bullets for a reviewer. Separate behavior changes from formatting changes.
Use Claude Haiku 5.5 to classify the issues in the project's issue export as bug, feature request, documentation, or unclear. Preserve each issue ID.
Use Claude Haiku 5.5 to extract environment variable names and their documented purposes from the README. Mark missing descriptions as unknown.
Use Claude Haiku 5.5 to compact this coding conversation into the agreed requirements, completed edits, checks run, and remaining work.
How to set up Claude Haiku 5.5 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 Claude Haiku 5.5
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": "anthropic", "model": "anthropic/claude-haiku-5.5", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Windsurf finds Claude Haiku 5.5 on Spiral, shows the price and runs it.
Claude Haiku 5.5 providers and prices
Spiral runs Claude Haiku 5.5 through Anthropic. Open a card for today's price, with every fee included.
Up to $0.002672 per run at the default inputs. $0.13 per 1M input tokens, $0.013 per 1M cached input tokens, $0.1625 per 1M cache write tokens, $0.26 per 1M 1-hour cache write tokens, $0.65 per 1M output tokens.
Settings you can ask for
Ask Windsurf for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Max tokens | 1 to 128000 | The most output tokens to generate. On a reasoning model the reasoning tokens count toward it: a cap too low for the effort can end with no answer (finish_reason length). | |
| Reasoning effort | low, medium, high, xhigh, or max | medium | How much the model reasons. |
| Parallel tool calls | on or off |
Every API field of Claude Haiku 5.5 is on its tool page: open its card above.
What can you do with Claude Haiku 5.5 in Windsurf?
Claude Haiku 5.5 can handle focused edits and summarize project material. Give it a specific change and require a relevant check before completion.
Support ticket classification
Assign incoming tickets to billing, access, bug, or other queues.
Meeting summaries
Condense meeting transcripts into decisions, owners, and open questions.
Record extraction
Pull dates, names, and reference numbers from supplied text.
Request routing
Choose the appropriate workflow for each incoming request.
Conversation compaction
Shorten conversation history while preserving decisions and unfinished work.
Focused code edits
Apply a specific change, then run a relevant check.
Claude Haiku 5.5 success rate and speed on Spiral
Success and speed over the last 24 hours, across every run of these tools on Spiral.
| Tool | Success | Median time | Runs |
|---|---|---|---|
| Claude Haiku 5.5 | 100.0% | 3.1s | 550 |
More on Claude Haiku 5.5 and Windsurf
Claude Haiku 5.5 in other agents
Questions about Claude Haiku 5.5 in Windsurf
Can Windsurf use Claude Haiku 5.5?
Yes. Add Spiral to Windsurf as an MCP server, and Windsurf can find and run Claude Haiku 5.5 like any built-in tool.
How much does Claude Haiku 5.5 cost in Windsurf?
Up to $0.002672 per run at the default inputs. $0.13 per 1M input tokens, $0.013 per 1M cached input tokens, $0.1625 per 1M cache write tokens, $0.26 per 1M 1-hour cache write tokens, $0.65 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 Anthropic account to use Claude Haiku 5.5 in Windsurf?
No. Spiral runs Claude Haiku 5.5 on its own Anthropic account. You sign in to Spiral once and never paste a key.
How long does it take to set up Claude Haiku 5.5 in Windsurf?
About two minutes: add the server, then sign in, then check it.
Does Windsurf wait while Claude Haiku 5.5 runs?
Claude Haiku 5.5 runs in the background. Windsurf starts the run, checks on it and gives you the text, json when it's ready.
What is Claude Haiku 5.5 best for?
Use it for repeated, clearly defined work: summaries, classification, extraction, routing, and focused code edits.
When should I choose another Claude model?
Anthropic recommends Claude Sonnet 5.5 or Claude Opus 5.5 for complex agentic coding. Keep Haiku tasks narrowly scoped.
How much text can Claude Haiku 5.5 handle?
It has a 1 million token context window and supports up to 128,000 output tokens. Those are token limits, not word counts.
Which reasoning effort should I use?
Medium is the default. High suits longer tasks and work where following detailed instructions matters.
Why can a response end without an answer?
Thinking consumes the output token budget. A small limit can stop generation before visible answer text, so leave room for both thinking and the response.
Start using Claude Haiku 5.5 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


