How to Use Claude Sonnet 5.5 in Gemini CLI
Claude Sonnet 5.5 fits bug fixes, small features, and document drafting with clear requirements. Claude Opus 5.5 is the better choice for the hardest work that requires sustained reasoning over many steps.
Prompts to try with Claude Sonnet 5.5 in Gemini CLI
Copy an example into Gemini CLI, or ask in your own words.
Use Claude Sonnet 5.5 at medium effort to investigate the failing test in this project. Fix the cause, run the affected tests, and report the result.
Use Claude Sonnet 5.5 to review the current diff for correctness bugs. For each finding, give the file, affected behavior, and smallest useful correction.
Use Claude Sonnet 5.5 at medium effort to implement the acceptance criteria in this issue. Follow the project's conventions and run checks that exercise each requirement.
Use Claude Sonnet 5.5 at high effort to trace why this command returns duplicate records. Make a focused fix and verify it against a case that previously failed.
Use Claude Sonnet 5.5 to draft release notes from this project's changes. Describe user-visible behavior, group related changes, and flag anything the code does not establish.
How to set up Claude Sonnet 5.5 in Gemini CLI
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Or add it to ~/.gemini/settings.json yourself:
gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
- Sign in
Start gemini and run:
/mcp auth spiral
- Check it
In Gemini CLI, run /mcp. From your shell:
gemini mcp list
Use the Spiral skill
- Send Gemini CLI 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 Sonnet 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-sonnet-5.5", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Gemini CLI finds Claude Sonnet 5.5 on Spiral, shows the price and runs it.
Claude Sonnet 5.5 providers and prices
Spiral runs Claude Sonnet 5.5 through Anthropic. Open a card for today's price, with every fee included.
Up to $0.05343 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, $5.20 per 1M 1-hour cache write tokens, $13.00 per 1M output tokens; for a prompt above 200,000 tokens, $5.20 per 1M input tokens, $0.26 per 1M cached input tokens, $6.50 per 1M cache write tokens, $10.40 per 1M 1-hour cache write tokens, $19.50 per 1M output tokens.
Settings you can ask for
Ask Gemini CLI 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 | high | How much the model reasons. |
| Parallel tool calls | on or off |
Every API field of Claude Sonnet 5.5 is on its tool page: open its card above.
What can you do with Claude Sonnet 5.5 in Gemini CLI?
Turn a defined bug report or feature request into code you can review. Ask Claude Sonnet 5.5 to keep the change focused and verify the resulting behavior.
Fix a reproducible bug
Trace a failing behavior, make a focused correction, and run a check that reproduces the original problem.
Build a small feature
Turn clear acceptance criteria into a reviewable implementation, with checks tied to the requested behavior.
Review a code change
Inspect a patch for likely defects and explain each finding with the affected behavior and a suggested correction.
Draft a decision brief
Turn supplied notes into a concise document with the decision, supporting evidence, unresolved questions, and next steps.
Prepare a presentation
Develop slide titles, supporting points, and speaker notes from an approved brief and a defined audience.
Analyze a recurring report
Compare supplied figures, identify changes, and produce an explanation that distinguishes observations from possible causes.
Localize customer communications
Translate supplied messages while preserving names, numbers, and product terminology. Review the result with speakers of the target language.
More on Claude Sonnet 5.5 and Gemini CLI
Claude Sonnet 5.5 in other agents
Questions about Claude Sonnet 5.5 in Gemini CLI
Can Gemini CLI use Claude Sonnet 5.5?
Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run Claude Sonnet 5.5 like any built-in tool.
How much does Claude Sonnet 5.5 cost in Gemini CLI?
Up to $0.05343 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, $5.20 per 1M 1-hour cache write tokens, $13.00 per 1M output tokens; for a prompt above 200,000 tokens, $5.20 per 1M input tokens, $0.26 per 1M cached input tokens, $6.50 per 1M cache write tokens, $10.40 per 1M 1-hour cache write tokens, $19.50 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini CLI plan is separate.
Do I need an Anthropic account to use Claude Sonnet 5.5 in Gemini CLI?
No. Spiral runs Claude Sonnet 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 Sonnet 5.5 in Gemini CLI?
About two minutes: add the server, then sign in, then check it.
Does Gemini CLI wait while Claude Sonnet 5.5 runs?
Claude Sonnet 5.5 runs in the background. Gemini CLI starts the run, checks on it and gives you the text, json when it's ready.
What is Claude Sonnet 5.5 best for?
Use it for work with a clear target: fixing a bug, building a small feature, analyzing supplied data, or drafting a document. Give it concrete requirements and a defined stopping point.
When should I choose Claude Opus 5.5 instead?
Anthropic recommends an Opus model for the hardest tasks that require sustained reasoning over many steps. Claude Sonnet 5.5 is a practical starting point when the task is clearly defined.
How much text can Claude Sonnet 5.5 handle?
Its context window holds up to one million tokens, and its standard output limit is 128,000 tokens. Those are token limits, so avoid treating them as fixed page or word counts.
Which reasoning effort should I use?
Start with medium effort for clearly specified coding and multistep tool tasks. Move to high when the work becomes harder or longer, and compare results on your actual tasks.
Does Claude Sonnet 5.5 always check its code?
No. At low effort, it can skip verification, so ask for a test, build, or other check that exercises the change and have it report the result.
Start using Claude Sonnet 5.5 in Gemini CLI
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Gemini CLI:
set up https://spiral.ai/SKILL.md


