How to Use Claude Opus 5.5 in ChatGPT
Claude Opus 5.5 is built for long coding tasks, large refactors, and detailed knowledge work. Compared with Claude Opus 5, it generates output more than 30% faster in Anthropic’s tests.
Prompts to try with Claude Opus 5.5 in ChatGPT
Copy an example into ChatGPT, or ask in your own words.
Use Claude Opus 5.5 to compare the proposals in this conversation. Write a 500-word decision brief covering requirements met, tradeoffs, and unanswered questions, with supporting quotations for each important claim.
Use Claude Opus 5.5 to check the calculations and assumptions in the analysis above. List each discrepancy, show the corrected calculation, and identify missing information without inventing values.
Use Claude Opus 5.5 to reconcile the planning discussion above. Produce a table of decisions, owners, deadlines, and conflicts, citing the relevant passage for each entry.
Use Claude Opus 5.5 to turn the research excerpts in this conversation into a 600-word brief. Separate supported findings from open questions and include a short supporting quotation for every conclusion.
Use Claude Opus 5.5 to assess the system design described above. Compare two implementation approaches against the stated requirements, explain the tradeoffs, and end with a concrete verification checklist.
How to set up Claude Opus 5.5 in ChatGPT
Pick the way that suits you. Each takes about two minutes.
Use the ChatGPT connector
- Add a custom MCP server
In ChatGPT open Plugins, then Add › Add custom MCP server. Name it Spiral, paste this URL and keep Authentication on OAuth. Tick I understand and want to continue, then click Create.
https://api.spiral.ai/mcp
- Click Connect
ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.
- Sign in to Spiral and approve
Sign in, pick the organization ChatGPT should use and click Authorize. Spiral gives the connection its own API key; ChatGPT never sees it, and you can remove the connection under Settings › Connected apps.
Use the Spiral skill
- Send ChatGPT 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 Opus 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-opus-5.5", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: ChatGPT finds Claude Opus 5.5 on Spiral, shows the price and runs it.
Claude Opus 5.5 providers and prices
Spiral runs Claude Opus 5.5 through Anthropic. Open a card for today's price, with every fee included.
Up to $0.10686 per run at the default inputs. $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, $26.00 per 1M output tokens; for a prompt above 200,000 tokens, $10.40 per 1M input tokens, $0.52 per 1M cached input tokens, $13.00 per 1M cache write tokens, $20.80 per 1M 1-hour cache write tokens, $39.00 per 1M output tokens.
Settings you can ask for
Ask ChatGPT 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 Opus 5.5 is on its tool page: open its card above.
What can you do with Claude Opus 5.5 in ChatGPT?
Turn detailed source material into a decision brief or a checked analysis with Claude Opus 5.5. Specify the question, required evidence, and answer length so the result is easy to review.
Migrate a large codebase
Use Claude Opus 5.5 to move deprecated interfaces to their replacements, update affected tests, and report any remaining blockers against a migration checklist.
Refactor across modules
Ask Claude Opus 5.5 to trace dependencies, simplify duplicated logic, and verify that the affected behavior still passes its tests.
Review a complicated change
Have Claude Opus 5.5 examine a patch and its surrounding code, then report reproducible defects with evidence and a suggested test.
Prepare a research brief
Give Claude Opus 5.5 the source material and a specific decision to support. Request a concise brief with quotations for key claims and a list of unresolved questions.
Check a financial analysis
Ask Claude Opus 5.5 to inspect supplied calculations, identify inconsistent assumptions, and explain how each proposed correction changes the result.
Reconcile planning records
Use Claude Opus 5.5 to compare lengthy planning material, flag conflicting commitments, and produce a decision log with evidence for each entry.
More on Claude Opus 5.5 and ChatGPT
Claude Opus 5.5 in other agents
Questions about Claude Opus 5.5 in ChatGPT
Can ChatGPT use Claude Opus 5.5?
Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run Claude Opus 5.5 like any built-in tool.
How much does Claude Opus 5.5 cost in ChatGPT?
Up to $0.10686 per run at the default inputs. $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, $26.00 per 1M output tokens; for a prompt above 200,000 tokens, $10.40 per 1M input tokens, $0.52 per 1M cached input tokens, $13.00 per 1M cache write tokens, $20.80 per 1M 1-hour cache write tokens, $39.00 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your ChatGPT plan is separate.
Do I need an Anthropic account to use Claude Opus 5.5 in ChatGPT?
No. Spiral runs Claude Opus 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 Opus 5.5 in ChatGPT?
About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.
Does ChatGPT wait while Claude Opus 5.5 runs?
Claude Opus 5.5 runs in the background. ChatGPT starts the run, checks on it and gives you the text, json when it's ready.
What is Claude Opus 5.5 best suited for?
Use it for work with several dependent steps, such as a large refactor, a code migration, or a detailed analysis. Give it a concrete deliverable and a clear completion checklist.
How much text can Claude Opus 5.5 handle?
It has a 1 million token context window and supports up to 128,000 output tokens in a standard response. Thinking also uses the output budget, so the full allowance is not available for the visible answer.
Does higher effort always produce a better result?
Test effort settings on your actual tasks before choosing one. For demanding work, leave enough output space for thinking and the answer, then compare correctness and completeness.
How should I prompt Claude Opus 5.5?
State the deliverable, constraints, and completion criteria explicitly. Include an example when the answer must follow a particular format or writing style.
Can I trust every figure or citation it produces?
Check important claims against their sources. Ask for supporting quotations, and tell it to mark missing evidence instead of filling gaps.
Start using Claude Opus 5.5 in ChatGPT
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into ChatGPT:
set up https://spiral.ai/SKILL.md


