How to Use Claude Fable 5.1 in Instinct
Claude Fable 5.1 suits difficult debugging, codebase changes, and research that takes several steps. Anthropic reports stronger coding and knowledge-work results than Claude Fable 5.
Prompts to try with Claude Fable 5.1 in Instinct
Copy an example into Instinct, or ask in your own words.
Every Monday, use Claude Fable 5.1 to research changes to the products on my watchlist. Verify current sources and report only changes since the previous run.
Each morning, use Claude Fable 5.1 to compare newly collected customer feedback with the prior summary. Report emerging problems with supporting examples.
Each Friday, use Claude Fable 5.1 to review the latest research on our tracked questions. Separate replicated findings, disputed claims, and open questions.
After each quarterly update, use Claude Fable 5.1 to compare the reported figures with the previous quarter. Show calculations and flag missing evidence.
Each week, use Claude Fable 5.1 to reconcile project updates into a decision brief. Identify conflicting commitments and name the decisions still needed.
How to set up Claude Fable 5.1 in Instinct
Pick the way that suits you. Each takes about two minutes.
Use the Spiral skill
- Send Instinct 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 Spiral's MCP server
- Create an API key
In the console, open API keys and create a key for Instinct. Copy it.
- Send Instinct this message
Instinct reads Spiral's skill and asks for your API key.
set up https://spiral.ai/SKILL.md
- Give Instinct the key
When Instinct asks for the key, add it where Instinct keeps secrets, never in the chat itself.
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 Fable 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": "anthropic", "model": "anthropic/claude-fable-5.1", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Instinct finds Claude Fable 5.1 on Spiral, shows the price and runs it.
Claude Fable 5.1 providers and prices
Spiral runs Claude Fable 5.1 through Anthropic. Open a card for today's price, with every fee included.
Up to $0.26715 per run at the default inputs. $13.00 per 1M input tokens, $0.325 per 1M cached input tokens, $16.25 per 1M cache write tokens, $26.00 per 1M 1-hour cache write tokens, $65.00 per 1M output tokens.
Settings you can ask for
Ask Instinct 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 Fable 5.1 is on its tool page: open its card above.
What can you do with Claude Fable 5.1 in Instinct?
Claude Fable 5.1 can investigate recurring business or research questions across multiple steps. Define the evidence to collect and the finished report each run should produce.
Trace a stubborn software bug
Use Claude Fable 5.1 to follow a failure through related code and logs, then propose a patch with a reproducible check.
Plan a codebase refactor
Ask Claude Fable 5.1 to map dependencies, identify affected behavior, and divide the change into reviewable steps.
Build a front-end feature
Give Claude Fable 5.1 a concrete interaction brief and ask it to implement the interface with explicit acceptance criteria.
Compare lengthy business material
Ask Claude Fable 5.1 to reconcile competing proposals, flag contradictions, and produce a decision memo tied to the supplied evidence.
Investigate a research question
Use Claude Fable 5.1 to compare explanations, identify missing evidence, and propose tests that could distinguish them.
Explain financial changes
Provide quarterly figures as text and ask Claude Fable 5.1 to compare periods, show calculations, and separate observed changes from possible causes.
More on Claude Fable 5.1 and Instinct
Claude Fable 5.1 in other agents
Questions about Claude Fable 5.1 in Instinct
Can Instinct use Claude Fable 5.1?
Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run Claude Fable 5.1 like any built-in tool.
How much does Claude Fable 5.1 cost in Instinct?
Up to $0.26715 per run at the default inputs. $13.00 per 1M input tokens, $0.325 per 1M cached input tokens, $16.25 per 1M cache write tokens, $26.00 per 1M 1-hour cache write tokens, $65.00 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Instinct plan is separate.
Do I need an Anthropic account to use Claude Fable 5.1 in Instinct?
You need no Anthropic account. Instinct uses one Spiral API key for every tool, and Spiral runs Claude Fable 5.1 on its own Anthropic account.
How long does it take to set up Claude Fable 5.1 in Instinct?
About two minutes: create an API key, then send Instinct this message, then give Instinct the key.
Does Instinct wait while Claude Fable 5.1 runs?
Claude Fable 5.1 runs in the background. Instinct starts the run, checks on it and gives you the text, json when it's ready.
What is Claude Fable 5.1 good at?
It suits difficult coding, knowledge work, and problems that require several steps. Examples include tracing a stubborn bug, comparing lengthy source material, and developing a research analysis.
How does Claude Fable 5.1 compare with Claude Fable 5?
Anthropic reports stronger results in coding, knowledge work, and long-running problem solving. Those evaluation results are a reason to test it on your own tasks, rather than assume every answer improves.
How much can Claude Fable 5.1 read and write?
Its context window is 1M tokens, and its maximum output is 128K tokens. Treat these as capacity limits when planning a large analysis or deliverable.
What should I watch for when editing code?
Small changes can lead to whole-file rewrites. Ask for targeted edits and specify the behavior the patch must preserve.
Does Claude Fable 5.1 always search before answering?
No. At low reasoning effort, it is more likely to rely on memory, so explicitly request verification when current information matters.
Start using Claude Fable 5.1 in Instinct
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Instinct:
set up https://spiral.ai/SKILL.md


