How to Use Claude Fable 5 in OpenClaw
Claude Fable 5 suits complex coding projects and document-heavy analysis that require sustained work across many steps. Compared with Claude Opus 4.8, it handles longer autonomous tasks and produces stronger financial and document deliverables.
Prompts to try with Claude Fable 5 in OpenClaw
Copy an example into OpenClaw, or ask in your own words.
Each Monday, use Claude Fable 5 to compare supplied weekly metrics. Report material changes, supporting calculations, and missing data.
Each morning, use Claude Fable 5 to synthesize the supplied research updates into a cited brief. Label unsupported claims.
Every Friday, use Claude Fable 5 to reconcile supplied project updates. List conflicting statements and decisions needed next week.
At month end, use Claude Fable 5 with extra-high reasoning effort to analyze supplied forecast changes and identify their main drivers.
Each afternoon, use Claude Fable 5 with medium reasoning effort to summarize supplied meeting notes into decisions, owners, and open questions.
How to set up Claude Fable 5 in OpenClaw
Pick the way that suits you. Each takes about two minutes.
Use the Spiral skill
- Send OpenClaw 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
- Add the server
On the machine that runs OpenClaw's Gateway:
openclaw mcp add spiral \ --url https://api.spiral.ai/mcp \ --transport streamable-http \ --auth oauth
- Sign in
In Settings › MCP, select Sign in on the Spiral server, sign in to Spiral and click Authorize. No API key.
openclaw mcp login spiral
- Reload and check
A running Gateway may keep its old tool list: restart it, or Save & Publish in the Control UI.
openclaw mcp reload openclaw mcp doctor spiral --probe
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
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", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: OpenClaw finds Claude Fable 5 on Spiral, shows the price and runs it.
Claude Fable 5 providers and prices
Spiral runs Claude Fable 5 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, $1.30 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 OpenClaw 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 is on its tool page: open its card above.
What can you do with Claude Fable 5 in OpenClaw?
Claude Fable 5 can produce recurring analytical briefs from the information supplied on each run. Define the reporting period and require evidence for every reported change.
Codebase migrations
Have Claude Fable 5 carry a migration through implementation and verification, with explicit compatibility requirements.
Complex bug investigations
Use Claude Fable 5 to investigate a failure across components, propose a fix, and check the result.
Financial decision briefs
Ask Claude Fable 5 to compare supplied financial evidence and identify assumptions that change the recommendation.
Spreadsheet analysis
Have Claude Fable 5 analyze supplied spreadsheet data and explain discrepancies with supporting calculations.
Document synthesis
Use Claude Fable 5 to turn several source documents into a cited brief that identifies conflicting evidence.
Presentation drafts
Ask Claude Fable 5 to turn an analytical brief into slide content with a clear decision and supporting evidence.
More on Claude Fable 5 and OpenClaw
Claude Fable 5 in other agents
Questions about Claude Fable 5 in OpenClaw
Can OpenClaw use Claude Fable 5?
Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run Claude Fable 5 like any built-in tool.
How much does Claude Fable 5 cost in OpenClaw?
Up to $0.26715 per run at the default inputs. $13.00 per 1M input tokens, $1.30 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 OpenClaw plan is separate.
Do I need an Anthropic account to use Claude Fable 5 in OpenClaw?
No. Spiral runs Claude Fable 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 Fable 5 in OpenClaw?
About two minutes: add the server, then sign in, then reload and check.
Does OpenClaw wait while Claude Fable 5 runs?
Claude Fable 5 runs in the background. OpenClaw starts the run, checks on it and gives you the text, json when it's ready.
What is Claude Fable 5 good at?
Complex coding projects, financial analysis, and work that combines many documents or steps. Its sustained autonomous work is a documented improvement over Claude Opus 4.8.
How much context and output can Claude Fable 5 handle?
It supports a one-million-token context window and up to 128,000 output tokens. Treat those as ceilings when planning a large analysis or deliverable.
Which reasoning effort should I use?
Use extra-high effort for especially difficult coding or analysis. Try medium or low effort for routine work, then check whether the results meet your requirements.
How should I prompt Claude Fable 5?
Explain who needs the result, what decision it supports, and the exact deliverable. Specify scope, length, and evidence requirements so the task has a clear finish.
Can Claude Fable 5 make factual mistakes?
Yes. Ask it to support conclusions with source quotes, flag missing evidence, and verify claims before presenting the final answer.
Start using Claude Fable 5 in OpenClaw
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into OpenClaw:
set up https://spiral.ai/SKILL.md


