How to Use Claude Fable 5.1 in Codex
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 Codex
Copy an example into Codex, or ask in your own words.
Use Claude Fable 5.1 to investigate the failing tests in this project. Trace the cause, make targeted edits, and rerun the relevant checks.
Use Claude Fable 5.1 to map the authentication flow across this repository. Identify dependencies and propose a refactor that preserves public behavior.
Use Claude Fable 5.1 to implement keyboard navigation in this project's settings dialog. Preserve existing mouse interactions and verify both paths.
Use Claude Fable 5.1 to review the current diff for behavioral regressions. Report concrete failure paths with file references and keep edits out of this review.
Use Claude Fable 5.1 with high reasoning effort to trace the intermittent crash described in this project's logs. Test competing explanations before changing code.
How to set up Claude Fable 5.1 in Codex
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
codex mcp add spiral --url https://api.spiral.ai/mcp
- Sign in
Codex opens the browser: sign in to Spiral and click Authorize. No API key. codex mcp list then shows Spiral.
codex mcp login spiral
Use the Spiral skill
- Send Codex 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 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: Codex 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 Codex 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 Codex?
Claude Fable 5.1 can carry a codebase investigation through diagnosis, implementation, and verification. Give it a bounded change and explicitly request targeted edits.
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 Codex
Overview
Claude Fable 5.1 in other agents
Questions about Claude Fable 5.1 in Codex
Can Codex use Claude Fable 5.1?
Yes. Add Spiral to Codex as an MCP server, and Codex can find and run Claude Fable 5.1 like any built-in tool.
How much does Claude Fable 5.1 cost in Codex?
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 Codex plan is separate.
Do I need an Anthropic account to use Claude Fable 5.1 in Codex?
No. Spiral runs Claude Fable 5.1 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 5.1 in Codex?
About two minutes: add the hosted server, then sign in.
Does Codex wait while Claude Fable 5.1 runs?
Claude Fable 5.1 runs in the background. Codex 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 Codex
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Codex:
set up https://spiral.ai/SKILL.md


