Spiral gives your agent every tool with one account. Browse the tools →

Claude Code · LLMReleased 2026-11-09

How to Use Claude Fable 5.2 in Claude Code

Claude Fable 5.2 is built for difficult coding, deep research, and extended technical tasks. Compared with Claude Fable 5.1, Anthropic reports improvements in coding, reasoning, and vision.

Prompts to try with Claude Fable 5.2 in Claude Code

Copy an example into Claude Code, or ask in your own words.

Use Claude Fable 5.2 to investigate the failing tests in this repository at high reasoning effort. Reproduce the failure, trace its cause, make a focused fix, and run the relevant checks. Finish with the cause, changes, results, and any remaining blocker.

Claude Fable 5.2Claude Code
Try asking
  • Use Claude Fable 5.2 to review this project's background job retry logic. Identify paths that could repeat a completed operation, explain the evidence, and propose the smallest correction. Keep the final report under 600 words.

  • Use Claude Fable 5.2 to plan the database migration described in this project's issue notes. Inspect the schema and callers, identify compatibility risks, and produce an ordered implementation plan with rollback criteria and acceptance checks.

  • Use Claude Fable 5.2 to compare the two caching approaches documented in this repository. Evaluate invalidation behavior, concurrency, and failure recovery against the project's requirements. Recommend one approach and identify assumptions that need testing.

  • Use Claude Fable 5.2 to complete the refactor described in the project task. Preserve documented behavior, verify the affected paths, and continue through recoverable errors until the acceptance checks pass or a concrete blocker remains. Report the actual diff and check results.

How to set up Claude Fable 5.2 in Claude Code

Pick the way that suits you. Each takes about two minutes.

Use Spiral's MCP server

  1. Add the hosted server

    This adds Spiral to the current project. Add --scope user to use it in every project.

    claude mcp add --transport http spiral https://api.spiral.ai/mcp
  2. Sign in

    Start claude, type /mcp, choose spiral and Authenticate. Sign in to Spiral in the browser and click Authorize. No API key.

Use the Spiral skill

  1. Send Claude Code this message

    Your agent reads Spiral's skill and sets itself up.

    set up https://spiral.ai/SKILL.md
  2. Sign in or paste a key

    Approve Spiral in the browser, or give the agent a key from the console.

Use the Spiral CLI

  1. 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

  1. Create an API key

    In the console, under API keys.

  2. Run Claude Fable 5.2

    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-5.2",
        "input": {
          "messages": [
            {
              "role": "system"
            }
          ]
        }
      }'

Then paste one of the prompts above: Claude Code finds Claude Fable 5.2 on Spiral, shows the price and runs it.

Claude Fable 5.2 providers and prices

Spiral runs Claude Fable 5.2 through Anthropic. Open a card for today's price, with every fee included.

AnthropicLLM
Claude Fable 5.2
anthropic/claude-fable-5.2

Settings you can ask for

Ask Claude Code for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Max tokens1 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 effortlow, medium, high, xhigh, or maxhigh

How much the model reasons.

Parallel tool callson or off

Every API field of Claude Fable 5.2 is on its tool page: open its card above.

What can you do with Claude Fable 5.2 in Claude Code?

Turn difficult code investigations into reviewed changes with Claude Fable 5.2. Give the agent a defined scope, acceptance checks, and a final report that distinguishes completed work from unresolved issues.

Diagnose a difficult software bug

Ask Claude Fable 5.2 to trace a failure through the relevant code, identify a reproducible cause, and propose a focused fix with verification.

Plan a complex code change

Have Claude Fable 5.2 map dependencies, identify behavior that must stay consistent, and develop an implementation plan with acceptance checks.

Compare technical approaches

Give Claude Fable 5.2 competing designs and explicit requirements. Request a recommendation that identifies assumptions, tradeoffs, and unanswered questions.

Synthesize technical research

Provide source excerpts and ask Claude Fable 5.2 to reconcile competing findings, distinguish evidence from inference, and identify the next questions to investigate.

Turn analysis into a technical report

Ask Claude Fable 5.2 to develop supplied findings into a finished report with recommendations, supporting evidence, and clearly stated gaps.

Review a multistep technical investigation

Have Claude Fable 5.2 assess completed experiments, identify unresolved hypotheses, and produce a prioritized plan for the remaining investigation.

Questions about Claude Fable 5.2 in Claude Code

Can Claude Code use Claude Fable 5.2?

Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run Claude Fable 5.2 like any built-in tool.

How much does Claude Fable 5.2 cost in Claude Code?

Up to $0.21372 per run at the default inputs. $10.40 per 1M input tokens, $0.26 per 1M cached input tokens, $13.00 per 1M cache write tokens, $20.80 per 1M 1-hour cache write tokens, $52.00 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude Code plan is separate.

Do I need an Anthropic account to use Claude Fable 5.2 in Claude Code?

No. Spiral runs Claude Fable 5.2 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 5.2 in Claude Code?

About two minutes: add the hosted server, then sign in.

Does Claude Code wait while Claude Fable 5.2 runs?

Claude Fable 5.2 runs in the background. Claude Code starts the run, checks on it and gives you the text, json when it's ready.

What is Claude Fable 5.2 best suited for?

Use it for difficult coding, multistep research, and technical analysis that needs a finished deliverable. Give it a concrete result to produce and clear criteria for completion.

How much context and output can Claude Fable 5.2 handle?

It supports a one-million-token context window and up to 128,000 output tokens. These are token limits, so avoid treating them as fixed page or word counts.

Which reasoning effort should I use?

Start with high effort and compare results on representative tasks. Increase effort for difficult work only when testing shows a benefit; lower it when the results still meet your requirements.

Can I turn Claude Fable 5.2 thinking off?

Adaptive thinking is always enabled. Adjust effort to control thinking depth, and request a specific answer length separately.

What should I do if Claude Fable 5.2 stops before finishing?

State the remaining deliverable and tell it to continue through ordinary, recoverable obstacles. Early stopping is more common at lower effort levels, so test high effort for extended tasks.

Get started

Start using Claude Fable 5.2 in Claude Code

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into Claude Code:

Set up Claude Code

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options