[Integrations](https://spiral.ai/integrations) › [Perplexity](https://spiral.ai/integrations/perplexity) › [Claude Fable Latest](https://spiral.ai/integrations/perplexity/claude-fable-latest)

# How to Use Claude Fable Latest in Perplexity

Use Claude Fable Latest for difficult coding, research, and analysis that needs several rounds of checking. Anthropic currently identifies Fable 5.2 as its latest release, with support for large software migrations and mathematical proof formalization.

|  |  |
| --- | --- |
| Model | Claude Fable Latest |
| Available through | Anthropic |
| Category | LLM |
| Price | 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. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Claude Fable Latest in Perplexity

- Use Claude Fable Latest to turn the research excerpts in this conversation into an 800-word technical brief. Explain where the sources agree, where they conflict, and what evidence would resolve the disagreement.
- Use Claude Fable Latest with high reasoning effort to review the mathematical argument above. State its assumptions, identify missing lemmas, and separate verified steps from steps that still need proof.
- Use Claude Fable Latest to compare the experiment results pasted above. Check the baseline, possible confounders, and repeatability, then propose three ablations with clear success criteria.
- Use Claude Fable Latest to review the software architecture described in this conversation. Trace failure paths across services and recommend an incremental change plan with a check for each stage.
- Use Claude Fable Latest to develop a migration plan from the Python service description above to Rust. Identify compatibility risks, observable behavior to preserve, and the evidence needed before each rollout stage.

## How to set up Claude Fable Latest in Perplexity

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

### Use the Perplexity connector

1. **Add a remote connector**: In Perplexity, open Plugins in the sidebar (or Customize › Connectors if you don't see Plugins yet). Choose Add custom › Add MCP connector, then Remote. Name it Spiral and paste this MCP server URL:

```text
https://api.spiral.ai/mcp
```

2. **Sign in to Spiral and approve**: Select the Spiral card on the Plugins page to start sign-in. Spiral opens: sign in, pick the organization and click Authorize. No API key.

### Use the Spiral skill

1. **Send Perplexity 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.

```bash
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 Latest**: One request; the result comes back by polling or a webhook.

```bash
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-latest",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

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

Setup guide in the docs: https://spiral.ai/docs/quickstarts/perplexity

## Claude Fable Latest tools and prices

- [Claude Fable Latest](https://spiral.ai/tools/anthropic/~anthropic/claude-fable-latest) (Anthropic): 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.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| stop |  | — |  |
| tools |  | — |  |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| 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). |
| tool_choice |  | — |  |
| response_format |  | — |  |

## What can you do with Claude Fable Latest in Perplexity?

Develop a technical research brief, experiment plan, or mathematical argument through conversation with Claude Fable. Supply the evidence and define the finished answer so the work has a clear endpoint.

### Plan and implement a software migration

Map existing behavior, migrate one component at a time, and compare results against the original implementation.

### Investigate a persistent software bug

Trace a failure across components, test competing explanations, and produce a fix with evidence that it addresses the cause.

### Review architecture across repositories

Compare dependencies and responsibilities across services, then turn the findings into a concrete change proposal.

### Produce a technical research brief

Work from supplied sources to develop an analysis, resolve conflicting evidence, and finish a document with clear conclusions.

### Evaluate machine learning experiments

Compare a baseline with proposed changes, plan ablations, and check whether measured improvements survive repeat runs.

### Develop a checkable mathematical proof

Break a proof into lemmas, state assumptions, and work toward a formalization that a proof checker can validate.

## Overview

- [Anthropic Claude](https://spiral.ai/providers/anthropic)
- [All Perplexity guides](https://spiral.ai/integrations/perplexity)

## Claude Fable Latest in other agents

- [Amp](https://spiral.ai/integrations/amp/claude-fable-latest)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/claude-fable-latest)
- [Claude](https://spiral.ai/integrations/claude-desktop/claude-fable-latest)
- [Claude Code](https://spiral.ai/integrations/claude-code/claude-fable-latest)
- [Cline](https://spiral.ai/integrations/cline/claude-fable-latest)
- [Codex](https://spiral.ai/integrations/codex/claude-fable-latest)
- [Cursor](https://spiral.ai/integrations/cursor/claude-fable-latest)
- [Devin](https://spiral.ai/integrations/devin/claude-fable-latest)
- [dots](https://spiral.ai/integrations/dots/claude-fable-latest)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/claude-fable-latest)
- [Gemini](https://spiral.ai/integrations/gemini/claude-fable-latest)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/claude-fable-latest)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/claude-fable-latest)
- [goose](https://spiral.ai/integrations/goose/claude-fable-latest)
- [Grok](https://spiral.ai/integrations/grok/claude-fable-latest)
- [Grok Build](https://spiral.ai/integrations/grok-build/claude-fable-latest)
- [Hermes](https://spiral.ai/integrations/hermes/claude-fable-latest)
- [Instinct](https://spiral.ai/integrations/instinct/claude-fable-latest)
- [Manus](https://spiral.ai/integrations/manus/claude-fable-latest)
- [Muse](https://spiral.ai/integrations/muse/claude-fable-latest)
- [Muse Code](https://spiral.ai/integrations/muse-code/claude-fable-latest)
- [n8n](https://spiral.ai/integrations/n8n/claude-fable-latest)
- [Notion](https://spiral.ai/integrations/notion/claude-fable-latest)
- [OpenClaw](https://spiral.ai/integrations/openclaw/claude-fable-latest)
- [opencode](https://spiral.ai/integrations/opencode/claude-fable-latest)
- [Raycast](https://spiral.ai/integrations/raycast/claude-fable-latest)
- [VS Code](https://spiral.ai/integrations/vscode/claude-fable-latest)
- [Windsurf](https://spiral.ai/integrations/windsurf/claude-fable-latest)
- [Zapier](https://spiral.ai/integrations/zapier/claude-fable-latest)

## More Perplexity guides

- [Claude Fable 5.2](https://spiral.ai/integrations/perplexity/claude-fable-5-2)
- [Claude Haiku 4.5](https://spiral.ai/integrations/perplexity/claude-haiku-4-5)
- [Claude Fable 5.1](https://spiral.ai/integrations/perplexity/claude-fable-5-1)
- [Claude Haiku 5.5](https://spiral.ai/integrations/perplexity/claude-haiku-5-5)
- [Claude Fable 5](https://spiral.ai/integrations/perplexity/claude-fable-5)
- [Claude Haiku Latest](https://spiral.ai/integrations/perplexity/claude-haiku-latest)

## Questions about Claude Fable Latest in Perplexity

**Can Perplexity use Claude Fable Latest?**

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

**How much does Claude Fable Latest cost in Perplexity?**

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 Perplexity plan is separate.

**Do I need an Anthropic account to use Claude Fable Latest in Perplexity?**

No. Spiral runs Claude Fable Latest 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 Latest in Perplexity?**

About two minutes: add a remote connector, then sign in to Spiral and approve.

**Does Perplexity wait while Claude Fable Latest runs?**

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

**What is Claude Fable best suited for?**

Difficult software changes, extended research, and analysis that needs repeated checking. Anthropic's current release, Fable 5.2, also supports work across large repositories.

**How much context and output can Claude Fable handle?**

The current Fable 5.2 release supports a one-million-token context window and up to 128,000 output tokens. Thinking uses part of the output allowance, so the maximum is not a promise of 128,000 tokens of visible text.

**Which reasoning effort should I start with?**

Start at high and evaluate the results on your actual tasks before increasing it. Leave enough output room for both thinking and the finished answer.

**What weakness should I watch for on long tasks?**

Fable 5.2 can end a turn while work remains. Give it a completion checklist and explicitly ask it to work through ordinary errors until the requested deliverable is finished.

**Can Claude Fable help with mathematical proofs?**

Yes. Anthropic reports that a team of Fable 5.2 agents formalized Fermat's Last Theorem; for your own work, ask for explicit assumptions and verification with a proof checker where available.

