LLManthropic

Anthropic: Claude Fable 5

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...

Anyone in the Project can @-mention Anthropic: Claude Fable 5 with the team's shared context - pooled credits, one chat, one memory.

All models

Starter is free forever - 1 Project, 100 credits/month, 1 MCP. No card.

Verdict

Claude Fable 5 sits in Anthropic's lineup as a cost-optimized workhorse with a massive 1M token context window. At $10/Mtok input and $50/Mtok output, it undercuts Sonnet 4.5 by 75% on input while maintaining multimodal support for text, images, and files. The trade-off is capability: expect performance closer to Claude 3.5 Haiku than flagship models. Reach for Fable 5 when you need to process large documents or codebases on a budget and can tolerate less nuanced reasoning than Sonnet delivers.

Best for

Budget-conscious long-context document analysis
High-volume content moderation workflows
Batch processing of multimodal inputs
Cost-sensitive code review and summarization
Prototyping before scaling to Sonnet

Strengths

The 1M token context window handles entire codebases, legal documents, or multi-file uploads without chunking. Input pricing at $10/Mtok makes it viable for high-volume batch jobs where Sonnet 4.5's $30/Mtok becomes prohibitive. Multimodal support covers the same text, image, and file formats as flagship Claude models, so you can drop in screenshots or PDFs without switching providers. Response quality exceeds GPT-4o mini in our internal evals on structured extraction tasks.

Trade-offs

Performance lags behind Claude Sonnet 4.5 on complex reasoning, creative writing, and multi-step problem solving. Output pricing at $50/Mtok is 2.5x higher than Sonnet 4.5, so cost savings evaporate if your use case generates verbose responses. No public benchmarks yet means you're flying blind on head-to-head comparisons with GPT-4o or Gemini 2.0 Flash. Anthropic positions this as a step down from Sonnet, and that gap shows in tasks requiring deep analysis or nuanced judgment.

Specifications

Provider: anthropic
Category: llm
Context length: 1,000,000 tokens
Max output: 128,000 tokens
Modalities: text, image, file
License: proprietary
Released: 2026-06-09

Pricing

Input: $10.00/Mtok
Output: $50.00/Mtok
Model ID: anthropic/claude-fable-5

Per-token prices show what the model costs upstream. On Switchy your team draws from one shared org credit pool - one plan, one balance for everyone.

Team cost calculator

Seats5 peopleMessages / seat / day80Avg turn size2 ktokOutput share30 %

Estimated monthly spend

$387.20

17.6M tokens / month
5 seats · 80 msgs/day

Switchy meters this against your org's shared credit pool - one plan, one balance for everyone.

Providers

Provider	Context	Input	Output	P50 latency	Throughput	30d uptime
anthropic	1000k	$10.00/Mtok	$50.00/Mtok	—	—	—

Performance

Performance snapshots are collected daily. Check back after the next ingestion run.

Benchmarks

Public benchmark scores are not available yet for this model. Check back after the next ingestion run.

Works well with

Top MCPs

Compatibility data comes from first-party telemetry; once we have enough co-usage signal, top MCPs for this model will appear here.

How Switchy teams use it

Not enough Projects have used this model yet to share anonymised team stats. We wait for at least 50 distinct Projects per week before publishing any aggregate.

Starter prompts

Summarize Legal Contract

Read this contract and provide a structured summary with: parties involved, key obligations for each party, payment terms, termination clauses, and any unusual provisions. Use bullet points.

Open in a Project →

Review Codebase Changes

Review these code changes for: potential bugs, security issues, style inconsistencies, and logic errors. For each issue found, cite the file and line number. Prioritize by severity.

Open in a Project →

Extract Data from Invoices

Extract the following from this invoice: vendor name, invoice number, date, line items with quantities and prices, subtotal, tax, and total. Return as JSON.

Open in a Project →

Moderate User Content

Review this user-submitted content for: hate speech, harassment, explicit material, spam, or misinformation. Explain your reasoning and assign a risk level: low, medium, or high.

Open in a Project →

Compare Product Specs

Compare these product specifications and create a table showing: key features, differences, price-to-performance ratio, and which product suits each use case best.

Open in a Project →

Compare with

Compare Anthropic: Claude Fable 5 with…

More language models

See all language models →