LLManthropic

Anthropic: Claude Fable 5 (batch)

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 (batch) 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 batch is Anthropic's asynchronous processing tier for their Fable 5 model, trading immediate response for 50% cost savings. With $5/Mtok input and $25/Mtok output, it undercuts real-time Claude pricing significantly while maintaining the same 1M token context window and multimodal capabilities. Requests process within 24 hours, making this the right choice for bulk document analysis, overnight data pipelines, or any workflow where you can queue tasks and wait. If you need conversational speed, pay for real-time; if you're processing batches of reports or images on a schedule, this is your model.

Best for

Overnight document processing pipelines
Bulk invoice or contract analysis
Scheduled report generation from files
Cost-sensitive image annotation tasks
Non-interactive data transformation jobs

Strengths

The 50% discount over real-time Claude pricing makes this the most economical way to access Anthropic's Fable 5 capabilities when latency doesn't matter. The full 1M token context window remains intact, so you can process book-length documents or multi-file codebases in single requests. Multimodal support means you can batch-process screenshots, diagrams, and PDFs alongside text. For teams running nightly ETL jobs or processing customer support ticket archives, the cost savings compound quickly without sacrificing model quality.

Trade-offs

Batch requests can take up to 24 hours to complete, which rules out any interactive or user-facing use case. You lose the conversational back-and-forth that makes Claude useful for iterative tasks like debugging or brainstorming. Without public benchmarks yet, we can't compare Fable 5's accuracy to Claude 3.5 Sonnet or Opus on standard evals. If your workflow needs sub-second responses or real-time feedback loops, the cost savings won't justify the wait.

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: $5.00/Mtok
Output: $25.00/Mtok
Model ID: anthropic/claude-fable-5:batch

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

$193.60

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-level routing data is not available yet for this model.

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

Extract Invoice Line Items

Extract all line items from this invoice image into a JSON array. For each item include: description, quantity, unit_price, and total. Return only valid JSON with no markdown formatting.

Open in a Project →

Summarize Support Tickets

Read this support ticket thread and produce a 3-sentence summary covering: the customer's core issue, steps taken by support, and current resolution status. Be specific about technical details.

Open in a Project →

Classify Document Types

Classify this document into one of these categories: contract, invoice, receipt, report, correspondence, or other. Return only the category name and a one-sentence justification.

Open in a Project →

Generate Product Descriptions

Write a 100-word product description for this item based on the provided specifications. Focus on benefits over features, use active voice, and target a general consumer audience.

Open in a Project →

Translate Technical Docs

Translate this technical documentation from English to [target language]. Preserve all code snippets unchanged, maintain heading structure, and keep technical terms consistent with industry standards.

Open in a Project →

Compare with

Compare Anthropic: Claude Fable 5 (batch) with…

More language models

See all language models →