Anthropic: Claude Fable Latest
This model always redirects to the latest model in the Claude Fable family.
Anyone in the Space can @-mention Anthropic: Claude Fable Latest with the team's shared context - pooled credits, one chat, one memory.
Starter is free forever - 1 Space, 100 credits/month, 1 MCP. No card.
Verdict
Best for
- High-volume document processing at scale
- Cost-sensitive long-context summarization
- Batch extraction from large file sets
- Prototyping before upgrading to Sonnet
- Maintaining extended conversation history
Strengths
The 1M token window lets you ingest entire codebases, legal documents, or multi-hour transcripts in a single call. At $10/$50 per Mtok, it undercuts Sonnet 4.5 by roughly 75% on input and 60% on output, making it viable for high-throughput pipelines where you're processing hundreds of documents daily. Multimodal support (text, image, file) means you can handle screenshots and PDFs without preprocessing. It's a workhorse for teams that need Anthropic's safety posture and long-context handling but can't justify Sonnet pricing across every use case.
Trade-offs
Fable trades reasoning depth for cost. It will stumble on complex multi-step problems, nuanced creative writing, or tasks requiring deep domain expertise—areas where Sonnet 4.5 or Opus excel. Without public benchmarks, we're inferring from pricing and positioning: expect it to lag 10-20 percentage points behind Sonnet on MMLU, GSM8K, and HumanEval. If your workflow involves iterative refinement, ambiguous instructions, or subtle tone control, you'll hit Fable's ceiling quickly. It's also slower to respond under load compared to Sonnet, so real-time applications may feel sluggish.
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-latest
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
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
Benchmarks
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
Starter prompts
Extract Key Terms from Contract
Read the attached contract and extract: (1) all defined terms with their definitions, (2) party names and roles, (3) key obligations and deadlines. Format as a structured list.Open in a Space →
Summarize Multi-Hour Transcript
Summarize this transcript in 300 words. Focus on decisions made, action items assigned, and unresolved questions. Use bullet points for clarity.Open in a Space →
Batch Process Customer Feedback
Analyze these customer feedback entries. For each, assign a sentiment (positive/neutral/negative) and tag recurring themes (e.g., 'billing issue', 'feature request'). Output as CSV.Open in a Space →
Generate FAQ from Documentation
Read this product documentation and generate 10 FAQ entries. Each should have a question users would actually ask and a concise answer (2-3 sentences).Open in a Space →
Compare Code Versions Across Files
Compare these two code files and list all functional changes. Ignore whitespace and comments. For each change, explain what it does in one sentence.Open in a Space →