Claude Fable 5 pricing
Claude Fable 5 costs $10 per million input tokens and $50 per million output tokens , with cached input at $1. Its context window is 1M tokens. Batch requests are discounted 50%.
Price per million tokens
| Input | $10 |
| Cached input | $1 |
| Output | $50 |
| Context window | 1M tokens |
| Batch discount | −50% |
| Minimum prefix to cache | 512 tokens |
| Tokenizer factor | ×1.3 |
What it costs in practice
Monthly cost for three common workload shapes, with prompt caching applied.
| Workload | Shape | Per request | Per month |
|---|---|---|---|
| Support chatbot | 1.5k in / 400 out, 100k requests/month, 30% cached | $0.0402 | $4,024 |
| RAG / document Q&A | 12k in / 700 out, 50k requests/month, 60% cached | $0.117 | $5,863 |
| Coding agent | 25k in / 2.5k out, 20k requests/month, 80% cached | $0.254 | $5,070 |
Model your own workload with caching, batching and tokenizer correction →
Caching on Claude Fable 5
A cached prefix on this model must be at least 512 tokens. Below that, Anthropic ignores cache_control silently — no error is returned and you pay full input price on
every request. A cache hit costs $1 per million tokens, roughly 10% of the
base input rate.
Comparable models from other providers
| Model | Provider | Input | Output |
|---|---|---|---|
| GPT-5.6 Sol | OpenAI | $5 | $30 |
| GPT-5.5 | OpenAI | $5 | $30 |
| GPT-5.5 Pro | OpenAI | $30 | $180 |
| GPT-5.4 | OpenAI | $2.5 | $15 |
All figures verified 2026-08-18 against Anthropic's official pricing documentation . Fields the provider does not publish are shown as “—” rather than estimated.