Claude Fable 5 vs Claude Sonnet 5 — Side-by-side pricing
Side-by-side API pricing and tokenizer details for Claude Fable 5 (Anthropic) and Claude Sonnet 5 (Anthropic).
Side-by-side pricing
| Feature | Claude Fable 5 | Claude Sonnet 5 |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Input (per 1M tokens) | $10.00 | $2.00 |
| Output (per 1M tokens) | $50.00 | $10.00 |
| Context caching | Yes — 90% off cached tokens | Yes — 90% off cached tokens |
| Batch API discount | 50% off | 50% off |
| Context window | 1M tokens | 1M tokens |
| Tokenizer | Anthropic tokenizer (Opus 4.7+) | Anthropic tokenizer (Opus 4.7+) |
ⓘ Claude Sonnet 5: Introductory pricing through Aug 31, 2026. Standard price: $3.00 / $15.00 per MTok after that date.
Real-world cost example
1,000 API requests per month, each with 500 input tokens and 200 output tokens (500K input + 200K output total).
Claude Fable 5
$15.0000
Input: $5.0000 +Output: $10.0000
Claude Sonnet 5
$3.0000
Input: $1.0000 +Output: $2.0000
Claude Sonnet 5 is 80% cheaper for this workload — saving $12.0000 per month at this volume.
Frequently asked questions
No, Claude Sonnet 5 is cheaper for the typical workload above. At $2.00/1M input and $10.00/1M output tokens, it costs $3.0000 versus $15.0000 for Claude Fable 5 — a 80% difference.
Claude Fable 5 supports a 1M token context window. Claude Sonnet 5 supports a 1M token context window. A larger context window lets you include more text — documents, conversation history, or code — in a single API call.
Claude Fable 5 supports context caching (90% off repeated tokens). It offers a 50% Batch API discount. Claude Sonnet 5 supports context caching (90% off repeated tokens). It offers a 50% Batch API discount.
Yes, both Claude Fable 5 and Claude Sonnet 5 use the Anthropic tokenizer (Opus 4.7+). The same text produces identical token counts on both models, so any cost difference is purely due to the rate each provider charges per token.
Claude Fable 5 (Anthropic): $10 input / $50 output per 1M tokens. Claude Sonnet 5 (Anthropic): $2 input / $10 output per 1M tokens. Rates shown before caching or batch discounts.
For an 80% output / 20% input workload — typical for code generation or long-form writing — Claude Fable 5 costs $42.0000 per 1M total tokens and Claude Sonnet 5 costs $8.4000. Claude Sonnet 5 is 80% cheaper for this pattern. For your exact ratio, paste a real prompt into the calculator above.
Claude Fable 5 has a 1M-token context window — approximately 750K words or ~3K pages of standard text. Claude Sonnet 5 has a 1M-token context window — approximately 750K words or ~3K pages. (Estimates assume ~0.75 words per token.)
Calculate costs for your actual prompt
Paste your prompt into the calculator and get exact token counts using each model's real tokenizer — all in your browser.
Open calculator