Processing or generating 100,000 words (approximately 132,000 tokens) with Claude Sonnet 5 ranges from $0.0264 (cached input) to $1.32 (full generation).
You send 100,000 words as prompt context, documentation, or background knowledge.
Claude Sonnet 5 drafts a complete 100,000 words article, chapter, or code module.
80,000 words input prompt + 20,000 words output reply.
| Model | Provider | Input Cost (100,000 words) | Cached Input Cost | Output Cost (100,000 words) | Context Limit |
|---|---|---|---|---|---|
| Claude Sonnet 5 (Current) | anthropic | $0.264 | $0.0264 | $1.32 | 1,000,000 |
| GPT-5.6 Terra | openai | $0.256 | $0.0256 | $1.536 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $0.32 | $0.032 | $1.92 | 256,000 |
| o3-mini | openai | $0.1408 | $0.0704 | $0.5632 | 200,000 |
| o4-mini | openai | $0.1408 | $0.0352 | $0.5632 | 256,000 |
| o1-mini | openai | $0.1408 | $0.0704 | $0.5632 | 128,000 |
For Claude Sonnet 5 (claude_bpe tokenizer), 100,000 words is approximately 132,000 tokens (an average ratio of 1.32 tokens per word in English). Code, technical vocabulary, and non-English scripts will have higher token densities.
Sending 100,000 words as input costs $0.264 (or $0.0264 with prompt caching). Generating 100,000 words as output costs $1.32. Output tokens are more expensive because autoregressive token generation requires significantly more computation per token.
Yes! If your input text is part of a repeated context, prompt caching saves 50% to 90% (costing $0.0264). For non-urgent asynchronous batch processing, 24-hour batch queues provide a flat 50% discount across all tokens (costing $0.132 for input, $0.66 for output).
At an average human reading speed of 250 words per minute, 100,000 words takes approximately 400 minutes to read. In contrast, Claude Sonnet 5 can process or generate this text in seconds.