Processing or generating 10,000 words (approximately 13,200 tokens) with Claude 3.7 Sonnet (Hybrid Reasoning) ranges from $0.00396 (cached input) to $0.198 (full generation).
You send 10,000 words as prompt context, documentation, or background knowledge.
Claude 3.7 Sonnet (Hybrid Reasoning) drafts a complete 10,000 words article, chapter, or code module.
8,000 words input prompt + 2,000 words output reply.
| Model | Provider | Input Cost (10,000 words) | Cached Input Cost | Output Cost (10,000 words) | Context Limit |
|---|---|---|---|---|---|
| Claude 3.7 Sonnet (Hybrid Reasoning) (Current) | anthropic | $0.0396 | $0.00396 | $0.198 | 200,000 |
| GPT-5.6 Sol | openai | $0.064 | $0.0064 | $0.384 | 1,050,000 |
| GPT-5.6 Cyber | openai | $0.16 | $0.016 | $0.96 | 1,050,000 |
| GPT-5.5 Standard | openai | $0.064 | $0.0064 | $0.384 | 512,000 |
| GPT-5.5 Pro | openai | $0.384 | $0.0384 | $2.304 | 512,000 |
| o3-pro (Frontier Reasoning) | openai | $0.256 | $0.0256 | $1.024 | 1,000,000 |
For Claude 3.7 Sonnet (Hybrid Reasoning) (claude_bpe tokenizer), 10,000 words is approximately 13,200 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 10,000 words as input costs $0.0396 (or $0.00396 with prompt caching). Generating 10,000 words as output costs $0.198. 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 $0.00396). For non-urgent asynchronous batch processing, 24-hour batch queues provide a flat 50% discount across all tokens (costing $0.0198 for input, $0.099 for output).
At an average human reading speed of 250 words per minute, 10,000 words takes approximately 40 minutes to read. In contrast, Claude 3.7 Sonnet (Hybrid Reasoning) can process or generate this text in seconds.