Processing or generating 5,000 words (approximately 6,665 tokens) with GPT-4 Turbo ranges from $0.0333 (cached input) to $0.20 (full generation).
You send 5,000 words as prompt context, documentation, or background knowledge.
GPT-4 Turbo drafts a complete 5,000 words article, chapter, or code module.
4,000 words input prompt + 1,000 words output reply.
| Model | Provider | Input Cost (5,000 words) | Cached Input Cost | Output Cost (5,000 words) | Context Limit |
|---|---|---|---|---|---|
| GPT-4 Turbo (Current) | openai | $0.0667 | $0.0333 | $0.20 | 128,000 |
| GPT-3.5 Turbo | openai | $0.003333 | $0.000833 | $0.009998 | 16,385 |
For GPT-4 Turbo (cl100k_base tokenizer), 5,000 words is approximately 6,665 tokens (an average ratio of 1.33 tokens per word in English). Code, technical vocabulary, and non-English scripts will have higher token densities.
Sending 5,000 words as input costs $0.0667 (or $0.0333 with prompt caching). Generating 5,000 words as output costs $0.20. 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 $0.0333). For non-urgent asynchronous batch processing, 24-hour batch queues provide a flat 50% discount across all tokens (costing $0.0333 for input, $0.10 for output).
At an average human reading speed of 250 words per minute, 5,000 words takes approximately 20 minutes to read. In contrast, GPT-4 Turbo can process or generate this text in seconds.