Processing or generating 1,000 words (approximately 1,333 tokens) with GPT-3.5 Turbo ranges from $0.000167 (cached input) to $0.002 (full generation).
Quick answer
For 1,000 words, GPT-3.5 Turbo processes approximately 1,333 tokens. That costs $0.000667 as uncached input, $0.000167 with the modeled cache discount, or $0.002 when generated as output.
Method & trust
The estimate converts the selected English word count with the model tokenizer family, then applies the published input/output price per million tokens. Real prompts vary with code, formatting, language, and system instructions.
You send 1,000 words as prompt context, documentation, or background knowledge.
GPT-3.5 Turbo drafts a complete 1,000 words article, chapter, or code module.
800 words input prompt + 200 words output reply.
| Model | Provider | Input Cost (1,000 words) | Cached Input Cost | Output Cost (1,000 words) | Context Limit |
|---|---|---|---|---|---|
| GPT-3.5 Turbo (Current) | openai | $0.000667 | $0.000167 | $0.002 | 16,385 |
| GPT-4 Turbo | openai | $0.0133 | $0.006665 | $0.04 | 128,000 |
| GLM-4-32B-0414-128K (Z.ai) | zai | $0.000133 | $0.000033 | $0.000133 | 128,000 |
For GPT-3.5 Turbo (cl100k_base tokenizer), 1,000 words is approximately 1,333 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 1,000 words as input costs $0.000667 (or $0.000167 with prompt caching). Generating 1,000 words as output costs $0.002. 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 $0.000167). For non-urgent asynchronous batch processing, 24-hour batch queues provide a flat 50% discount across all tokens (costing $0.000333 for input, $0.001 for output).
At an average human reading speed of 250 words per minute, 1,000 words takes approximately 4 minutes to read. In contrast, GPT-3.5 Turbo can process or generate this text in seconds.