Processing or generating 500 words (approximately 640 tokens) with GPT-4o mini ranges from $0.000048 (cached input) to $0.000384 (full generation).
You send 500 words as prompt context, documentation, or background knowledge.
GPT-4o mini drafts a complete 500 words article, chapter, or code module.
400 words input prompt + 100 words output reply.
| Model | Provider | Input Cost (500 words) | Cached Input Cost | Output Cost (500 words) | Context Limit |
|---|---|---|---|---|---|
| GPT-4o mini (Current) | openai | $0.000096 | $0.000048 | $0.000384 | 128,000 |
| GPT-5.6 Luna | openai | $0.000128 | $0.000013 | $0.000768 | 1,050,000 |
| GPT-5.4 mini | openai | $0.00048 | $0.000048 | $0.00288 | 256,000 |
| GPT-5.4 nano | openai | $0.000128 | $0.000013 | $0.0008 | 128,000 |
| Claude Haiku 4.5 | anthropic | $0.00066 | $0.000066 | $0.0033 | 1,000,000 |
| Claude 3.5 Haiku | anthropic | $0.000528 | $0.000053 | $0.00264 | 200,000 |
For GPT-4o mini (o200k_base tokenizer), 500 words is approximately 640 tokens (an average ratio of 1.28 tokens per word in English). Code, technical vocabulary, and non-English scripts will have higher token densities.
Sending 500 words as input costs $0.000096 (or $0.000048 with prompt caching). Generating 500 words as output costs $0.000384. 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 $0.000048). For non-urgent asynchronous batch processing, 24-hour batch queues provide a flat 50% discount across all tokens (costing $0.000048 for input, $0.000192 for output).
At an average human reading speed of 250 words per minute, 500 words takes approximately 2 minutes to read. In contrast, GPT-4o mini can process or generate this text in seconds.