Processing or generating 2,500 words (approximately 3,200 tokens) with GPT-5.4 mini ranges from $0.00024 (cached input) to $0.0144 (full generation).
You send 2,500 words as prompt context, documentation, or background knowledge.
GPT-5.4 mini drafts a complete 2,500 words article, chapter, or code module.
2,000 words input prompt + 500 words output reply.
| Model | Provider | Input Cost (2,500 words) | Cached Input Cost | Output Cost (2,500 words) | Context Limit |
|---|---|---|---|---|---|
| GPT-5.4 mini (Current) | openai | $0.0024 | $0.00024 | $0.0144 | 256,000 |
| GPT-5.6 Luna | openai | $0.00064 | $0.000064 | $0.00384 | 1,050,000 |
| GPT-5.4 nano | openai | $0.00064 | $0.000064 | $0.004 | 128,000 |
| GPT-4o mini | openai | $0.00048 | $0.00024 | $0.00192 | 128,000 |
| Claude Haiku 4.5 | anthropic | $0.0033 | $0.00033 | $0.0165 | 1,000,000 |
| Claude 3.5 Haiku | anthropic | $0.00264 | $0.000264 | $0.0132 | 200,000 |
For GPT-5.4 mini (o200k_base tokenizer), 2,500 words is approximately 3,200 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 2,500 words as input costs $0.0024 (or $0.00024 with prompt caching). Generating 2,500 words as output costs $0.0144. 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 $0.00024). For non-urgent asynchronous batch processing, 24-hour batch queues provide a flat 50% discount across all tokens (costing $0.0012 for input, $0.0072 for output).
At an average human reading speed of 250 words per minute, 2,500 words takes approximately 10 minutes to read. In contrast, GPT-5.4 mini can process or generate this text in seconds.