Processing or generating 10,000 words (approximately 12,800 tokens) with GPT-4o mini ranges from $0.00096 (cached input) to $0.00768 (full generation).
You send 10,000 words as prompt context, documentation, or background knowledge.
GPT-4o mini 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 |
|---|---|---|---|---|---|
| GPT-4o mini (Current) | openai | $0.00192 | $0.00096 | $0.00768 | 128,000 |
| GPT-5.6 Luna | openai | $0.00256 | $0.000256 | $0.0154 | 1,050,000 |
| GPT-5.4 mini | openai | $0.0096 | $0.00096 | $0.0576 | 256,000 |
| GPT-5.4 nano | openai | $0.00256 | $0.000256 | $0.016 | 128,000 |
| Claude Haiku 4.5 | anthropic | $0.0132 | $0.00132 | $0.066 | 1,000,000 |
| Claude 3.5 Haiku | anthropic | $0.0106 | $0.001056 | $0.0528 | 200,000 |
For GPT-4o mini (o200k_base tokenizer), 10,000 words is approximately 12,800 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 10,000 words as input costs $0.00192 (or $0.00096 with prompt caching). Generating 10,000 words as output costs $0.00768. 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 $0.00096). For non-urgent asynchronous batch processing, 24-hour batch queues provide a flat 50% discount across all tokens (costing $0.00096 for input, $0.00384 for output).
At an average human reading speed of 250 words per minute, 10,000 words takes approximately 40 minutes to read. In contrast, GPT-4o mini can process or generate this text in seconds.