Processing or generating 5,000 words (approximately 6,400 tokens) with o1-mini ranges from $0.00352 (cached input) to $0.0282 (full generation).
You send 5,000 words as prompt context, documentation, or background knowledge.
o1-mini 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 |
|---|---|---|---|---|---|
| o1-mini (Current) | openai | $0.00704 | $0.00352 | $0.0282 | 128,000 |
| GPT-5.6 Terra | openai | $0.0128 | $0.00128 | $0.0768 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $0.016 | $0.0016 | $0.096 | 256,000 |
| o3-mini | openai | $0.00704 | $0.00352 | $0.0282 | 200,000 |
| o4-mini | openai | $0.00704 | $0.00176 | $0.0282 | 256,000 |
| Claude Sonnet 5 | anthropic | $0.0132 | $0.00132 | $0.066 | 1,000,000 |
For o1-mini (o200k_base tokenizer), 5,000 words is approximately 6,400 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 5,000 words as input costs $0.00704 (or $0.00352 with prompt caching). Generating 5,000 words as output costs $0.0282. 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 $0.00352). For non-urgent asynchronous batch processing, 24-hour batch queues provide a flat 50% discount across all tokens (costing $0.00352 for input, $0.0141 for output).
At an average human reading speed of 250 words per minute, 5,000 words takes approximately 20 minutes to read. In contrast, o1-mini can process or generate this text in seconds.