Processing or generating 1,000 words (approximately 1,280 tokens) with o4-mini ranges from $0.000352 (cached input) to $0.005632 (full generation).
You send 1,000 words as prompt context, documentation, or background knowledge.
o4-mini 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 |
|---|---|---|---|---|---|
| o4-mini (Current) | openai | $0.001408 | $0.000352 | $0.005632 | 256,000 |
| GPT-5.6 Terra | openai | $0.00256 | $0.000256 | $0.0154 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $0.0032 | $0.00032 | $0.0192 | 256,000 |
| o3-mini | openai | $0.001408 | $0.000704 | $0.005632 | 200,000 |
| o1-mini | openai | $0.001408 | $0.000704 | $0.005632 | 128,000 |
| Claude Sonnet 5 | anthropic | $0.00264 | $0.000264 | $0.0132 | 1,000,000 |
For o4-mini (o200k_base tokenizer), 1,000 words is approximately 1,280 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 1,000 words as input costs $0.001408 (or $0.000352 with prompt caching). Generating 1,000 words as output costs $0.005632. 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 $0.000352). For non-urgent asynchronous batch processing, 24-hour batch queues provide a flat 50% discount across all tokens (costing $0.000704 for input, $0.002816 for output).
At an average human reading speed of 250 words per minute, 1,000 words takes approximately 4 minutes to read. In contrast, o4-mini can process or generate this text in seconds.