Processing or generating 500 words (approximately 667 tokens) with Text Embedding 004 ranges from $0.0000033 (cached input) to $0.00 (full generation).
You send 500 words as prompt context, documentation, or background knowledge.
Text Embedding 004 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 |
|---|---|---|---|---|---|
| Text Embedding 004 (Current) | $0.000013 | $0.0000033 | $0.00 | 8,192 | |
| Text Embedding 3 (Small) | openai | $0.000013 | $0.0000033 | $0.00 | 8,191 |
| Text Embedding 3 (Large) | openai | $0.000087 | $0.000022 | $0.00 | 8,191 |
For Text Embedding 004 (sentencepiece tokenizer), 500 words is approximately 667 tokens (an average ratio of 1.33 tokens per word in English). Code, technical vocabulary, and non-English scripts will have higher token densities.
Sending 500 words as input costs $0.000013 (or $0.0000033 with prompt caching). Generating 500 words as output costs $0.00. 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 $0.0000033). For non-urgent asynchronous batch processing, 24-hour batch queues provide a flat 50% discount across all tokens (costing $0.0000067 for input, $0.00 for output).
At an average human reading speed of 250 words per minute, 500 words takes approximately 2 minutes to read. In contrast, Text Embedding 004 can process or generate this text in seconds.