Processing or generating 50,000 words (approximately 66,650 tokens) with Text Embedding 3 (Small) ranges from $0.000333 (cached input) to $0.00 (full generation).
You send 50,000 words as prompt context, documentation, or background knowledge.
Text Embedding 3 (Small) drafts a complete 50,000 words article, chapter, or code module.
40,000 words input prompt + 10,000 words output reply.
| Model | Provider | Input Cost (50,000 words) | Cached Input Cost | Output Cost (50,000 words) | Context Limit |
|---|---|---|---|---|---|
| Text Embedding 3 (Small) (Current) | openai | $0.001333 | $0.000333 | $0.00 | 8,191 |
| Text Embedding 3 (Large) | openai | $0.008665 | $0.002166 | $0.00 | 8,191 |
| Text Embedding 004 | $0.001333 | $0.000333 | $0.00 | 8,192 |
For Text Embedding 3 (Small) (cl100k_base tokenizer), 50,000 words is approximately 66,650 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 50,000 words as input costs $0.001333 (or $0.000333 with prompt caching). Generating 50,000 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 $0.000333). For non-urgent asynchronous batch processing, 24-hour batch queues provide a flat 50% discount across all tokens (costing $0.000667 for input, $0.00 for output).
At an average human reading speed of 250 words per minute, 50,000 words takes approximately 200 minutes to read. In contrast, Text Embedding 3 (Small) can process or generate this text in seconds.