Processing or generating 5,000 words (approximately 6,665 tokens) with Fireworks AI — DeepSeek R1 ranges from $0.000916 (cached input) to $0.0146 (full generation).
You send 5,000 words as prompt context, documentation, or background knowledge.
Fireworks AI — DeepSeek R1 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 |
|---|---|---|---|---|---|
| Fireworks AI — DeepSeek R1 (Current) | fireworks | $0.003666 | $0.000916 | $0.0146 | 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 |
| o1-mini | openai | $0.00704 | $0.00352 | $0.0282 | 128,000 |
For Fireworks AI — DeepSeek R1 (deepseek_bpe tokenizer), 5,000 words is approximately 6,665 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 5,000 words as input costs $0.003666 (or $0.000916 with prompt caching). Generating 5,000 words as output costs $0.0146. 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 $0.000916). For non-urgent asynchronous batch processing, 24-hour batch queues provide a flat 50% discount across all tokens (costing $0.001833 for input, $0.007298 for output).
At an average human reading speed of 250 words per minute, 5,000 words takes approximately 20 minutes to read. In contrast, Fireworks AI — DeepSeek R1 can process or generate this text in seconds.