Processing or generating 5,000 words (approximately 6,665 tokens) with Fireworks AI — Llama 4 Scout ranges from $0.0002 (cached input) to $0.002399 (full generation).
Quick answer
For 5,000 words, Fireworks AI — Llama 4 Scout processes approximately 6,665 tokens. That costs $0.0008 as uncached input, $0.0002 with the modeled cache discount, or $0.002399 when generated as output.
Method & trust
The estimate converts the selected English word count with the model tokenizer family, then applies the published input/output price per million tokens. Real prompts vary with code, formatting, language, and system instructions.
You send 5,000 words as prompt context, documentation, or background knowledge.
Fireworks AI — Llama 4 Scout 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 — Llama 4 Scout (Current) | fireworks | $0.0008 | $0.0002 | $0.002399 | 10,000,000 |
| 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 — Llama 4 Scout (tiktoken_cl100k 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 $0.0008 (or $0.0002 with prompt caching). Generating 5,000 words as output costs $0.002399. 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 $0.0002). For non-urgent asynchronous batch processing, 24-hour batch queues provide a flat 50% discount across all tokens (costing $0.0004 for input, $0.0012 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 — Llama 4 Scout can process or generate this text in seconds.