Processing or generating 100,000 words (approximately 128,000 tokens) with GPT-5.6 Luna Pro (OpenRouter) ranges from $0.00256 (cached input) to $0.1536 (full generation).
Quick answer
For 100,000 words, GPT-5.6 Luna Pro (OpenRouter) processes approximately 128,000 tokens. That costs $0.0256 as uncached input, $0.00256 with the modeled cache discount, or $0.1536 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 100,000 words as prompt context, documentation, or background knowledge.
GPT-5.6 Luna Pro (OpenRouter) drafts a complete 100,000 words article, chapter, or code module.
80,000 words input prompt + 20,000 words output reply.
| Model | Provider | Input Cost (100,000 words) | Cached Input Cost | Output Cost (100,000 words) | Context Limit |
|---|---|---|---|---|---|
| GPT-5.6 Luna Pro (OpenRouter) (Current) | openai | $0.0256 | $0.00256 | $0.1536 | 1,050,000 |
| GPT-5.6 Sol | openai | $0.64 | $0.064 | $3.84 | 1,050,000 |
| GPT-5.6 Cyber | openai | $1.60 | $0.16 | $9.60 | 1,050,000 |
| GPT-5.5 Standard | openai | $0.64 | $0.064 | $3.84 | 512,000 |
| GPT-5.5 Pro | openai | $3.84 | $0.384 | $23.04 | 512,000 |
| o3-pro (Frontier Reasoning) | openai | $2.56 | $0.256 | $10.24 | 1,000,000 |
For GPT-5.6 Luna Pro (OpenRouter) (o200k_base tokenizer), 100,000 words is approximately 128,000 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 100,000 words as input costs $0.0256 (or $0.00256 with prompt caching). Generating 100,000 words as output costs $0.1536. 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 $0.00256). For non-urgent asynchronous batch processing, 24-hour batch queues provide a flat 50% discount across all tokens (costing $0.0128 for input, $0.0768 for output).
At an average human reading speed of 250 words per minute, 100,000 words takes approximately 400 minutes to read. In contrast, GPT-5.6 Luna Pro (OpenRouter) can process or generate this text in seconds.