Processing or generating 5,000 words (approximately 6,665 tokens) with Mistral Small 3.2 24B (OpenRouter) ranges from $0.000125 (cached input) to $0.001333 (full generation).
Quick answer
For 5,000 words, Mistral Small 3.2 24B (OpenRouter) processes approximately 6,665 tokens. That costs $0.0005 as uncached input, $0.000125 with the modeled cache discount, or $0.001333 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.
Mistral Small 3.2 24B (OpenRouter) 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 |
|---|---|---|---|---|---|
| Mistral Small 3.2 24B (OpenRouter) (Current) | mistral | $0.0005 | $0.000125 | $0.001333 | 131,072 |
| GPT-5.6 Luna | openai | $0.00128 | $0.000128 | $0.00768 | 1,050,000 |
| GPT-5.4 mini | openai | $0.0048 | $0.00048 | $0.0288 | 256,000 |
| GPT-5.4 nano | openai | $0.00128 | $0.000128 | $0.008 | 128,000 |
| GPT-4o mini | openai | $0.00096 | $0.00048 | $0.00384 | 128,000 |
| Claude Haiku 4.5 | anthropic | $0.0066 | $0.00066 | $0.033 | 1,000,000 |
For Mistral Small 3.2 24B (OpenRouter) (mistral_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 $0.0005 (or $0.000125 with prompt caching). Generating 5,000 words as output costs $0.001333. 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 $0.000125). For non-urgent asynchronous batch processing, 24-hour batch queues provide a flat 50% discount across all tokens (costing $0.00025 for input, $0.000667 for output).
At an average human reading speed of 250 words per minute, 5,000 words takes approximately 20 minutes to read. In contrast, Mistral Small 3.2 24B (OpenRouter) can process or generate this text in seconds.