Processing or generating 50,000 words (approximately 66,650 tokens) with Mistral Small 4 ranges from $0.001 (cached input) to $0.04 (full generation).
You send 50,000 words as prompt context, documentation, or background knowledge.
Mistral Small 4 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 |
|---|---|---|---|---|---|
| Mistral Small 4 (Current) | mistral | $0.009998 | $0.001 | $0.04 | 128,000 |
| GPT-5.6 Luna | openai | $0.0128 | $0.00128 | $0.0768 | 1,050,000 |
| GPT-5.4 mini | openai | $0.048 | $0.0048 | $0.288 | 256,000 |
| GPT-5.4 nano | openai | $0.0128 | $0.00128 | $0.08 | 128,000 |
| GPT-4o mini | openai | $0.0096 | $0.0048 | $0.0384 | 128,000 |
| Claude Haiku 4.5 | anthropic | $0.066 | $0.0066 | $0.33 | 1,000,000 |
For Mistral Small 4 (mistral_bpe 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 $0.009998 (or $0.001 with prompt caching). Generating 50,000 words as output costs $0.04. 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 $0.001). For non-urgent asynchronous batch processing, 24-hour batch queues provide a flat 50% discount across all tokens (costing $0.004999 for input, $0.02 for output).
At an average human reading speed of 250 words per minute, 50,000 words takes approximately 200 minutes to read. In contrast, Mistral Small 4 can process or generate this text in seconds.