Processing or generating 500 words (approximately 667 tokens) with Codestral 2501 ranges from $0.000020 (cached input) to $0.0006 (full generation).
You send 500 words as prompt context, documentation, or background knowledge.
Codestral 2501 drafts a complete 500 words article, chapter, or code module.
400 words input prompt + 100 words output reply.
| Model | Provider | Input Cost (500 words) | Cached Input Cost | Output Cost (500 words) | Context Limit |
|---|---|---|---|---|---|
| Codestral 2501 (Current) | mistral | $0.0002 | $0.000020 | $0.0006 | 256,000 |
| GPT-5.3 Codex | openai | $0.00112 | $0.000112 | $0.00896 | 256,000 |
| DeepSeek Coder V2.5 | deepseek | $0.000093 | $0.0000093 | $0.000187 | 128,000 |
| Grok Build 0.1 | xai | $0.000667 | $0.000133 | $0.001334 | 256,000 |
| Qwen 2.5 Coder 32B | qwen | $0.000133 | $0.000013 | $0.0004 | 128,000 |
| DeepInfra — Qwen 2.5 Coder 32B | deepinfra | $0.000053 | $0.000013 | $0.00016 | 128,000 |
For Codestral 2501 (mistral_bpe tokenizer), 500 words is approximately 667 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 500 words as input costs $0.0002 (or $0.000020 with prompt caching). Generating 500 words as output costs $0.0006. 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 $0.000020). For non-urgent asynchronous batch processing, 24-hour batch queues provide a flat 50% discount across all tokens (costing $0.0001 for input, $0.0003 for output).
At an average human reading speed of 250 words per minute, 500 words takes approximately 2 minutes to read. In contrast, Codestral 2501 can process or generate this text in seconds.