Processing or generating 1,000 words (approximately 1,333 tokens) with Codestral 2501 ranges from $0.000040 (cached input) to $0.0012 (full generation).
You send 1,000 words as prompt context, documentation, or background knowledge.
Codestral 2501 drafts a complete 1,000 words article, chapter, or code module.
800 words input prompt + 200 words output reply.
| Model | Provider | Input Cost (1,000 words) | Cached Input Cost | Output Cost (1,000 words) | Context Limit |
|---|---|---|---|---|---|
| Codestral 2501 (Current) | mistral | $0.0004 | $0.000040 | $0.0012 | 256,000 |
| GPT-5.3 Codex | openai | $0.00224 | $0.000224 | $0.0179 | 256,000 |
| DeepSeek Coder V2.5 | deepseek | $0.000187 | $0.000019 | $0.000373 | 128,000 |
| Grok Build 0.1 | xai | $0.001333 | $0.000267 | $0.002666 | 256,000 |
| Qwen 2.5 Coder 32B | qwen | $0.000267 | $0.000027 | $0.0008 | 128,000 |
| DeepInfra — Qwen 2.5 Coder 32B | deepinfra | $0.000107 | $0.000027 | $0.00032 | 128,000 |
For Codestral 2501 (mistral_bpe tokenizer), 1,000 words is approximately 1,333 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 1,000 words as input costs $0.0004 (or $0.000040 with prompt caching). Generating 1,000 words as output costs $0.0012. 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 $0.000040). For non-urgent asynchronous batch processing, 24-hour batch queues provide a flat 50% discount across all tokens (costing $0.0002 for input, $0.0006 for output).
At an average human reading speed of 250 words per minute, 1,000 words takes approximately 4 minutes to read. In contrast, Codestral 2501 can process or generate this text in seconds.