Processing or generating 25,000 words (approximately 33,325 tokens) with Cohere Command R+ ranges from $0.0208 (cached input) to $0.3333 (full generation).
You send 25,000 words as prompt context, documentation, or background knowledge.
Cohere Command R+ drafts a complete 25,000 words article, chapter, or code module.
20,000 words input prompt + 5,000 words output reply.
| Model | Provider | Input Cost (25,000 words) | Cached Input Cost | Output Cost (25,000 words) | Context Limit |
|---|---|---|---|---|---|
| Cohere Command R+ (Current) | cohere | $0.0833 | $0.0208 | $0.3333 | 128,000 |
| GPT-5.6 Sol | openai | $0.16 | $0.016 | $0.96 | 1,050,000 |
| GPT-5.6 Cyber | openai | $0.40 | $0.04 | $2.40 | 1,050,000 |
| GPT-5.5 Standard | openai | $0.16 | $0.016 | $0.96 | 512,000 |
| GPT-5.5 Pro | openai | $0.96 | $0.096 | $5.76 | 512,000 |
| o3-pro (Frontier Reasoning) | openai | $0.64 | $0.064 | $2.56 | 1,000,000 |
For Cohere Command R+ (cohere_bpe tokenizer), 25,000 words is approximately 33,325 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 25,000 words as input costs $0.0833 (or $0.0208 with prompt caching). Generating 25,000 words as output costs $0.3333. 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 $0.0208). For non-urgent asynchronous batch processing, 24-hour batch queues provide a flat 50% discount across all tokens (costing $0.0417 for input, $0.1666 for output).
At an average human reading speed of 250 words per minute, 25,000 words takes approximately 100 minutes to read. In contrast, Cohere Command R+ can process or generate this text in seconds.