Processing or generating 1,000 words (approximately 1,333 tokens) with Perplexity Sonar Reasoning Pro ranges from $0.000667 (cached input) to $0.0107 (full generation).
Quick answer
For 1,000 words, Perplexity Sonar Reasoning Pro processes approximately 1,333 tokens. That costs $0.002666 as uncached input, $0.000667 with the modeled cache discount, or $0.0107 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 1,000 words as prompt context, documentation, or background knowledge.
Perplexity Sonar Reasoning Pro 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 |
|---|---|---|---|---|---|
| Perplexity Sonar Reasoning Pro (Current) | perplexity | $0.002666 | $0.000667 | $0.0107 | 127,072 |
| GPT-5.6 Sol | openai | $0.0064 | $0.00064 | $0.0384 | 1,050,000 |
| GPT-5.6 Cyber | openai | $0.016 | $0.0016 | $0.096 | 1,050,000 |
| GPT-5.5 Standard | openai | $0.0064 | $0.00064 | $0.0384 | 512,000 |
| GPT-5.5 Pro | openai | $0.0384 | $0.00384 | $0.2304 | 512,000 |
| o3-pro (Frontier Reasoning) | openai | $0.0256 | $0.00256 | $0.1024 | 1,000,000 |
For Perplexity Sonar Reasoning Pro (tiktoken_cl100k 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 $0.002666 (or $0.000667 with prompt caching). Generating 1,000 words as output costs $0.0107. 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 $0.000667). For non-urgent asynchronous batch processing, 24-hour batch queues provide a flat 50% discount across all tokens (costing $0.001333 for input, $0.005332 for output).
At an average human reading speed of 250 words per minute, 1,000 words takes approximately 4 minutes to read. In contrast, Perplexity Sonar Reasoning Pro can process or generate this text in seconds.