From the source
From the source
From the source

From the source
The Agent API Models reference and pricing calculator include openai/gpt-6.2-sol and openai/gpt-6.2-astra . For requests with up to 272,000 input tokens, GPT-6.2 Sol costs $2.00 per million input tokens, $0.10 per million cached input tokens, and $10.00 per million output tokens.
GPT-6.2 Astra costs $8.00, $0.40, and $40.00, respectively. Above that input threshold, input and cache-read prices double, and output prices increase by 50%. Cache creation costs $2.50 per million cache-write tokens for GPT-6.2 Sol and $10.00 for GPT-6.2 Astra up to 272,000 input tokens; these rates double above that threshold. These are default-processing rates; see the Models reference for service tiers and calculator limitations.
docs.perplexity.ai