### Answer --- Retell AI has pricing adjustments based on token usage. When your agent uses more than 3,500 LLM tokens in prompts, the billing duration scales proportionally [(1) ]() . How token-based pricing scaling works: - Scaling Factor = Prompt LLM Tokens ÷ 3,500 - Billed Duration = Original Duration × Scaling Factor (rounded up) What's included in token calculation: - global prompt - functions (tool descriptions) - state / node prompt - transcript between agent and user - tool call history and results Example: - Call duration: 60 seconds - LLM tokens used: 4,200 - Scaling factor: 4,200 ÷ 3,500 = 1.2 - Billed duration: 72 seconds (12 seconds additional charge) Why this happens: Larger LLM prompt lengths incur greater costs due to token-based pricing from underlying model providers, so billing scales accordingly to reflect these increased expenses . For multi-prompt agents specifically, the token count is evaluated as system prompt plus current node tokens, and it moves up and down as you move through the flow [(2) ]() . If your agent jumped from 3,000 to 20,000 tokens, check your: - Total length of all prompts (global + state prompts) [(1) ]() - Function/tool descriptions - Conversation transcript length - Tool call history accumulating during calls

​ To learn more, see the sources I considered: [[1] Exceptions to Our Per-Minute Pricing](https://docs.retellai.com/accounts/billing-exceptions) [[2] Question about Token-Based Pricing for Multi-Prompt Agents](https://discord.com/channels/1186424376300679209/1375213752743366727) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.