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

### Answer The LLM Token Surcharge applies when your agent uses more than 3,500 LLM tokens in prompts. [(1) ]() What counts toward the token calculation: - Global prompt - Functions (tool descriptions) - State/node prompt - Transcript between agent and user - Tool call history and results How billing is adjusted: - Scaling Factor = Prompt LLM Tokens ÷ 3,500 - Billed Duration = Original Duration × Scaling Factor (rounded up) 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 exists: Larger prompt lengths incur greater costs due to token-based pricing from underlying model providers, so billing scales accordingly. Note that even if your base prompt is under 3,500 tokens, the surcharge can still apply because the transcript, tool call history, and results accumulate during the conversation. [(7) ]()

​ To learn more, see the sources I considered: [[1] Exceptions to Our Per-Minute Pricing](https://docs.retellai.com/accounts/billing-exceptions) ​

### Answer ### Call Agent Add-ons | Item | Pricing | |------|---------| | Knowledge Base | +$0.005/minute | | Batch Call | +$0.005/dial | | Branded Call | +$0.10/outbound call | | Advanced Denoising | +$0.005/min | | PII Removal | +$0.01/min | [(1) ]() ### Chat Agent Add-ons | Item | Pricing | |------|---------| | SMS | $0.01/Msg | ### Monthly Subscription Items | Item | Pricing | Note | |------|---------|------| | Retell Phone Numbers | $2.00/month | No charge for custom phone numbers | | Retell SMS | $20.00/month | No charge for custom telephony SMS | | Concurrency (Active Calls) | $8.00/Concurrency/month | Free for first 20 | | Knowledge Base | $8.00/Knowledge Base/month | Free for first 10 | | Verified Phone Number | $100.00/Phone number/month | — | These are additional costs on top of the base per-minute pricing for voice/chat agents.

​ To learn more, see the sources I considered: [[1] AI Phone Agent Pricing | Retell AI](https://www.retellai.com/pricing) ​

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

### Answer ### LLM Token Surcharge (Add-on Cost) The LLM Token Surcharge is a billing adjustment that applies when your agent uses more than 3,500 LLM tokens in prompts. [(1) ]() What counts toward the token calculation: - Global prompt - Functions (tool descriptions) - State/node prompt - Transcript between agent and user - Tool call history and results How the surcharge is calculated: - Scaling Factor = Prompt LLM Tokens ÷ 3,500 - Billed Duration = Original Duration × Scaling Factor (rounded up) 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 surcharge exists: 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. This is separate from the other add-ons (like Knowledge Base, Batch Call, Branded Call, etc.) and is specifically tied to how much LLM processing your conversations require.

​ To learn more, see the sources I considered: [[1] Exceptions to Our Per-Minute Pricing](https://docs.retellai.com/accounts/billing-exceptions) ​

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

### Answer ### Voice Engine Pricing by Provider Based on the available sources, here's what I found: | Provider | Price per Minute | |----------|------------------| | ElevenLabs | $0.07/min | | OpenAI/Deepgram | $0.08/min | | PlayHT | $0.08/min | [(1) ]() , [(2) ]() , [(3) ]() Notes: - Cartesia is available as a TTS provider, but specific per-minute pricing is not detailed in the sources I have access to [(2) ]() - MiniMax Speech is mentioned as a potential integration option, but pricing details are not specified in the available documentation [(4) ]() For the most current and complete pricing breakdown across all voice providers, I'd recommend checking the official pricing page: [AI Phone Agent Pricing]()

​ To learn more, see the sources I considered: [[1] ](https://www.retellai.com/resources/inbound-vs-outbound-callers-pricing-comparison-2025) [[2] Platform Changelogs | Retell AI](https://www.retellai.com/changelog) [[3] ](https://www.retellai.com/resources/sub-second-latency-voice-assistants-benchmarks) [[4] VOICE GENERATION ALTERNATIVE SUPPORT](https://discord.com/channels/1186424376300679209/1394267063270379522) ​

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