Wakili

Migration guide

Moving from Retell AI to Wakili

Retell's Pay As You Go tier lists $0.07/min, but stack an LLM and telephony on top and the floor moves to about $0.088/min. Real production setups typically run $0.13-$0.31/min. Scale past that and the next step is Enterprise, which starts at $8,000/mo. Wakili has one tier between free and custom: a flat $0.06/min platform fee, no jump to a five-figure monthly minimum.

Why teams switch

The listed rate isn't the floor

$0.07/min covers voice infrastructure and standard TTS. Add an LLM and telephony and the real minimum is closer to $0.088/min before you've made a single call.

A steep cliff to Enterprise

Need SLAs or more concurrency? The next tier starts at $8,000/mo. There's no path between pay-as-you-go and that.

Production cost is 2-4x the sticker

$0.13-$0.31/min all-in depending on which LLM and voice models you stack, well past what the homepage number implies.

Cost, side by side

Figures reflect publicly listed rates and typical stacked costs at the time of writing. Confirm current numbers before you commit.

Retell AIWakili
Base rate$0.07/min, ~$0.088/min with LLM + telephony$0.06/min platform fee
Realistic all-in cost$0.13-$0.31/min$0.11-$0.13/min
Next tier upEnterprise from $8,000/moCustom Enterprise, scoped to what you need
Free credits$10 (about 60-90 minutes)30 min/mo, free forever

What maps where

Most Retell AI agents map onto Wakili one field at a time. Nothing about your prompt, voice, or model choice has to change.

FieldRetell AIWakili
Agentagent.create()agents.create()
System promptllm.general_promptsystemPrompt
Voiceagent.voice_idtts
Language / STTagent.languagestt
Webhookagent.webhook_urlwebhookUrl
create-agent.ts
// Same idea as your Retell AI agent config
const agent = await wakili.agents.create({
  stt: "deepgram:nova-3",
  llm: "anthropic:claude-sonnet",
  tts: "elevenlabs:rachel",
  systemPrompt: "Paste your existing prompt here…",
  webhookUrl: "https://api.acme.com/wakili",
});

How the switch works

  1. 0101

    Export your config

    Pull your agent's system prompt, voice ID, LLM model, and webhook URL.

  2. 0202

    Map fields into Wakili

    Same STT, LLM, and TTS choices if you want them. Nothing forces a swap.

  3. 0303

    Run both in parallel

    Point a test number at Wakili and compare transcripts side by side.

  4. 0404

    Cut over your number

    Swap the webhook, retire the old plan. Most teams do this in an afternoon.

Ready when you are

Bring your Retell AI agent over

Keep your prompt, your voice, your model. Just change where the bill comes from.

Start BuildingTalk to Us