Migration guide

Moving from Bland AI to Wakili

Bland used to charge a flat $0.09/min. As of late 2025 it moved to tiered monthly plans starting at $299/mo, where your per-minute rate depends on how much you commit upfront, plus add-ons like custom voice, knowledge base lookup, and recording. Real cost lands around $0.09-$0.14/min once those stack up, and you're using Bland's own stack throughout. Wakili charges one flat $0.06/min platform fee, no monthly minimum, and you keep your own STT, LLM, and TTS providers.

Why teams switch

A monthly minimum just to get a good rate

Plans start at $299/mo. Your per-minute rate is tied to which tier you're paying for, not just usage.

Add-ons stack on top of the base rate

Custom voices, knowledge base lookups, and call recording each carry their own per-minute charge, pushing real cost to $0.09-$0.14/min.

One stack, no provider choice

Bland runs its own STT/LLM/TTS. If you want a specific model or voice vendor, you're out of luck.

Cost, side by side

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

Bland AIWakili
Entry cost$299/mo minimum + per-min rate$0 to start
Per-minute rate$0.09/min listed, $0.09-$0.14/min real$0.06/min platform fee + provider cost
Provider choiceBland's stack onlyBring your own STT/LLM/TTS
Free tierTrial credits only30 min/mo, free forever

What maps where

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

FieldBland AIWakili
Pathway / agentpathway.create()agents.create()
Prompt / tasktasksystemPrompt
Voicevoicetts
Modelmodelllm
WebhookwebhookwebhookUrl
create-agent.ts
// Same idea as your Bland 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 Bland AI agent over

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