GA Millis AI

Millis AI

Low-latency voice-agent platform with a $0.02/min platform fee on top of separately priced STT, LLM and character-metered TTS; bring your own LLM endpoint at no LLM charge.

Est. per minute$0.04 - 0.09

Overview

Best for: Cost-sensitive builders who want a cheap orchestration fee and their own LLM.

At a glance

Platform $/min$0.02
All-in priceNo
Entry plan $/mo$0
Phone numbersYes
Own LLMYes
WebRTCYes
WebSocketYes
Phone / SIPYes
Self-hostNo
Open weightsNo

$0.02/min platform fee plus STT, LLM and per-character TTS; phone minutes from your own carrier. Pricing page looks stale.

Audio in

Web SDK and phone (via your Twilio/Plivo etc.)

Audio out

Same

Languages

Not verified.

Latency

Vendor markets very low latency; no verified number.

Regions

Not verified.

Compliance

Not verified.

Features

  • multi-provider plug-ins
  • custom LLM endpoint
  • telephony integrations
  • 'Choose by Millis' lowest-latency model selection

Pricing

WhatPriceUnitNotes
Platform fee$0.02per minuteOn top of LLM, TTS and STT.
STT$0.0043per minute
LLMGPT-4o ~$0.004, GPT-3.5 Turbo ~$0.0004, Llama-3 ~$0.00018per minute (estimate)Custom LLM endpoint: no Millis charge. Model list on the docs page looks dated.
TTSElevenLabs $0.10, Cartesia $0.0392, OpenAI/Deepgram $0.015, Rime $0.075per 1,000 charactersRoughly $0.0075-$0.05/min per Millis' own conversion.
How the per-minute estimate was worked out

$0.02 + $0.0043 STT + ~$0.004 LLM + $0.0075-$0.05 TTS + your carrier minutes (~$0.005-$0.014). Third-party worked example: ~$0.066/min with GPT-4o + ElevenLabs.

Free tier: Not published.

Source: docs.millis.ai

Setup

  1. Sign up and create an agent (prompt, voice, LLM) in the dashboard.
  2. Use the web SDK for browser calls or connect a Twilio/Plivo number for phone.
  3. Optionally point the agent at your own LLM endpoint.

Endpoint

Millis API

Authentication

Public key (web SDK) / private API key

Quick start javascript

// Millis agents are created in the dashboard; see docs.millis.ai for the current web SDK snippet.
// Snippet not reproduced here because the SDK surface could not be verified on 2026-10-10.

Written from the current docs. Check the vendor's SDK version before you ship.

Warnings

TTS billed per character

Cost depends on how much the agent talks; a chatty agent with ElevenLabs costs several times the headline.

Pricing page looks stale

Docs still list GPT-4 Turbo, GPT-3.5 and PlayHT; confirm current models and rates in the dashboard.

Telephony not priced

Phone minutes come from your own carrier account.

Limited public compliance info

No SOC 2/HIPAA statements were verified.

Plus 12 warnings that apply to all platforms and telephony APIs. See category warnings.

Limits

  • Concurrency not published

Models and products

NameStatusNotes
Pay as you goGA$0.02/min platform + components; no subscription tier published.

Docs and sources

Docs

Sources used

Not fully verified

Whether model/TTS list is current; concurrency; free credit; SDK snippet.

Similar platforms APIs

Spotted a wrong price or a dead link?