Compare realtime APIs
Pick up to four APIs from any category and see them side by side.
| Twilio Media Streams Twilio | Millis AI Millis AI | LiveKit Agents + LiveKit Cloud LiveKit | |
|---|---|---|---|
| Category | Platforms | Platforms | Platforms |
| Status | GA | GA | GA |
| Est. per minute | $0.035 - 0.12 | $0.04 - 0.09 | $0.03 - 0.08 |
| How that was worked out | $0.0044 stream + $0.0085-$0.014 voice + your STT/LLM/TTS ($0.02-$0.10 depending on providers; speech-to-speech realtime models can exceed this). | $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. | LiveKit's own calculator default is $0.0479/min (agent session $0.01 + telephony $0.01 + STT $0.0075 + LLM $0.0014 + TTS $0.009 + observability $0.01). Low end: WebRTC only, cheap STT/TTS, small LLM. High end: phone calls, premium TTS (Cartesia/ElevenLabs class) and a larger LLM. Speech-to-speech realtime models cost much more and are priced in the model segment. |
| Pricing model | per-minute | per-minute | usage |
| Free tier | Twilio trial credit only. | Not published. | Build plan: 1,000 agent session minutes/month, $2.50 inference credit, 1 US number with 50 inbound minutes, no credit card. |
| Connects by | PSTN, SIP, WebSocket | WebRTC, WebSocket, PSTN, SIP | WebRTC, SIP, PSTN |
| Audio in | audio/x-mulaw 8000 Hz mono, base64 in JSON 'media' events | Web SDK and phone (via your Twilio/Plivo etc.) | Opus over WebRTC; SIP/PSTN calls bridged in |
| Audio out | Same format sent back in 'media' events; 'clear' to flush on barge-in, 'mark' to track playback | Same | Opus over WebRTC; telephony codecs on SIP legs |
| Languages | Whatever your models support. | Not verified. | Depends on the chosen STT/TTS/LLM; LiveKit Inference restricts to EU-hosted models for EU agents. |
| Latency (vendor claim) | Not applicable (transport); your pipeline determines latency. | Vendor markets very low latency; no verified number. | No single vendor number verified; depends on models and region. |
| Key limits |
|
|
|
| High-severity warnings |
|
|
|
| Compliance | Twilio offers BAAs for HIPAA-eligible products; not re-verified for Media Streams here. | Not verified. | SOC 2 Type II (Security, Availability, Confidentiality) and GDPR per LiveKit security page; HIPAA/BAA not verified. |
| Self-hostable | No | No | Yes |
| Last checked | 2026-10-10 | 2026-10-10 | 2026-10-10 |
| Key numbers and features | |||
| Platform $/min | $0.0044 | $0.02 | $0.01 |
| All-in price | No | No | No |
| Entry plan $/mo | $0 | $0 | $50 |
| Free tier | Yes | - | Yes |
| Free credit $ | - | - | $2.5 |
| Phone numbers | Yes | Yes | Yes |
| Own LLM | Yes | Yes | Yes |
| Own keys | Yes | - | Yes |
| No-code | - | - | - |
| Recording | Yes | - | Yes |
| Noise cancel | - | - | Yes |
| Smart turns | No | - | Yes |
| Latency ms | - | - | - |
| Languages | - | - | - |
| Max session min | - | - | - |
| Concurrency | - | - | 20 |
| WebRTC | - | Yes | Yes |
| WebSocket | Yes | Yes | - |
| Phone / SIP | Yes | Yes | Yes |
| HIPAA | - | - | - |
| SOC 2 | - | - | Yes |
| EU data | - | - | Yes |
| Self-host | No | No | Yes |
| Open weights | No | No | Yes |
| High warnings | 0 | 0 | 0 |