Using Eleven Realtime v1 Max on ElevenLabs API

Implementation guide · Eleven Realtime · ElevenLabs

Serverless

ElevenLabs API exposes Eleven Realtime v1 Max through model ID eleven_realtime_v1_max. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-10-20. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at ElevenLabs API and generate an API key.
  2. 2
    Use the ElevenLabs API SDK or REST API to call eleven_realtime_v1_max — see the documentation for request format.
  3. 3
    You'll be billed $1.80/1M input, $9.00/1M output tokens. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

See ElevenLabs API documentation for integration details.

Pricing on ElevenLabs API

TypePrice (per 1M)
Input tokens$1.80
Output tokens$9.00

Capabilities

MultimodalReasoningJSON / Tool useAudio

About Eleven Realtime v1 Max

Eleven Realtime v1 Max is ElevenLabs' speech-to-speech voice agent model for complex tasks, released October 20, 2026. Like v1 Mini it combines speech recognition, turn-taking, a language model and text-to-speech in one end-to-end tuned cascaded system, but it reasons before it responds and is aimed at long instructions and multi-step tool use such as customer support and lead qualification. It supports 90+ languages and ElevenLabs reports 570 ms time to first audio.

Full model details →

Model Specs

Released2026-10-20

More Models on ElevenLabs API

Eleven Realtime v1 Mini
All models on ElevenLabs API →

Provider

ElevenLabs API

ElevenLabs

New York, New York, United States