LLM Reference

Eleven v3 on ElevenLabs API

ElevenLabs Text-to-Speech · ElevenLabs

Serverless

Last refreshed 2026-06-07. Next refresh: weekly.

Why use Eleven v3 on ElevenLabs API?

ElevenLabs API offers Eleven v3 with pay-as-you-go pricing at $100.00/1M input tokens. ElevenLabs' API provides hosted text-to-speech, speech-to-speech, dubbing, and voice models for creative production and realtime conversational applications.

Input / 1M
$100.00
Output / 1M
-
Cache
Not sourced
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: eleven_v3
Model ID
eleven_v3

Request example

Curated snippets for this provider are not sourced yet. Use ElevenLabs API documentation with model ID eleven_v3.

Gotchas

  • Use provider model ID "eleven_v3", not the LLMReference slug "eleven-v3".

Pricing

TypePrice (per 1M)
Input tokens$100.00

Capabilities

Audio

About Eleven v3

Eleven v3 is ElevenLabs' most expressive text-to-speech model, generally available February 2, 2026 (API preview from June 8, 2025). Supports dramatic delivery, emotional nuance, multi-speaker dialogue, and 70+ languages. Maximum input: 5,000 characters per request. Preferred over Multilingual v2 with 72% preference rate in testing. Priced at $0.10/1K characters ($100/1M chars). API ID: eleven_v3.

FAQ

What API model ID do I use for Eleven v3 on ElevenLabs API?

Use the model ID eleven_v3 when calling ElevenLabs API's API.

Who created Eleven v3?

Eleven v3 was created by ElevenLabs as part of the ElevenLabs Text-to-Speech model family.

Is Eleven v3 open source?

Eleven v3 is not open source; the seed data lists it as proprietary.

Get Started

Model Specs

Released2026-02-02
Architectureneural

Related Models on ElevenLabs API