Eleven Flash / Turbo v2.5 API Pricing
Short answer
Eleven Flash / Turbo v2.5 costs Job-based hosted endpoint; runtime price varies. Last verified 2026-06-21 from replicate.com. Confidence: Auto.
Eleven Flash and Turbo v2.5 are ElevenLabs' lower-cost, ultra-low-latency models for voice agents and bulk synthesis.
TTS pricing
—
Price detailJob-based hosted endpoint; runtime price varies
Capabilities
Speech / billing spec~75ms model latency; 32 languages
Modalitytext → speech
ChannelReplicate
ProviderElevenLabs
Best for
TTSLow latencyVoice agents
API price is half the Multilingual/v3 family. Exact credit consumption can vary by plan and model.
Last checked Auto