feature
Fast service tier for ElevenAgents LLM execution
elevenlabs.ioagent
ElevenAgents can run supported LLMs on a fast tier trading per-token price premium for higher token throughput and lower latency. Configure with service_tier parameter in agent prompt; default remains standard.
Stacks this affects
ElevenLabs ships in 5 tested stacks here.
More ElevenLabs
renameVoice Changer endpoints renamed and speech-to-speech paths deprecatedfeatureFast LLM service tier for ElevenAgentsfeatureClone strength control added for v4 Professional Voice ClonesfeatureKnowledge base crawl pattern exclusions for agent trainingfeatureClone strength parameter controls professional voice clone fidelityfeatureFast LLM service tier added for ElevenAgents