feature

Conversation observability added with context_usage events in ElevenAgents

Realtime clients can now receive context_usage events after each agent turn, reporting the model name, prompt token count, and model context limit. Provides developers visibility into token usage and model resource utilization during agent interactions.

Stacks this affects

ElevenLabs ships in 5 tested stacks here.

Faceless YouTube
Video · Creator
$92/mo
Faceless YouTube (budget)
Video · Creator
$6/mo
TikTok character
Video · Creator
$92/mo
TikTok character (audio + text)
Video · Creator
$42/mo
UGC ad creative
Marketing · Ads
$67/mo
All ElevenLabs changes and pricing

More ElevenLabs

featurePhone keypad (DTMF) input support added to ElevenAgents conversationsreleaseElevenLabs CLI v1.0.0 released with complete API coverage and local agent managementfeatureProcedures now generally available in ElevenAgents for task-specific instructionsfeatureConversation triage ticket API added to ElevenAgents for QA and feedback