ElevenLabs · ElevenLabs platform · LLM

gemini-3.8-flash

Capability changeCapability change announced Sep 14, 2026

Notice

Capability change

Capability change announced Sep 14, 2026

ElevenLabs documents a capability change: “ElevenAgents Call queueing and hold audio: Added call queueing for agents at their concurrency limit.”

Hosting route
ElevenLabs platform
Affected scope
Not stated in the notice
Announced
Sep 14, 2026
First seen by ModelClock
Oct 3, 2026

What the provider published

elevenlabs.io ↗

ElevenAgents

  • Call queueing and hold audio: Added call queueing for agents at their concurrency limit. Queued callers hear hold audio and receive queue_status events until they are admitted or time out. New API methods upload or delete custom hold audio.
  • Test version metadata: Agent test results now identify the agent version they ran against and whether they included draft changes. Invocation summaries also indicate when partial resubmissions ran against different versions.
  • Model and account metadata: Agent LLM configuration now accepts gemini-3.8-flash. WhatsApp account responses identify whether the account uses the Cloud API or coexistence signup flow.

Read from the provider's text; the quote is the provider's exact lines.

Revision history

Loading…
Raw history JSON

Same model elsewhere

Each provider and hosting route sets its own dates.

gemini-3.8-flash lifecycle (ElevenLabs) · ModelClock