Launch faster, more capable, and more efficient voice agents using colocated open-source LLMs hosted by ElevenLabs.
We’re introducing ElevenLabs-hosted LLMs in our agents platform, enabling faster, more capable, and more efficient voice agents.
By hosting open-source models directly within our infrastructure, we deliver ultra-low latency and reduced reasoning cost, and our customers can now deploy voice agents without relying on additional providers.
With GLM 4.5 Air, ElevenLabs Agents achieve top-tier reasoning accuracy and tool-calling performance at roughly one-third the cost of alternatives.
For lighter reasoning tasks, Qwen3-30b-a3b delivers sub-150ms Time To First Sentence, enabling fluid, natural dialogue experiences.
.webp&w=3840&q=95)
Our hosted LLMs operate alongside proprietary Speech to Text, Text to Speech, and turn-taking models within a single environment. This unified architecture reduces latency, improves reliability, and enhances data security.
ElevenLabs-hosted LLMs are now available in Agents Platform.
Learn more about our LLM offering in our docs.
Säkerställ tillförlitlighet och efterlevnad med ElevenLabs Agents Testing. Kör strukturerade simuleringar för verktygsanrop, mänskliga överföringar, arbetsflöden och skyddsräcken. Integrera i CI/CD och leverera agenter med självförtroende.
Ensure reliability and compliance with ElevenLabs Agents Testing. Run structured simulations for tool calls, human transfers, workflows, and guardrails. Integrate into CI/CD and ship agents with confidence.
Drivs av ElevenLabs Agenter
