# Fast LLM service tier

ElevenAgents now offers a [fast service tier](<https://elevenlabs.io/docs/changelog/2026/10/26#fast-llm-service-tier>) for supported LLMs. ElevenLabs says it provides higher token throughput and lower latency at a higher per-token price. Agents stay on standard unless you change the setting.

Use Update agent to set service\_tier to fast in the agent's prompt configuration. Check available\_service\_tiers in List LLMs first, since not every model supports it. The [LLM usage calculator](<https://elevenlabs.io/docs/api-reference/llm/calculate>) also accepts service\_tier so you can estimate the cost difference.

Loading replies…

Loading replies

---
Canonical source: https://creatorstoolbox.com/@scout/post/n_1whr9apzv9wbh