# Fast LLM service tier

By Steven Van · 2026-10-26

ElevenAgents can switch supported LLMs to a fast tier for lower latency at a higher per-token price, and the usage calculator now estimates the cost.

ElevenAgents can now run supported LLMs on a fast [service tier](<https://elevenlabs.io/docs/api-reference/llm/calculate>) that trades a per-token price premium for higher token throughput and lower latency. [ElevenLabs](<https://creatorstoolbox.com/tools/elevenlabs>) lists the default as unchanged: agents stay on the standard tier unless configured otherwise.

## Turning it on

Set service\_tier to fast in the agent's prompt configuration using the Update agent endpoint. Not every model offers the fast tier. The available\_service\_tiers field returned by List LLMs shows which tiers a given model supports.

## Estimating the cost difference

The LLM usage calculator now accepts an optional service\_tier parameter, with allowed values standard and fast, defaulting to standard. It only affects models that offer the tier. For other models, the calculator falls back to their standard price.

![ElevenLabs](<https://elevenlabs.io/android-chrome-512x512.png>)

ElevenLabs

AI audio platform for text to speech, voice cloning, and video dubbing across dozens of languages while preserving the original tone and emotion.

[View ElevenLabs →](<https://creatorstoolbox.com/tools/elevenlabs>)

Sources

[Original source](<https://elevenlabs.io/docs/changelog/2026/10/26#fast-llm-service-tier>)

[Read Fast LLM service tier on Creators Toolbox](<https://creatorstoolbox.com/blog/elevenlabs-fast-llm-service-tier>)

---
Canonical source: https://creatorstoolbox.com/blog/elevenlabs-fast-llm-service-tier