Agents Platform

Calculate Expected Llm Usage

Changed on Oct 28, 2026

Returns a list of LLM models and the expected cost for using them based on the provided values.

post/v1/convai/llm-usage/calculate

Request

Base URL
https://api.elevenlabs.io (the document declares no server; this is the origin it was published from)
Auth
none declared
TypeScript
https://skmtc.dev/elevenlabs/apis/elevenlabs-api-documentation/docs/v1/convai/llm-usage/calculate/post.ts
A function with typed inputs. Its response is checked against the schema.

Request body

prompt_lengthinteger required

Length of the prompt in characters.

number_of_pagesinteger required

Pages of content in PDF documents or URLs in the agent's knowledge base.

rag_enabledboolean required

Whether RAG is enabled.

service_tier'standard' | 'fast'

Request-time processing tier for a model.

STANDARD: default price and throughput. FAST: pays a per-token price premium for higher throughput / lower latency. See OpenAI's fast mode: https://openai.com/api-fast-mode/

Response

Successful Response

Changes

Oct 28, 20260e2bfc751634 Revision changes
- warning
  added the new gpt-6.1-terra enum value to the // response property for the response status
Oct 22, 202661de2e1f86c1 Revision changes
- info
  added the new optional request property

Operation history (21 revisions)

Calculate Expected Llm Usage

Request

Request body

Response 200OK

Changes

Response