Model provider6 models

AssemblyAI

AssemblyAI serves 6 audio models on LLM API, all from AssemblyAI.

Models and prices

Prices when AssemblyAI serves the request.

Audio 6

Price per minute of audio or per 1K characters

Sort

Audio models on AssemblyAI and their prices on LLM API

AssemblyAI U3 RT Pro`u3-rt-pro`	Live transcription	$0.0075/ minute
AssemblyAI Universal-3.5 Pro`universal-3-5-pro`	Transcription	$0.0035/ minute
AssemblyAI Universal Streaming (Multilingual)`universal-streaming-multilingual`	Live transcription	$0.0025/ minute
AssemblyAI Universal-2`universal-2`	Transcription	$0.0025/ minute
AssemblyAI Universal Streaming (English)`universal-streaming-english`	Live transcription	$0.0025/ minute
AssemblyAI Whisper RT`whisper-rt`	Live transcription	$0.005/ minute

Send requests to AssemblyAI

Use the model ID as it is: video, audio and embedding requests take no provider prefix.

Example: AssemblyAI Universal-3.5 Pro

POST /v1/audio/transcriptionsSet LLMAPI_KEY to your LLM API key.Transcription docs

import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.llmapi.ai/v1",
    api_key=os.environ["LLMAPI_KEY"],
)

transcript = client.audio.transcriptions.create(
    model="universal-3-5-pro",
    file=open("meeting.mp3", "rb"),
)
print(transcript.text)

import fs from "node:fs";
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.llmapi.ai/v1",
  apiKey: process.env.LLMAPI_KEY,
});

const transcript = await client.audio.transcriptions.create({
  model: "universal-3-5-pro",
  file: fs.createReadStream("meeting.mp3"),
});
console.log(transcript.text);

curl https://api.llmapi.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $LLMAPI_KEY" \
  -F model="universal-3-5-pro" \
  -F file="@meeting.mp3"

Prices synced October 27, 2026.