Releases
July 10, 2025

Claude 4 models now available through our LeMUR API

Today we're announcing that we have added Anthropic's Claude 4 model family into our API, giving you immediate access to the latest AI capabilities through the same endpoint you're already using.

Madison Boyd
Product Marketing Manager
Madison Boyd
Product Marketing Manager
Reviewed by
No items found.
No items found.
No items found.
No items found.

We're excited to announce that LeMUR now supports Claude 4 Sonnet and Claude 4 Opus, expanding our LLM framework with even more powerful reasoning capabilities at familiar pricing. This enhancement delivers significantly better analysis and more nuanced understanding to your conversation intelligence workflows.

Unlock advanced AI for your Audio Intelligence

Development teams worldwide trust LeMUR to transform their audio transcripts into actionable insights. By combining AssemblyAI’s industry-leading speech-to-text with advanced LLM reasoning, you get a unified solution that turns audio into powerful insights. This end-to-end approach eliminates the complexity of multiple providers, while delivering enterprise grade performance at scale. Plus, you automatically get access to Anthropic’s latest models without updating your existing workflow or managing additional integrations.  

What's new with Claude 4

Claude 4 Sonnet - Enhanced intelligence for everyday use

  • Delivers enhanced reasoning and improved performance for everyday tasks
  • Maintains exceptional speed and cost-effectiveness
  • Perfect for applications requiring reliable, intelligent responses across a wide range of use cases

Claude 4 Opus - The most capable model yet

  • Anthropic’s most capable model yet with superior performance
  • Excels at complex reasoning tasks, advanced creative work, and sophisticated problem-solving
  • Perfect for nuanced analysis, detailed research, and intricate multi-step workflows

Transform your audio data

Leverage these powerful models to unlock new possibilities from your audio content:

  • Conversation Intelligence: Track customer sentiment, identify pain points, and surface coaching opportunities for teams
  • AI Notetakers: Generate comprehensive meeting notes with speaker attribution, decisions made, and follow-up items
  • Sales Call Optimization: Analyze conversation patterns, identify successful tactics, and track objection handling
  • Educational Content: Convert lectures into structured learning materials with quiz questions and key concepts

Implementation made easy

Integrating Claude 4 models is seamless - simply update your final_model parameter in your existing LeMUR API calls. Claude 4 Sonnet is available in both US and EU regions, while Claude 4 Opus is currently available only in the US.

Claude 4 is naturally verbose, so we've tuned prompts for conciseness with no performance impact. If you need more detail, add "elaborate" to your context parameter to override this tuning. To learn more, and for a list of all LeMUR model options and parameters, check out our documentation.

Here's how you can start using Claude 4 Sonnet for transcript summarization:

import assemblyai as aai

aai.settings.api_key = "YOUR_API_KEY"

# Step 1: Transcribe your audio
audio_url = "https://storage.googleapis.com/aai-web-samples/5_common_sports_injuries.mp3"
transcriber = aai.Transcriber()
transcript = transcriber.transcribe(audio_url)

# Step 2: Define your analysis prompt
prompt = "Provide a brief summary of the transcript."

# Step 3: Choose Claude 4 Sonnet
result = transcript.lemur.task(
    prompt,
    final_model="anthropic/claude-sonnet-4-20250514"
)
print(result.response)

Build from basic requests and gradually explore more sophisticated prompts like "analyze the emotional tone and extract three key insights with supporting evidence from the discussion."

Browse our prompting best practices to maximize the effectiveness of your Claude 4 implementations.

Unlock enhanced performance with no markup

We're maintaining familiar pricing structures, giving you access to Claude 4 capabilities at the same great prices you're already used to. This means you get the newest, most powerful language models alongside our industry-leading speech AI capabilities without any pricing surprises.

Streamlined development experience

Using LeMUR eliminates the complexity of juggling multiple AI service providers. Your development team can focus on building features instead of managing integrations, while still accessing the most sophisticated AI models available. This unified approach accelerates your time-to-market and reduces operational overhead.

Start building today

Start building on our API and access Claude 4 family of models directly from LeMUR, no need to set anything up. View our updated LeMUR Quick Start Guide.

Try a More Powerful Speech-to-Text API

AssemblyAI delivers comprehensive Speech AI solutions including automatic transcription, speaker identification, and intelligent audio analysis. Create your free account and receive $50 in credits to explore Claude 4's capabilities.

Sign up now
Title goes here

Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.

Button Text
LeMUR