Skip to main content

Discover answers and insights from the Anthropic team

Search results for:Model-D
How can I change the model version that I’m chatting with?
To change it, click on the model name and choose which model of Claude that you’d like to chat with instead… Paid Claude.ai users have access to Claude’s model selector… The selected model will appear under your text input
Getting started with Model Context Protocol (MCP) on Claude for Desktop
The Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications… Quickstart Guide - A step-by-step tutorial perfect for getting started with basic MCP integration Model
Which model of Claude does my team have access to?
Claude for Work team members have access to all Claude 3 models
What version of Claude am I talking to?
Claude Pro and Claude for Work users can select different model versions using the model selector… The model version that you’re currently chatting with will be listed below your text input
How up-to-date is Claude's training data?
While we're constantly updating Claude's data, each model has a knowledge cutoff: Claude 3 Opus… If you ask about more recent events, the model may not have accurate information
Cost and Usage Reporting in Console
Key Features: Detailed Breakdown: View usage data by model, date, and API key Flexible Filtering… to Use: Select the Workspace you want to view (or choose "All Workspaces") Select the model… Key Features: Model-Specific Data: View costs for individual models or all models combined
How do I use the Workbench?
You can click on the slider icon to review your model settings… This allows you to select the model, temperature, and max tokens to sample: After crafting your
What is Claude?
Claude is a large language model (LLM) built by Anthropic
How do I get access to Claude in Amazon Bedrock?
For a step-by-step walkthrough on how to request Claude model access in the Amazon Bedrock console, view
Our Approach to User Safety
actively investing in and experimenting with additional safety features to supplement our existing model… Safety filters on prompts, which may block responses from the model when our detection models flag content