Manage chat models

Learn how to manage which AI models are available in your prompt editor.

GPT-5: The best model for coding and agentic tasks across domains with reasoning capabilities
GPT-5 mini: A faster, cost-efficient version of GPT-5 for well-defined tasks with reasoning capabilities
GPT-5 nano: Fastest, most cost-efficient version of GPT-5 for summarization and classification tasks
GPT-4.1: Fast, highly intelligent model with largest context window. Our flagship model for complex tasks
GPT-4.1 mini: Balanced for intelligence, speed, and cost that makes it an attractive model for many use cases
GPT-4.1 nano: Fastest, most cost-effective GPT-4.1 model with 1M+ context window and multimodal capabilities
o1-pro: Version of o1 with more compute for better responses with complex reasoning
o1: Previous full o-series reasoning model with reinforcement learning to think before answering
GPT-4o: Fast, intelligent, flexible GPT model with text and image inputs and text outputs
GPT-4o mini: Fast, affordable small model for focused tasks with 128K context window
GPT-4 Turbo: Next generation of GPT-4, designed to be cheaper and better version
GPT-4: An older high-intelligence GPT model
GPT-3.5 Turbo: Legacy GPT model for cheaper chat and non-chat tasks (deprecated)

Claude Opus 4.1: Anthropic’s most capable and intelligent model yet with superior reasoning capabilities
Claude Opus 4: Anthropic’s most advanced model for complex reasoning and analysis
Claude Sonnet 4: Balanced performance and cost for a wide range of tasks
Claude Sonnet 3.7: Stable Sonnet version, efficient for most use cases
Claude Sonnet 3.5: Cost-effective choice for general tasks
Claude Haiku 3.5: Fast and economical, ideal for lightweight tasks

Gemini 2.5 Pro: Google’s most capable model with reasoning, coding, and multimodal capabilities
Gemini 2.5 Flash: Efficient and cost-effective model with 1M token context window and multimodal capabilities
Gemini 2.5 Flash-Lite: Text-only version of Gemini 2.5 Flash optimized for speed and cost-effectiveness
Gemini 2.0 Flash: Balanced performance model with multimodal capabilities and 128K context window
Gemini 2.0 Flash-Lite: Text-only version of Gemini 2.0 Flash optimized for speed and cost-effectiveness

Grok 4: Next-generation Grok model with strong reasoning and coding with enterprise data handling
Grok Code Fast 1: Speedy, economical reasoning model specialized for agentic coding with 256k context
Grok 3: Excels at enterprise tasks like data extraction, coding, and summarization with strong domain knowledge
Grok 3 Fast: Fast Grok 3 variant for coding, extraction, summarization with deep domain knowledge
Grok 3 Mini: A lightweight model that thinks before responding, fast and great for logic-based tasks

Prompty provides flexible model management capabilities that allow you to customize which models are available in your workflow.

You can control which models appear in the prompt editor by enabling or disabling specific models:

Enabled Models: These models will appear in the model selection dropdown in the prompt editor
Disabled Models: These models will be hidden from the prompt editor interface but remain available for configuration

Navigate to the model management section on Siderbar
Find the model you want to configure
Toggle the enable/disable switch
Changes are applied immediately - disabled models will no longer appear in the prompt editor