Prompt Chains

Multi-step prompt sequences for complex AI workflows.

476 tools found

Getting the Most out of GPT-5.4 for Vision and Document Understanding

GPT-5.4 is a major step forward for real-world multimodal workloads.

Agents

Test and evaluate ElevenLabs voice AI agents with multi-turn conversations.

Models

You can run this example with:

Compare Claude Vs Gpt

You can run this example with:

Compare Gpt 4O Vs 4O Mini

You can run this example with:

Compare Gpt 5 Vs Gpt 5 Mini Mmlu

You can run this example with:

Compare Gpt Temperature

You can run this example with:

Compare Gpt Vs Claude Vs Gemini

This example compares OpenAI's GPT-5.2, Anthropic's Claude Sonnet 4.6, and Google's Gemini on riddle-solving tasks with cost, latency, and quality assertions.

Compare Llama Vs Gpt

You can run this example with:

Compare Mistral Vs Llama

You can run this example with:

Compare Open Source Models

This example compares Mistral, Mixtral, Llama, and Gemma on various tasks with factual assertions using OpenRouter.

Compare Openai Models

This example compares OpenAI's `gpt-5.4` with `gpt-5.3-chat-latest` across various riddles and reasoning tasks.