gpt-4o-mini
GPT-4o Mini is a compact and cost-effective version of OpenAI's GPT-4o model. It is designed to offer a balance between performance and affordability, making advanced AI more accessible for various applications.
Notable features include support for text and vision inputs, a 128k context window, and up to 16k output tokens per request. It excels in verbal reasoning and is ideal for cost-sensitive, high-volume tasks.
Learn more on this model from Open AI or ask Yaddle about gpt-4o-mini.
Open AI
GPT-OSS-20B
GPT-OSS-20B is one of OpenAI's open-weight language models, released as part of their commitment to open AI development. This 20 billion parameter model offers strong performance across a wide range of tasks while being fully accessible and transparent for developers and researchers.
Notable features include multilingual capabilities, strong reasoning abilities, and efficient inference. It's designed for developers and researchers who want to build upon and customize AI models for their specific use cases, with full access to the model weights and architecture.
Learn more on this model from OpenAI or ask Yaddle about GPT-OSS-20B.
OpenAI
Claude 3 Haiku
Claude 3 Haiku is a cutting-edge AI developed by Anthropic, designed for fast, cost-effective responses. It excels at organizational tasks and offers strong performance for a wide range of applications, especially where speed and efficiency are critical.
Learn more on this model from Anthropic or ask Yaddle about Claude-3-Haiku.
Anthropic
Llama3-8B
Llama3-8B is a versatile model from Meta, trained on a wide range of tasks including mathematics, history, and computer science. It is known for its multitask accuracy, flexibility, and deep understanding across domains.
Learn more on this model from Meta or ask Yaddle about llama3-8B.
Meta
Llama3-70B
Llama3-70B is a state-of-the-art large language model from Meta, known for enhanced reasoning, coding, and multilingual capabilities. It is highly ranked among top models and is ideal for complex queries and advice.
Learn more on this model from Meta or ask Yaddle about llama3-70B.
Meta
DeepSeek-R1-Distill-Llama-70B
DeepSeek R1 Distill Llama 70B is a high-performance reasoning model based on Llama-3.3, using knowledge distillation for efficiency. It achieves top accuracy on benchmarks like MATH-500 and is designed for fast, competitive language tasks.
Learn more on this model from Deepseek or ask Yaddle about this model.
Deepseek
Qwen3-32B
Qwen3-32B is a fast reasoning model from Alibaba, designed for efficiency and strong performance on a variety of language tasks. It is well-suited for users seeking a balance of speed and capability.
Learn more on this model from Alibaba or ask Yaddle about Qwen3-32B.
Alibaba
Gemini 2.0 Flash Lite
Gemini 2.0 Flash Lite is a medium, fast model from Google, designed for quick, high-quality responses. It is suitable for a wide range of general-purpose tasks and excels in speed and efficiency.
Learn more on this model from Google or ask Yaddle about Gemini 2.0 Flash Lite.
Llama-4-Scout
Llama-4-Scout is Meta's latest fast model, designed for high efficiency and strong performance across a variety of tasks. It is ideal for users who want the latest advancements in open-source language models.
Learn more on this model from Meta or ask Yaddle about Llama-4-Scout.
Meta
Kimi-K2
Kimi-K2 is a fast reasoning model from Moonshot AI, designed for efficient, high-quality language generation. It is suitable for users who need quick, reliable results for a variety of tasks.
Learn more on this model from Moonshot AI or ask Yaddle about Kimi-K2.
Moonshot AI
Choose for me
Not sure which model to use? Select "Choose for me" and Yaddle will automatically pick the best model for your question based on speed, accuracy, and current availability.