Your question. Your choice.

Find your model

Explore the models available on Yaddle. Pick one in the search box, or let Yaddle choose for you.

Start a search

Model catalog

OpenAI

gpt-5-nano

GPT-5 Nano is OpenAI's fastest and most cost-efficient GPT-5 model. It is the best fit on Yaddle for quick answers, follow-up question generation, summarization, classification, and other cost-sensitive high-volume tasks.

Notable features include text input and output, image input support, a 400k context window, up to 128k output tokens, streaming, function calling, structured outputs, and configurable reasoning effort.

Learn more on this model from OpenAI or ask Yaddle about gpt-5-nano.

OpenAI

GPT-OSS-120B

GPT-OSS-120B is OpenAI's flagship open-weight reasoning model. It is built for higher-capability agentic tasks, with stronger multi-step reasoning, coding, and tool-use performance than smaller open models while still running quickly on Groq.

Notable features include a 131k context window, up to 65,536 output tokens, and strong benchmark performance for coding and advanced research workflows. It is a better fit when answer quality matters more than absolute lowest cost or latency.

Learn more on this model on Groq or ask Yaddle about GPT-OSS-120B.

Z.ai

GLM-5.3 Flash

GLM-5.3 Flash is an affordable reasoning model from Z.ai for questions, analysis, and coding. It is another option for everyday answers on Yaddle.

Learn more about GLM-5.3 Flash or ask Yaddle about GLM-5.3 Flash.

Alibaba

Qwen3.8-27B

Qwen3.8-27B is a preview reasoning model from Alibaba, available through Groq for fast inference on coding, analysis, and general language tasks. It is useful for evaluating newer Qwen behavior while keeping Groq-compatible routing.

Learn more on this model on Groq or ask Yaddle about Qwen3.8-27B.

Google

Gemini 2.5 Flash Lite

Gemini 2.5 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 2.5 Flash Lite.

Yaddle

Choose for me

Select "Choose for me" to use Yaddle’s default model, currently GPT-5 Nano.