Frequently asked questions
Is this free?
Yes, free to use. We pay the API costs out of the WholeTech network operating budget. We may add a paid tier in the future for power users (more queries per day, longer prompts, additional models), but the core service stays free.
Do you store my prompts?
No. Prompts and responses are forwarded to the selected providers and returned to your browser. We don't log them, store them, or share them.
Which AIs are supported?
Currently: Claude (Anthropic), GPT-4o (OpenAI), Gemini 1.5 Pro (Google), Grok 2 (xAI), Mistral Large, Perplexity Sonar, Cohere Command R+, and Llama 3.1 405B (via a hosted provider). We add new models as they're released.
Why do some models fail with "no API key"?
Some providers require an API key to be configured on our backend. If you see "no API key" for a model, it means we haven't yet enabled that provider. Email us if there's a model you want enabled urgently.
Why are different answers different?
Different models are trained differently. They have different strengths, different weaknesses, different training data, different fine-tuning approaches, and different safety policies. Comparing them is the whole point of Ask 'em AI.
How do I write a good prompt?
Read our prompt guide for the essentials. The short version: be specific, say who the answer is for, ask for the format you want, and iterate when the first answer isn't quite right.
Can I share results?
Click "Copy" on any result card to grab the text. Shareable result links are coming soon.
How do I report a bug?
Email walhus@gmail.com — we respond within 24 hours.