Skip to main content

Basic models

These models are available in BrowseWiz out-of-the-box with free plan (limited).

Gemini 2.0 Flash​

Gemini 2.0 Flash's incredible 1 million–token context window is perfect for writers who need to juggle extensive research, outlines, and drafts simultaneously. Its multimodal capabilities also enable integration of visual and textual ideas—ideal for brainstorming blog posts, multimedia articles, or creative campaigns.

ChatGPT 4o mini​

This lean, cost-efficient variant is designed to deliver crisp, engaging conversational outputs—great for drafting social media posts, short stories, or quick content ideas on a tight deadline. Its long context window ensures that your narrative remains consistent across complex projects while keeping production costs in check.

DeepSeek R1 Distill Qwen 32B​

DeepSeek-R1 is an open-source AI model developed by Chinese AI startup DeepSeek, which achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks at a fraction of the o1 costs. DeepSeek R1 Distill Qwen 32B model is a relatively small open-source LLM - Qwen 32B - fined-tuned with DeepSeek R1 outputs for better performance on series of benchmarks. For more information see HuggingFace model card.

Claude 3.5 Haiku​

Claude 3.5 Haiku is Anthropic's most lightweight and efficient AI assistant, designed for rapid responses and seamless integration where speed is essential. It delivers impressive language capabilities while prioritizing quick response time and cost efficiency. Haiku excels at straightforward tasks like content moderation, chat assistance, and concise information retrieval. It's best used for applications requiring rapid AI responses, simple customer service interactions, and situations where processing efficiency matters more than handling complex reasoning tasks. Ideal for mobile applications, high-volume workflows, or when you need quick, responsive AI assistance without the computational demands of larger models.