Here Are My Go-To AI Tools
My preferred LLMs, image and video models, music makers, research tools, and more.
I first published this round-up on October 17, 2024. But things in AI move fast, so I now release regular updates. Check out this archive page for snapshots of the past versions—fun for tracing how AI and my preferences evolved.
Note: Many tools (especially from Google) have limited global availability, but you can fix that using a VPN.
LATEST UPDATE: July 16, 2025 (below)
I often get asked about AI tools that I personally use.
While I regularly test and review all sorts of AI models and sites, most don’t end up a part of my routine.
Here are those that did.
🗣️ 1. Large language models
These are the chatbots and LLMs I turn to.
🎁Free:
Claude 4 Sonnet [UPDATED - replacing 3.7] for brainstorming and creative work. Claude has a “fresh” conversational feel and tends to suggest unconventional ideas. Artifacts are fantastic and now also let you build AI-powered apps. The only downside is the strict message limit for free accounts.
Gemini 2.5 Pro (via Google AI Studio) for working with big documents or files. Gemini’s massive token window and ability to natively process audio and video make it a beast for dealing with long inputs in multiple formats. It’s also my default “beta reader” when asking for draft feedback.
GPT-4o (via ChatGPT) for casual day-to-day chats. GPT-4o has improved noticeably in conversational “vibes” over the past few months. Plus, it’s hard to beat the all-in-one free ChatGPT package with web browsing, voice, (limited) image creation, and more.
💵Paid:
OpenAI o3 [NEW] for almost any heavy lifting. It’s fast becoming my default model. o3 automatically adjusts how much time it spends on a task depending on difficulty, independently calls on the right tool for the job, and automatically structures responses in helpful tables, etc.
ChatGPT Plus in general. It’s a true all-in-one solution that gives you…
Advanced Voice Mode: Lifelike real-time voice chat where you can share your screen and camera for context-aware, multimodal conversations
Advanced data analysis (“Code Interpreter”)
Deep Research: One of the best research agents on the market
Reasoning models (including the above o3) for advanced reasoning and coding tasks
Canvas: right-side space for working on code or documents
Web browsing for news and knowledge beyond its training data
Ability to create your own Custom GPTs for different purposes
For $20 / month, this set of features is a steal.
🖼️ 2. AI images
Here are my favorite image models.
🎁Free:
GPT-4o native image generation [moved up to “Free”]: A true paradigm shift in AI images. Understands context, can render entire pages of text inside an image, and more. Requires ChatGPT Plus, but you can also run it for free on copilot.microsoft.com.
Imagen 4 [UPDATED - replacing Imagen 3] for your everyday image needs. It’s close to GPT-4o on benchmarks, creates images faster, and you can run it for free at gemini.google.com and in products like Image FX and Whisk.
💵Paid:
Midjourney V7: Midjourney has been my go-to tool for years, and I’ve written dozens of posts about it. GPT-4o native image generation is now better at text rendering, scene complexity, and prompt following. But Midjourney is still great for artistic style exploration, creating a personalized aesthetic, and generating realistic photographic images.
📽️ 3. AI video
The AI video space is making the biggest leaps lately. Here’s my take on AI video models based on thorough tests of both text-to-video and image-to-video.
🎁Free:
Kling 2.1 Master [UPDATED - replacing 1.6] for image-to-video (Kling ended up at “God tier” in my most recent image-to-video test. Kling often upgrades its platform, introduces cool features, and gives free credits.
Wan 2.1 is still the best open-source video model and was Tier #1 in my image-to-video test. If you have the know-how and the hardware, you can even run it locally. If not, wan.video gives you free daily credits.
💵 Paid:
Krea is excellent for sampling the best options in a single place. It pulls together many third-party video models (plus image and 3D ones). Krea also has a fun real-time image editor for iterative experimentation.
Runway Gen-4 is a solid recent model (although Gen-4 Turbo is less impressive). More importantly, Runway offers a proper all-in-one creator platform with dozens of robust tools for professional filmmakers.
Veo 3 (Google) [UPDATED - replacing Veo 2] - simply put, Veo 3 is the best all-in-one video model that generates truly lifelike videos with native audio effects and speech.1
🎵 4. AI music
This space is surprisingly steady. I rarely use AI music tools, but when I do…
🎁Free:
The three are largely interchangeable for casual users, with similar features, interfaces, and output quality.2 All give you a generous amount of free credits, so take them for a spin to see which one you prefer. Today, Suno likely has an edge thanks to its recent feature releases and better audio quality.
💵 Paid:
Any of the above: Once you’ve picked your favorite, you can always upgrade for additional features.
🔬 5. Research
🎁Free:
NotebookLM remains an easy recommendation! I’ve been a fan since March 2024, and NotebookLM only keeps getting better. Since my last update, NotebookLM introduced interactive mind maps, native source discovery, and multilingual audio podcasts based on your uploads.
Learn About is another Google product that complements NotebookLM nicely. While NotebookLM is grounded in your preselected sources and synthesizes info across them, Learn About can browse the web and is built for open-ended exploration of any topic.
Perplexity I don’t use Perplexity too often, but its “Pro” search is a good midway point between simple web browsing and the time-intensive “Deep Research” tools.
💵 Paid:
Deep Research from either Google (Gemini) or OpenAI. “Deep Research” features are great when you need a thorough deep dive into a topic that intelligently parses dozens of sources.
📈 6. Productivity
🎁Free:
Google AI Studio [NEW]: It’s still crazy to me that Google makes so much available for free via Google AI Studio. You can access its latest frontier models (Gemini 2.5 Pro), image generation, voice generation, coding tools, and live calls with screen or camera sharing. It’s a great way to sample most of what Google has to offer at no charge.
Napkin automatically turns walls of text into catchy visuals like diagrams, infographics, etc. For design-challenged people like myself, it’s a superb way to illustrate concepts with minimal effort.
💵 Paid:
Genspark Super Agent: A robust agent that can orchestrate dozens of tools to complete complex, multi-step tasks. You get 200 free monthly credits to try it, but you’ll likely need the paid plan for bigger tasks.
🫵 Over to you…
What AI tools do you use the most? What would you add to the above list?
Leave a comment or drop me an email at whytryai@substack.com.
Thanks for reading!
If you enjoy my writing, here’s how you can help:
❤️Like this post if it resonates with you.
🔗Share it to help others discover this newsletter.
🗩 Comment below—I read and respond to all of them.
Why Try AI is a passion project, and I’m grateful to everyone who helps keep it going. If you’d like to support my work and unlock cool perks, consider a paid subscription:
More likely than not, you’ve already seen Veo 3 clips by now, from the vlogging Yeti to ASMR glass fruit cutting to dozens of other trends.
Even though I picked a winner some time ago in the Battle of the Bands.
I always appreciate these personal approaches and descriptions. It's good to know that you've been around the block several times, and you've settled on these particular tools. I myself have centered most of my research around ChatGPT Plus, and as a bonus, I get really good image generation. I use Gemini (or Google's Experimental Model) to read and "grade" my work - ChatGPT is still better at reviewing writing, but Gemini will notice some errors ChatGPT will not.
Perplexity has become a favorite too. It's amazing for quick research, probably better than the other 2 I mentioned. I've used the paid versions of GPT and Gemini, but only the free Perplexity model, and it is nearly as good as the paid models for my needs.
I've started using Napkin ai for ai based dynamic graphic images. It's kind of hard to explain, but it's my new go to for creating dynamic colourful images using prompts. Amazing