Having fun with oh my pi, DeepSeek-V4-Flash, GPT-5.6 Luna and Antigravity CLI

DeepSeek's V4-Flash model exited preview and is now available in public beta, with benchmark scores surpassing V4-Pro-Preview and native agent support, according to a tweet from DeepSeek. The author describes a setup using the omp coding agent with DeepSeek-V4-Flash for coding, OpenAI's GPT-5.6 Luna for vision after an 80% price cut, and Google's Antigravity CLI for web search, enabled via a custom omp extension. The setup aims to combine a cheap state-of-the-art model with vision and search capabilities.

Background background I know these are a lot of buzz words, but nevertheless I wanted to share my setup so you can have some fun too Recently, I’ve been working with omp https://omp.sh/ a “new” coding agent built on top of the very extensible and minimal coding agent pi https://pi.dev/ which also powers OpenClaw https://openclaw.ai/ . Where pi is minimal, barebones and is left up to the user to customize, omp is batteries included and gives you the agentic experience you’ve come to know and love from Codex https://chatgpt.com/codex/ and Claude Code https://claude.com/product/claude-code while adding even more features on top it. With the recent announcement that DeepSeek-V4-Flash is no longer in preview, goes head to head with other state-of-the-art models while being extremely cheap, I thought I would give it a try as well. 🚀 DeepSeek-V4-Flash Official API is now LIVE in public beta — DeepSeek @deepseek ai 🔷 We’ve massively upgraded its Agent capabilities—benchmark scores are now far surpassing the V4-Pro-Preview. Check out the massive performance leap below 👇 🔷 The official V4-Flash now natively supports the… pic.twitter.com/NUzOyxza2f July 31, 2026 Adding “vision” to DeepSeek adding-vision-to-deepseek omp allows you to use your ChatGPT subscription along with a host of providers including search. So I added my DeepSeek API key, logged in via my OpenAI account to use my ChatGPT subscription and got it running. While Flash is extremely good at coding, it does not have multimodal capabilities. This means that if you give it an image and ask it to describe it, it will not be able to do so. It is strictly a text-in, text-out model. While Luna was already cheap, OpenAI slashed the pricing by 80% https://openai.com/index/advancing-the-price-performance-frontier-with-gpt-5-6/ . This was a good chance to use Luna for vision, give its output to Flash and continue. This is pretty easy in omp. Just type in /models , choose the model you want to choose for vision and in the bottom nav bar, choose the vision option. That’s it. Now any time you paste an image in the chat, Luna would pass the output to DeepSeek or any non-vision model Search, search and search search-search-and-search This is where last piece of the puzzle fits in. We’re using one of, if not, the cheapest SOTA and even gave it vision. But what about the newest information out there? For a refresher, when you use any of the 1st party harnesses like Codex or Claude Code and try to query for something recent or something they don’t know, they perform a web search. This is not the case when you use your subscription in another harness at least not that I’m aware of . The alternative then is to use one of the search providers like Exa, Perplexity, etc. I was not interested in that. Antigravity CLI https://antigravity.google/product/antigravity-cli to the rescue. Since Google is excellent at search, I thought why not use Antigravity CLI or agy to search and use its output to drive whatever LLM I’m using? The reason you cannot simply log in via Google into omp is because it is against their ToS. So I asked DeepSeek-V4-Flash to create an omp extension to use the agy CLI whenever it wants to use web search. So right now, all the search providers are disabled and omp automatically reaches for agy for search. Here is the GitHub Gist https://gist.github.com/flashblaze/6b07cfeff124a33c952bb867855c1d5a if you want to use it. Conclusion conclusion So yeah. That’s the setup I’ve been using since the past few days. DeepSeek-V4-Flash along with GPT-5.6 Luna Max for coding and vision and agy CLI only for search. I’m also trying out herdr https://herdr.dev/ , but nothing exciting to report as of yet.