In addition to text models, you can access image models like Imagen 4 and FLUX Kontext, video models including Veo 3 and Hailuo 02, and audio models like ElevenLabs and Lyria. This can be valuable for media generation workflows that chain models together across modalities. (4/7)
APPS
-
Poe Launches Developer API with Multi-Modal Model Access
By
–
Introducing the Poe API for developers, with three important features: 1) Access to all models and bots on Poe across all modalities
2) A standard OpenAI-compatible chat completions interface
3) The ability to purchase points beyond subscription limits -
Poe API Unifies Access to Multiple AI Models and Custom Bots
By
–
With one API key, you get access to all models on Poe, including ones from OpenAI, Anthropic, Google, xAI, and more – plus millions of custom bots created by our community. This allows you to switch between o3, Grok 4, or any other model with a single parameter change. (2/7)
-
MagicPathAI Project Available for Remixing
By
–
Link to the @MagicPathAI project if you want to remix it
-
Mistral OCR App Converts Images PDFs to Markdown
By
–
I needed an app to export markdown from images and PDFs, so I built one using the best model on the market: Mistral OCR.
— Pietro Schirano (@skirano) 31 juillet 2025
It can convert images, PDFs, and even extract tables and images, keeping them contextually within the markdown.
All you need is a @MistralAI API. pic.twitter.com/cUcraPsD56I needed an app to export markdown from images and PDFs, so I built one using the best model on the market: Mistral OCR. It can convert images, PDFs, and even extract tables and images, keeping them contextually within the markdown. All you need is a @MistralAI API.
-
AI Reshapes SEO: Scaling Content Creation Without Burnout
By
–
Totally agree! AI is reshaping SEO from the ground up. It’s a game-changer for content creators looking to scale without burning out.
-
Figma enables solo designers to create beautiful AI tools
By
–
Most people wouldn't guess this, but not boring doesn't actually employ a team of designers.
— Packy McCormick (@packyM) 31 juillet 2025
It's only possible for me to make beautiful things like this because of Figma.
Thanks and congrats @zoink & team. https://t.co/ULs5raP8bz pic.twitter.com/fdQo2WZ4jEMost people wouldn't guess this, but not boring doesn't actually employ a team of designers. It's only possible for me to make beautiful things like this because of Figma. Thanks and congrats @zoink & team.
-
Creative AI Tools Company Hiring for Future Development
By
–
if you're interested in building the future of creative tools with us, we're hiring!
-
Krea-1 Open-Source Image Model Released with SOTA Realism
By
–
today, we're releasing an open version of Krea-1.
— KREA AI (@krea_ai) 31 juillet 2025
FLUX Krea is a new SOTA open-source image model with incredible realism and aesthetics.
try it for free 👇 pic.twitter.com/OpqLFkygwTtoday, we're releasing an open version of Krea-1. FLUX Krea is a new SOTA open-source image model with incredible realism and aesthetics. try it for free
-
AI Powers Business Applications: Manuals, Retail Analytics, Risk Detection
By
–
It can power impactful business applications such as interpreting product manuals, retail analytics, or analyzing real-world industrial scenes for risk detection.