How to prompt Nano Banana Pro
Nano Banana Pro brings powerful new capabilities in image generation and editing. Here are the main prompt tricks you should know.
Infrastructure 333 stories
Retro Diffusion's pixel art models are now on Replicate
Generate game assets, sprites, tiles, and pixel art with Retro Diffusion's suite of carefully crafted models.
GPT 5.1, GPT 5.1-Codex, and GPT-5.1-Codex Mini are now available in Windsurf
GPT 5.1, GPT 5.1-Codex, and GPT-5.1-Codex Mini deliver a solid upgrade for agentic coding with variable thinking and improved steerability
New Bulk Data Operations: Update, Delete, and Fetch by Metadata
New Bulk Data Operations: Update, Delete, and Fetch by Metadata
Introducing SWE-1.5: Our Fast Agent Model
SWE-1.5 is our latest frontier model, delivering near-SOTA coding performance at unprecedented speed.
Day Zero Support for OpenAI Open Safety Model
Day Zero Support for OpenAI Open Safety Model
OpenAI gpt-oss-safeguard
Ollama is partnering with OpenAI and ROOST (Robust Open Online Safety Tools) to bring the latest gpt-oss-safeguard reasoning models to users for safety classification tasks. gpt-oss-safeguard…
MiniMax M2
MiniMax M2 is now available on Ollama's cloud. It's a model built for coding and agentic workflows.
NVIDIA DGX Spark performance
We ran performance tests on release day firmware and an updated Ollama version to see how Ollama performs.
The Hidden Cost of Building: Lessons from Aquant
The Hidden Cost of Building: Lessons from Aquant
Extract text from documents and images with Datalab Marker and OCR
Turn whole documents into markdown or grab line-level polygons with two new models from Datalab.
How to prompt Veo 3.1
Google's Veo 3.1 brings powerful new video generation capabilities including reference images, first/last frame control, and enhanced image-to-video. Here's everything you need to know.
GPT‑OSS Improvements: Prompt Caching & Lower Pricing
GPT‑OSS Improvements: Prompt Caching & Lower Pricing
New coding models & integrations
GLM-4.6 and Qwen3-coder-480B are available on Ollama’s cloud service with easy integrations to the tools you are familiar with. Qwen3-Coder-30B has been updated for faster, more…
NVIDIA DGX Spark
The latest NVIDIA DGX Spark is here! Ollama has partnered with NVIDIA to ensure it runs fast and efficiently out-of-the-box.
Simplifying Vector Embeddings with Pinecone Integrated Inference Capabilities
Simplifying Vector Embeddings with Pinecone Integrated Inference Capabilities
Cognition and Windsurf's Commitment to United States Government (USG) and Impact Level 6 (IL6) Deployments
Windsurf is ready to support IL6 deployments through partnership with Palantir FedStart, demonstrating Cognition's commitment to serving DoD missions across all networks and domains.
Web search
A new web search API is now available in Ollama. Ollama provides a generous free tier of web searches for individuals to use, and higher rate…
Which image editing model should I use?
Here is the ultimate comparison post on all the latest image editing models.
Introducing Remote MCP Support in Beta on GroqCloud
Introducing Remote MCP Support in Beta on GroqCloud
New model scheduling
Ollama now includes a significantly improved model scheduling system, reducing crashes due to out of memory issues, maximizing GPU utilization and performance, especially on multi-GPU systems.
Cloud models
Cloud models are now in preview, letting you run larger models with fast, datacenter-grade hardware. You can keep using your local tools while running larger models…
Cognition (Windsurf) Named a Leader in the 2025 Gartner® Magic Quadrant™ for AI Code Assistants
Cognition’s Windsurf has been named a Leader in the 2025 Gartner® Magic Quadrant™ for AI Code Assistants
Introducing our new search API
Find the best models and collections with a single API call.