Memory Efficiency in LLMs: Study Summary
How context length, KV-cache growth, and attention choices trade memory, latency, and recall in LLMs—practical fixes for local setups.
NanoGPT Blog
Updates, guides, and insights
Showing
132 posts found for 'pricing'
Celeris 1: A Diffusion Model for Short AI Tasks
Celeris 1 uses diffusion-based text generation for short tasks. See its provider-reported speed results, benchmark caveats, NanoGPT limits, pricing, and a small API test.
Ling 3.0 Flash vs Thinking: What Changed in Our Test
We tested Ling 3.0 Flash and Ling 3.0 Flash Thinking on coding, extraction, tool use, counting, and logic. See where their results differed and what Thinking cost.
Gemini 3.6 Flash vs Gemini 3.5 Flash Lite: Which Should You Use?
Compare Gemini 3.6 Flash and Gemini 3.5 Flash Lite on benchmarks, speed, pricing, context, coding, research, and high-volume work.
Shipped in June: Private Mode, OAuth, GLM 5.2, Media Tools, and More
A complete roundup of what NanoGPT shipped in June 2026, including Private Mode improvements, Sign in with NanoGPT, Batch API expansion, new models, media tools, payment updates, privacy controls, and community projects.
Sofya is now on NanoGPT: search, fetch, extract, and deep research
Sofya is now available on NanoGPT as a web search provider and as the Sofya Research model, bringing page-content search, URL fetching, AI extraction, and multi-source research into one workflow.
Fluent + NanoGPT: a native Mac AI assistant with built-in NanoGPT support
Fluent, the native macOS AI assistant, now ships with a built-in NanoGPT integration, a 10% discount on all text models, and free NanoGPT credit with new Fluent purchases.
NanoGPT vs OpenRouter: Same Models, No Deposit Fee
NanoGPT and OpenRouter both offer one API for hundreds of AI models at provider list prices. The difference is what happens to your money: OpenRouter takes ~5.5% when you buy credits, NanoGPT credits deposits in full. A detailed comparison.
Shipped in May: Private Mode, Batch API, Data Tools, and More
A complete roundup of what NanoGPT shipped in May 2026, including Private Mode, PII redaction, Batch API, Data API, image templates, model comparisons, new media models, payment options, and reliability improvements.
Browser-Local AI on NanoGPT
NanoGPT can now run a small local Qwen model directly in supported browsers, powering private on-device chat helpers like titles, quick replies, memory analysis, and local Auto model routing.