Tag

LLM

14 tools 27 AI tools 24 articles

Advertisement

Tools14

RT-AI-038 AI & LLM Glossary

A searchable glossary of 50+ AI and LLM terms in plain English

RT-AI-004 Context Window Visualizer

See what % of each model's context window your text fills

RT-AI-008 Embedding Cost Calculator

Price embedding a corpus for RAG: documents × tokens × model rate

RT-AI-002 LLM Cost Calculator

Estimate GPT, Claude & Gemini API costs from token counts and volume

RT-AI-003 LLM Price Comparison

Compare one request's cost across GPT, Claude, Gemini & Mistral, ranked

RT-AI-027 llms.txt Generator

Build a spec-compliant /llms.txt to help AI models understand your site

RT-AI-006 Monthly LLM Spend Projector

Forecast monthly & annual API spend from requests per day

RT-AI-037 Sampling Parameters Cheat Sheet

Searchable reference of LLM sampling parameters and their effects

RT-AI-034 Stop Sequence Tester

Preview where an LLM stop sequence cuts generated text

RT-AI-035 Temperature & Top-p Explainer

See how temperature, top-p and top-k reshape token probabilities

RT-AI-007 Text Chunker for RAG & Embeddings

Split text into token-sized chunks with overlap for RAG

RT-AI-001 Token Counter

Count exact GPT tokens (tiktoken) plus words, characters & LLM estimates

RT-AI-036 Tokenization Visualizer

See exactly how text splits into GPT tokens, colour-coded

RT-AI-005 Tokens ↔ Words ↔ Characters Converter

Convert between tokens, words and characters for LLM prompts

AI tools27

4Paradigm SageGPT 式说

Private-deployment enterprise Copilot from 4Paradigm, now Phancy Group

AI Directory →

Jamba models, an agent-cost gateway and post-training from Tel Aviv

AI Directory →

Amazônia IA (WideLabs)

WideLabs' free Brazilian-Portuguese AI chat; the API is still waitlisted

AI Directory →

The 2023 task-loop agent, now a family of open-source experiments

AI Directory →

Government-funded Indic language and speech models led by IIT Bombay

AI Directory →

BigScience's 2022 open multilingual model, still downloadable, now a research artefact

AI Directory →

One tidy client for every LLM, with your own keys or hosted

AI Directory →

OpenAI's assistant, now on GPT-6, with Work agents and Codex built in

AI Directory →

Anthropic's assistant and models for writing, analysis and agentic coding

AI Directory →

Hangzhou lab shipping MIT-licensed V4 models and a very cheap API

AI Directory →

Google's AI assistant, now with Gemini 4 Argon on paid plans

AI Directory →

Nomic's free offline LLM app, no longer actively developed

AI Directory →

SpaceXSI's chatbot (formerly xAI), with live X data and Grok 4.7

AI Directory →

NAVER's Korean-first LLM family, sold through CLOVA Studio

AI Directory →

Open-source offline ChatGPT alternative from Singapore's Menlo Research

AI Directory →

Langboat 澜舟科技 (Mengzi)

Zhou Ming's Mengzi language models, now powering enterprise digital workers

AI Directory →

Open-source graph framework for durable, stateful AI agents

AI Directory →

Meta's downloadable LLM family, last updated with Llama 4 in April 2025

AI Directory →

Maritaca AI (Sabiá)

Sabiá language models built for Brazilian Portuguese and Brazilian data

AI Directory →

Meta's free assistant inside WhatsApp, Instagram and Facebook

AI Directory →

Microsoft Copilot

Microsoft's AI assistant across Windows, Edge, Bing and Microsoft 365

AI Directory →

Chinese ATS and HR suite selling its Moka Eva recruiting agent across APAC

AI Directory →

One API key and one credit balance for 450+ language models

AI Directory →

PowerLaw 幂律智能

Chinese legal AI for contract review, contract management and SME legal help

AI Directory →

India's sovereign LLM, built for 22 Indian languages

AI Directory →

Xiaoduo AI 晓多科技

Customer-service AI agents for sellers on Chinese marketplaces

AI Directory →

实在Agent (Intelligence Indeed 实在智能)

A Hangzhou RPA veteran's computer-use agent, top of OSWorld's verified results

AI Directory →

Advertisement

Articles24

Hands typing on a laptop keyboard

AI & ML 8 min Do DeepSeek and Qwen need different prompts from ChatGPT "Avoid adding a system prompt" is the most-repeated rule about prompting Chinese models, and DeepSeek's own cu... MA Maya Lin 27 Sep

A developer's desk at night: two monitors filled with coloured code, two keyboards and a small desk clock reading 12:32, lit red and blue

AI & ML 8 min How many tokens is a Chinese character, and what Chinese AI companies call things Four Chinese model vendors publish the same ratio in their own documentation: a Chinese character is about 0.6... MA Maya Lin 25 Sep

Lines of code on a dark screen in blue and purple, blurred outward from the centre

AI & ML 5 min One embedding model, four different maximum lengths The most downloaded sentence-embedding model ships four config files declaring 128, 256, 512 and 512 as its ma... KE Kenji Tanaka 5 Sep

A sheer cliff face dropping straight to the sea, the land above ending in a clean vertical edge.

AI & ML 6 min One token can double your bill OpenAI charges 2x input and 1.5x output on the full request once a prompt passes 272,000 tokens, so the 272,00... KE Kenji Tanaka 4 Sep

The exposed mechanism of an old mechanical meter on a black background, showing a numbered counter wheel, a graduated dial and brass gears.

AI & ML 6 min Two providers charge a toll for your prompt cache. One charges rent. All three major providers price a cache read at a tenth of normal input, so caching looks like the same deal e... KE Kenji Tanaka 3 Sep

A wall-mounted year planner photographed in shallow focus, columns of printed date numbers running down the sheet with several rows blocked out in yellow highlighter.

AI & ML 9 min One cloud answers with a different model instead of failing Every hosted model has a date after which it stops answering. Almost everywhere that is an error you can see i... KE Kenji Tanaka 2 Sep

A weathered blue parking meter against a yellow wall, its dial reading SIXTY MIN. TIME LIMIT above a red TIME EXPIRED flag.

AI & ML 8 min Your AI Coding Agent Charges You for Coffee Breaks A long session is cheap. An interrupted one is not. Every AI coding agent re-reads your whole conversation at... KE Kenji Tanaka 29 Aug

Close-up of a printed circuit board showing surface-mounted components and their designators, illustrating a report on Nvidia licensing Poolside's model-building system.

Business 8 min Nvidia Paid $7bn For Poolside's Technology And Staff Without Buying Poolside A US$6bn non-exclusive licence to the model factory, 109 employees transferring, and US$1bn of equity at a US$... EV Eva Chin 22 Aug

Vintage postage stamps from many different countries scattered across a single white envelope on a wooden desk

ASEAN Tech 6 min What the Same Sentence Costs in Eleven Languages Write a prompt in Thai and it costs more than the same prompt in English — not because the model charges you d... SA Sarah Chew 21 Aug

A railway junction where many tracks converge and diverge through switching gear, illustrating a report on the acquisition of a gateway that routes AI requests.

Developer Tools 8 min Stripe Is Buying The Layer That Decides Which AI Model Answers You OpenRouter routes enterprise work across about 400 models and meters the token spend. A payments company buyin... MA Maya Lin 21 Aug

Two rows of painted wooden nesting dolls on a shelf outdoors, larger ones behind and smaller ones in front, each hand-painted with flowers and headscarves in red, blue and gold against a green blurred background.

AI & ML 6 min How Big a "Small" Model Really Is A parameter count is not a size. Mistral 7B is 14.5 GB of weights before the KV cache exists, and most model r... MA Maya Lin 20 Aug

A straight dirt road running away from the camera between two bamboo fences, toward a large forested hill on the horizon. A few tin-roofed houses sit at the far end, and limestone peaks fade into haze behind.

Developer Tools 6 min Your AI API Call Leaves the Country From a server in Singapore, OpenAI's API accepts a connection in 6.2ms and takes 237ms to say anything. Anthro... MA Maya Lin 19 Aug

A worker in a frost-covered jacket and heavy gloves aims a handheld barcode scanner at a cardboard box in a cold-storage warehouse, the scanner's red beam falling across the box while breath fogs the freezing air. Racking recedes into the dark blue background.

AI & ML 6 min What You Are Trusting When You Download a Model We checked the 1,000 most-downloaded models on the Hugging Face Hub. 99% ship a model card, so documentation i... KE Kenji Tanaka 19 Aug

A close-up image of an open book with visible text, showcasing turning pages.

AI & ML 8 min The Region's Best "Sovereign" AI Model Is Built on Gemma and Licensed by Google Vietnam has made national language models a strategic product. Southeast Asia's most developed answer ranks #4... KE Kenji Tanaka 5 Aug

An antique balance beam mounted on a wall beside a wooden measuring rod, its pan hanging empty — an instrument that only tells you anything when it is weighed against a known standard.

AI & ML 10 min We Went Looking for What AI Is Bad At. We Found a Bill Instead. Every business owner wants a map of where AI is reliable and where it is not. We built five task types — draft... KE Kenji Tanaka 3 Aug

A researcher at a laboratory bench, back to the camera, surrounded by rows of identical glassware — the shape of a controlled comparison, where only one thing is allowed to differ.

AI & ML 12 min We Tested the Prompting Folklore — 474 Answers Later, Nothing Had Changed Tell the model it is an expert. Offer it a $200 tip. Threaten it. Say please. Add "let's think step by step".... NA Nadia Rahim 3 Aug

Close-up of vintage wooden letterpress blocks spelling 'pleasure' on paper.

AI & ML 14 min Why AI Cannot Spell — What Image, Video and Voice Models Do Instead A language model emits one symbol at a time, in order. An image model starts from noise and refines the whole... KE Kenji Tanaka 2 Aug

Close-up of a vintage industrial control panel with multiple buttons and switches.

AI & ML 12 min How to Spend Fewer Tokens — and Why That Is the Fourth Thing to Try Every guide to controlling an AI bill opens by telling you to trim your prompt. We ran the arithmetic over all... KE Kenji Tanaka 2 Aug

A woman searching a wall of library card-catalogue drawers, pulling one open — a filing system is only useful when its drawers match what is being filed.

AI & ML 13 min What Am I Actually Choosing Between? We Sorted 1,347 AI Tools by Shape The usual answer is five neat categories — chat assistants, copilots, command-line agents, autonomous runtimes... MA Maya Lin 2 Aug

Wooden closed sign hanging on a shop window, with blurred background outside.

AI & ML 17 min Do You Need Fine-Tuning? Two of the Big Three Are Taking It Away The usual case against fine-tuning is that it is expensive. That case is wrong — a small training run costs ab... KE Kenji Tanaka 2 Aug

A Hong Kong road sign giving the same directions twice, in English and in Traditional Chinese.

AI & ML 14 min Using AI in Your Own Language — What the Machine Can Actually See The same sentence costs seven tokens in English and fifteen in Malay. That gap is usually explained as a money... KE Kenji Tanaka 2 Aug

Industrial steel staircase in low light with steps of uneven prominence receding into shadow — illustrating a price ladder whose rungs have pulled apart.

AI & ML 6 min OpenAI Cut Its Cheapest Model by 80 Per Cent. Its Own Price Ladder Now Runs 25 to 1 Luna fell from $1 to 20 cents per million input tokens three weeks after launch. Terra fell 20 per cent. The f... AI AI Tools Desk 1 Aug

A laptop on a steel workbench on a factory mezzanine at night, work gloves and hand tools beside it, machine shop equipment out of focus below

AI & ML 12 min The Best Forward Deployed Engineers May Not Be Engineers An AI practitioner in Beijing argues that the best Forward Deployed Engineers he has worked with were not comp... JE Jeffrey Tan 31 Jul

A darkened server hall at night, rows of cabinets receding down a concrete aisle with status lights glowing faintly.

AI & ML 9 min Where Does My Data Actually Go? "Do you use my data?" is two questions wearing one coat. Training asks whether your text enters a future model... JE Jeffrey Tan 31 Jul

Advertisement