Large language models and tools
Learning Objectives
After this chapter, you should be able to:
- Segment the model landscape into closed frontier, open-weight frontier, and small local models, and match each segment to the workloads it serves.
- Choose models on capability, cost, and data-sovereignty grounds rather than brand familiarity.
- Run the fifteen-minute quarterly currency check that keeps your model knowledge from aging like a printed table.
Large Language Models (LLMs) have changed how we work with natural language. Trained on enormous datasets, they can draft a memo, debug a spreadsheet formula, or work through a problem in a specialized field, all from a plain English request. This chapter compares some of the most notable LLMs currently available, including OpenAI's GPT series, Anthropic's Claude, Google's Gemini series, and challengers such as DeepSeek, Moonshot AI's Kimi, and Grok. A note before we begin: model names and version numbers churn quarterly, so treat the specific models named here as a snapshot (mid-2026) and the selection criteria as the durable lesson. We will also look at integrated platforms, playgrounds for experimentation, and options for running models locally.
4.1 Leading Commercial Models: OpenAI, Anthropic, and Google
4.1.1 OpenAI's GPT Series: Pushing the Boundaries
OpenAI's GPT series sits at the front of the commercial pack. Each generation has brought improvements in architecture and capability, and the current family handles contextual understanding, multimodal processing (text, image, audio), and nuanced language generation better than anything the company shipped before. The flagship generation at press time (mid-2026) is GPT-5.6, released in three sizes named for celestial bodies: Sol, the frontier flagship and OpenAI's strongest coding and science model to date; Terra, the mid-tier workhorse; and Luna, the small, fast, inexpensive option. The generation's headline improvement is token efficiency: OpenAI reports Sol completing coding tasks with roughly half the tokens of its predecessors, which translates directly into lower cost and latency, and it ships with OpenAI's most advanced safety stack.
Around the models, OpenAI has built a serious agent platform: the Responses API (which replaced the older Chat Completions interface), the Agents SDK and AgentKit for building multi-agent systems with sandboxed execution and tracing, and Codex, its agentic coding product, which passed five million weekly active users in 2026. For business buyers, this platform layer increasingly matters as much as the model itself.
Choosing within the GPT series usually comes down to weighing raw capability (Sol) against efficiency and cost (Terra and Luna): route the hard, high-stakes work to the flagship and the high-volume routine work to the smaller tiers.
4.1.2 Anthropic's Claude Series: Focus on Enterprise and Safety
Anthropic's Claude series puts its emphasis on safe, coherent, and reliable output, and in June 2026 it gained a new top tier. Claude Fable 5, the first model in the Claude 5 family, belongs to a new "Mythos-class" capability tier that sits above the familiar Opus class. Its sibling, Claude Mythos 5, shares the same underlying model but is available only to approved organizations (such as vetted cyberdefense and biomedical research groups); Fable 5 is the generally available version, with additional safeguards around dual-use capabilities in areas like offensive cybersecurity and biology. The two-model release is itself a lesson in AI governance: as frontier capability grows, labs are beginning to segment access by risk rather than releasing one model to everyone.
Beneath the flagship sit the familiar tiers: Claude Opus, the everyday frontier workhorse; Claude Sonnet, balancing near-Opus capability with markedly lower cost; and Claude Haiku, covering fast, cost-sensitive, high-volume use cases such as sub-agent fleets. The series excels at agentic coding, long-horizon autonomous work, and writing; Anthropic trains its models with Constitutional AI to reduce harmful responses and stay aligned with user intent. Claude offers a very large context window (up to 1M tokens), native tool use, and computer use, and its Claude Code product has become one of the reference harnesses for agentic software work. Capability at the top of the family is striking: early Fable 5 deployments include a payment company's one-day migration of a 50-million-line codebase, work previously estimated in team-months. That combination suits enterprise applications, professional services, and customer-facing settings where dependability matters more than novelty, and by mid-2026 Anthropic held the largest share of enterprise LLM API spending.
4.1.3 Google's Gemini Series: Multimodality and Research Integration
Google's Gemini series was built multimodal from the start. The current line spans a Pro tier and an efficiency-focused Flash tier, with a "Deep Think" mode delivering Olympiad-level science and mathematics reasoning for premium subscribers, and the models reason across text, images, video, and audio inputs with context windows of up to one million tokens, which allows deep analysis of long documents, codebases, or multimedia content. Flash targets efficiency, offering high performance at lower cost, while the Pro tier handles the most demanding reasoning and multimodal workloads. One cautionary note for buyers: Google's next flagship slipped repeatedly through 2026 amid reliability rework, a useful reminder that roadmap promises are not products.
Google also puts its models to work in specialized research tools. NotebookLM acts as a personalized research assistant, grounding its responses in source materials you provide, which makes its answers easier to verify. Google is also exploring concepts like the "AI Co-scientist," which puts AI to work directly in the research process, from hypothesis generation to data analysis (https://research.google/ blog/accelerating-scientific-breakthroughs-with-an-ai-co-scientist/).
4.2 Other Notable Models and Platforms
The "big three" do not have the field to themselves, and by mid-2026 the most important challengers are open-weight models, several of them from Chinese labs, that trail the closed frontier by months rather than years.
4.2.1 DeepSeek: Open-Weight Powerhouse
DeepSeek made its name in early 2025 when its R1 reasoning model matched frontier-level performance at a fraction of the training cost, briefly shaking global technology markets. Its current generation, MIT-licensed, with a million-token context and near-frontier coding scores, plus an ultra-cheap Flash variant, continues the pattern: open weights, efficient Mixture-of-Experts architectures, and prices an order of magnitude below the closed labs. That openness is the draw: researchers and enterprises who want customization, transparency, on-premises deployment, or lower operating expenses can simply take the weights and run.
4.2.2 Grok: Real-time Information and Conversational Style
Grok, developed by xAI (folded into the SpaceX orbit in 2026), sells itself on a conversational style often described as witty or rebellious, and on access to real-time information through its integration with the X platform. Recent releases have repositioned the line as a serious coding and agents model rather than a personality act. If your work involves tracking current events, trends, or public discourse, the real-time access is worth something.
4.2.3 Kimi and the Open-Weight Wave
The clearest sign that open-weight models have reached the frontier came in July 2026, when Moonshot AI released Kimi K3: a 2.8-trillion-parameter Mixture-of-Experts model, the largest ever published with open weights, with a 1M-token context window, native vision, and an always-on reasoning mode. On independent leaderboards it ranks just behind the top closed flagships, meaning any company can now download, inspect, fine-tune, and self-host a model within striking distance of the best closed systems, at API prices well below them.
K3 is the crest of a broader wave. Zhipu's GLM line (MIT-licensed) and MiniMax's models (the first to combine open weights, frontier coding, and native multimodality) push the same frontier, while Alibaba's Qwen line dominates the small-model tier that runs on ordinary hardware. For strategy, the implication is twofold. First, the floor price of intelligence keeps collapsing, which changes build-versus-buy math for every AI product. Second, data sovereignty is now compatible with capability: a bank or hospital that cannot send data to a US cloud can self-host a near-frontier model. The trade-offs are governance and support: open weights mean you own the deployment, the security patching, and the compliance story yourself.
4.3 Integrated platforms
Some platforms bundle several LLMs behind a single interface, so you can switch models without switching accounts. Why would you want that? Because no single model is best at everything, and comparing two answers to the same prompt teaches you more about a model's blind spots than any benchmark table.
4.3.1 Poe
Poe, developed by Quora, gives you one place to reach multiple AI chatbots, including the latest GPT, Claude, Gemini, and open-weight models. You ask a question, get an answer, and carry on the conversation, switching models whenever one disappoints you.
4.3.2 Coze
Coze is a chatbot development platform for people who may never have written a line of code. Users build customized chatbots and deploy them across social platforms and messaging apps. Its focus is personalization: the bots adapt to user-specific preferences and learn from repeated interactions.
4.3.3 Perplexity AI
Perplexity AI is a conversational search engine. It pairs large language models with web search and returns concise answers backed by cited sources, so you get a direct response to your question rather than a page of links.
4.3.4 OpenRouter
OpenRouter is the developer-side version of the same idea: a single API gateway that routes requests to hundreds of models across every major provider, closed and open-weight alike, with unified billing and automatic fallbacks. For teams, it is the fastest way to A/B test models in a real application, and its public usage rankings double as a live census of which models developers actually choose when they are paying.
4.3.5 You.com
You.com is a search engine built around a chat-first AI assistant, with conventional web search still available underneath. Its AI Modes let users switch between leading models from OpenAI, Anthropic, Google, and the open-weight ecosystem, and the company has increasingly pivoted toward enterprise research-agent products.
The pattern across all five is the same: one interface, many models, and the freedom to pick whichever fits the task in front of you.
4.4 Playgrounds
Before you commit a budget to any model, test it. Playgrounds exist for exactly this. Platforms such as OpenAI Playground, Google AI Studio, NVIDIA AI Playground, IBM watsonx.ai, and Hugging Face give developers, researchers, and businesses a low-stakes place to try the leading open-weight models (Llama, Kimi, DeepSeek, Qwen) and others: experiment with prompts, explore fine-tuning, check integration options. Most offer free tiers or trials, so a half-day of testing costs you nothing but the half day. In my experience that half day saves weeks of regret later.
4.4.1 LMArena
LMArena (https://lmarena.ai/) lets you feed identical prompts to several language models and judge the results side by side. It is open access, and it gives you a transparent way to work out which model suits your needs, whether that is conversational fluency, response accuracy, or domain-specific expertise.
4.4.2 Nvidia build platform
Nvidia's LLM comparison platform (https://build.nvidia.com/) is another useful benchmarking stop. Built on Nvidia's hardware acceleration expertise, it lets you assess different LLMs for speed and accuracy across various tasks.
4.4.3 Google AI Studio
Google AI Studio (https://aistudio.google.com/) is the venue for comparing Google's own LLMs, such as Gemini, against other available models. Beyond benchmarks, it shows how a model behaves under awkward real-world conditions: limited compute, or a genuinely complicated user query.
4.4.4 Hugging Face
Hugging Face hosts a wide array of AI models, including the Llama, DeepSeek, Kimi, and Qwen families, many testable through the platform's interface. Many models are free to try; subscription plans add features on top.
Each of these platforms has its own strengths and access levels, but any of them will let you kick the tires before you buy.
4.4.5 OpenAI Playground
The OpenAI Playground is OpenAI's own web interface for experimenting with its language models, including the current GPT family in all its sizes and earlier models. Type a prompt, watch the response come back in real time. Free access comes with usage limitations; extended access may require a subscription.
4.4.6 IBM watsonx.ai
IBM's watsonx.ai is an enterprise-ready AI studio offering a selection of foundation models, including IBM's own Granite series alongside other open-source models. You can build, train, and deploy models on the platform, and a free trial lets you explore before committing.
4.5 Local Deployment of Language Models
Not everyone can, or should, pay for a frontier model over an API. Free alternatives exist, and they let you work with LLMs at little or no cost, with trade-offs in sophistication, accuracy, or data privacy.
For individuals or institutions that put data security and customization first, running language models locally is an attractive option. Tools such as LMStudio and Ollama let you run LLMs on local servers or personal hardware, so nothing you type ever leaves the building. For healthcare or finance, where privacy and compliance rules are strict, that alone can settle the question. Open-weight models can be deployed and used for research, education, and commercial use under their respective licenses. Be realistic about hardware, though: the frontier open models (the largest Kimi, DeepSeek, and Llama variants) need server-class GPUs, while the small-model tier, Alibaba's Qwen models, Mistral's Small line, and OpenAI's gpt-oss releases, runs comfortably on a well-equipped laptop. The small models do not rival the closed flagships in depth, but they deliver considerable functionality at no per-token cost, which makes them especially useful for classrooms, non-profits, and privacy-critical prototypes.
Mistral AI's open models are another alternative worth knowing. Mistral Large 3, released under an Apache license, was the largest open-weight model from a Western lab at its release, and the smaller Mistral models perform competitively on everyday language understanding and generation tasks. For many routine jobs the gap to the commercial frontier barely shows.
LMStudio offers a streamlined way to deploy smaller, fine-tuned versions of major LLMs, so enterprises can meet their own requirements without depending on third-party infrastructure. Because you can adjust the models to specific needs, you keep control over both your data and the model's behavior.
Ollama, another local deployment option, is built for ease of use. Its deployment scripts and pre-configured environments assume limited technical expertise, which makes it a sensible choice for small businesses and individual researchers who want to run LLMs without heavy spending on hardware or specialized talent.
4.5.1 Tutorial:
To install and run a local model in LM Studio, follow these steps. We use a small open-weight model that genuinely runs on a well-equipped laptop (the frontier open models need server-class GPUs):
- Download LM Studio: Visit the LM Studio website and download the installer compatible with your operating system.
- Install LM Studio: Run the downloaded installer and follow the on-screen instructions to complete the installation.
- Launch LM Studio: Open the application after installation.
- Download a model:
- Navigate to the 'Search' tab within LM Studio.
- Search for a small open-weight model, e.g., "Qwen" or "gpt-oss".
- Select a variant sized for your machine (a ~4B-20B parameter model for most laptops).
- Click 'Download' to initiate the model download.
- Load the Model:
- After the download completes, go to the 'AI Chat' section.
- Click on 'Select a model to load' and choose the downloaded model.
- The model will load, allowing you to interact with it through the chat interface.
Check your hardware first. Large models are memory-hungry, and an underpowered machine will make the experience miserable.
4.6 A Habit, Not a Snapshot: How to Check What Is Current
Every model name in this chapter is a photograph of a moving object, taken in mid-2026. The durable skill is not memorizing the lineup; it is the fifteen-minute quarterly check that keeps your mental map current. Three stops suffice. LMArena (lmarena.ai) shows how models rank on blind human preference. Artificial Analysis (artificialanalysis.ai) tracks independent benchmarks, prices, and speed across every provider on one page. And each vendor's own pricing page is the only authoritative source for what you will actually pay. When a colleague or vendor names a model, the reflex to build is simple: check when it shipped, what it costs per million tokens, and how it ranks against the incumbent, before anyone builds anything on it. Fifteen minutes, four times a year, keeps you permanently ahead of most of the room.
Discussion Questions
- For your most sensitive workload, argue both sides: closed frontier API versus self-hosted open-weight model. Which wins, and on what grounds?
- What concrete signals would make you switch primary model vendors, and how would your eval suite tell you it is time?
- Run the fifteen-minute currency check now. What has changed since this book's mid-2026 snapshot, and does any of it change a decision?