Independent guides to language models and computing: chatbots, API costs, agents, local models and regulation. Every figure links to its source and has a date. https://13k.eu/en/ 2026-11-06T17:00:00+01:00 https://13k.eu/en/apis/chatbot-cost-per-month/ 2026-11-06T08:00:00+01:00 2026-11-06T08:00:00+01:00

What a support chatbot costs in API fees on eight models at 1,000, 10,000 and 100,000 conversations a month, and how much prompt caching saves.

https://13k.eu/en/explained/what-is-a-system-prompt/ 2026-11-06T17:00:00+01:00 2026-11-06T17:00:00+01:00

A system prompt sets a model's role, rules and format before the user types. How OpenAI, Claude and Gemini handle it, what it costs and why it is not secret.

https://13k.eu/en/policy/open-weight-licenses/ 2026-11-05T07:00:00+01:00 2026-11-05T07:00:00+01:00

What open-weight model licenses allow: Apache 2.0 and MIT models, Qwen, Muse and Llama custom licenses, revenue thresholds, attribution and the EU clause.

https://13k.eu/en/explained/mixture-of-experts/ 2026-11-05T20:00:00+01:00 2026-11-05T20:00:00+01:00

Mixture of experts explained: how MoE models route each token to a few experts, why total parameters set memory and active ones set speed, and how to run them.

https://13k.eu/en/coding/code-review-tools/ 2026-11-04T20:00:00+01:00 2026-11-04T20:00:00+01:00

Automated code review compared: GitHub Copilot code review, Claude Code /code-review and Codex, how each one works, what it costs and how to get good results.

https://13k.eu/en/agents/self-host-n8n/ 2026-11-04T07:00:00+01:00 2026-11-04T07:00:00+01:00

How to self-host n8n with Docker: requirements, the recommended Compose setup, what the free Community edition leaves out and what the license allows.

https://13k.eu/en/apis/api-rate-limits/ 2026-11-03T07:00:00+01:00 2026-11-03T07:00:00+01:00

How API rate limits work at OpenAI, Anthropic and Google: RPM, TPM, usage tiers, spend caps, what a 429 error means and how to stop hitting it.

https://13k.eu/en/assistants/chatgpt-vs-gemini/ 2026-10-06T00:00:00Z 2026-11-03T00:00:00Z

ChatGPT or Gemini? Compare free and paid plans, prices in dollars and euros, usage limits, bundled extras, coding agents and data use from OpenAI and Google.

https://13k.eu/en/assistants/claude-vs-gemini/ 2026-10-17T07:00:00+02:00 2026-11-03T00:00:00Z

Claude vs Gemini from their own pages: free and paid plans, models, context window, coding tools, what each does with your chats and which to pick.

https://13k.eu/en/agents/n8n-vs-zapier-vs-make/ 2026-10-13T07:00:00+02:00 2026-11-03T00:00:00Z

n8n vs Zapier vs Make: executions, tasks and credits explained, plan prices, the same workflow priced three ways, agents, MCP and self-hosting compared.

https://13k.eu/en/apis/openai-api-pricing/ 2026-10-12T07:00:00+02:00 2026-11-03T00:00:00Z

OpenAI API prices per million tokens for GPT-6 Astra, GPT-6.1 Sol, GPT-6.1 Terra and GPT-6 Luna, with caching, long prompts, Batch, Fast and tools.

https://13k.eu/en/assistants/video-generators/ 2026-11-03T20:00:00+01:00 2026-11-03T20:00:00+01:00

Video generators compared after Sora closed: Gemini Omni, Runway, Midjourney video and Adobe Firefly, how each charges and what to check before publishing.

https://13k.eu/en/agents/connect-mcp-server/ 2026-11-02T07:00:00+01:00 2026-11-02T07:00:00+01:00

How to add an MCP server to Claude, Claude Desktop, Claude Code, VS Code and ChatGPT, remote or local, and the security checks to make before you connect.

https://13k.eu/en/local-models/open-webui/ 2026-11-02T20:00:00+01:00 2026-11-02T20:00:00+01:00

How to install Open WebUI with Docker or pip, connect it to Ollama, pick the main, slim or cuda image, set up the admin and what its license allows.

https://13k.eu/en/explained/llm-temperature/ 2026-11-01T07:00:00+01:00 2026-11-01T07:00:00+01:00

What LLM temperature, top_p and top_k do, which APIs still accept them in 2026, why temperature 0 is not deterministic and what to use instead.

https://13k.eu/en/assistants/make-a-presentation/ 2026-11-01T20:00:00+01:00 2026-11-01T20:00:00+01:00

How to make a presentation with ChatGPT, Copilot in PowerPoint, Gemini in Google Slides or Claude: plans, templates, export and a method that works.

https://13k.eu/en/assistants/chatgpt-memory/ 2026-10-31T20:00:00+01:00 2026-10-31T20:00:00+01:00

What ChatGPT memory remembers, how saved memories and chat history differ, how to check, turn off or fully delete it, and how Claude and Gemini compare.

https://13k.eu/en/local-models/run-llm-on-mac/ 2026-10-31T07:00:00+01:00 2026-10-31T07:00:00+01:00

How to run an LLM on an Apple silicon Mac with Ollama, LM Studio or MLX: requirements, how much unified memory each model needs, context and memory limits.

https://13k.eu/en/assistants/image-generators/ 2026-10-30T20:00:00+01:00 2026-10-30T20:00:00+01:00

ChatGPT Images, Gemini's Nano Banana, Midjourney and Adobe Firefly compared: free use, how limits work, prices, editing and who owns the pictures.

https://13k.eu/en/apis/structured-outputs/ 2026-10-30T07:00:00+01:00 2026-10-30T07:00:00+01:00

How structured outputs force a model to return JSON that matches your schema in OpenAI, Claude, Gemini and Ollama, what JSON Schema they accept and the limits.

https://13k.eu/en/coding/agents-md/ 2026-10-29T20:00:00+01:00 2026-10-29T20:00:00+01:00

What AGENTS.md is, what to put in it and how Codex, Claude Code, Cursor and GitHub Copilot read it, with nesting rules, size limits and security advice.

https://13k.eu/en/coding/best-coding-assistants/ 2026-10-06T00:00:00Z 2026-10-29T00:00:00Z

The best coding assistant by price and way of working: Claude Code, Codex, GitHub Copilot, Cursor, Antigravity, Mistral and local models, from vendor pages.

https://13k.eu/en/assistants/best-free-chatbot/ 2026-10-29T07:00:00+01:00 2026-10-29T07:00:00+01:00

Best free chatbot in 2026: the free plans of ChatGPT, Gemini, Claude, Copilot, Mistral Vibe and DeepSeek compared on limits, features and privacy.

https://13k.eu/en/apis/claude-api-pricing/ 2026-10-09T07:00:00+02:00 2026-10-29T00:00:00Z

Claude API prices per million tokens for Haiku 5.5, Sonnet 5.5, Opus 5.5 and Fable 5.1, with caching, batch, thinking and tool costs and a worked example.

https://13k.eu/en/coding/claude-code-vs-cursor/ 2026-10-06T00:00:00Z 2026-10-29T00:00:00Z

Claude Code vs Cursor, Codex and GitHub Copilot: what each costs, where it runs, how usage is limited and what each says about your code, from vendor pages.

https://13k.eu/en/assistants/chatgpt-pricing/ 2026-10-06T00:00:00Z 2026-10-28T00:00:00Z

ChatGPT pricing in October 2026: what Free, Go, Plus, Pro and Business cost, what each plan includes, context windows, usage limits and how euro prices work.

https://13k.eu/en/assistants/claude-pricing/ 2026-10-06T00:00:00Z 2026-10-28T00:00:00Z

Claude pricing in October 2026: what Free, Pro, Max, Team and Enterprise cost, what each plan includes, how usage limits work and when the API is cheaper.

https://13k.eu/en/apis/gemini-api-pricing/ 2026-10-15T07:00:00+02:00 2026-10-28T00:00:00Z

Gemini API prices per million tokens for 4 Argon, 3.1 Pro, 3.8 Flash and Flash-Lite, the free tier and its catches, paid tiers, grounding and the price rises.

https://13k.eu/en/apis/mistral-api-pricing/ 2026-10-28T07:00:00+01:00 2026-10-28T07:00:00+01:00

Mistral API pricing in October 2026: Large 4 at $1.36 and $4.18 per million tokens, plus Medium 3.5, Small 4, Ministral, Codestral, Voxtral and OCR.

https://13k.eu/en/explained/what-are-embeddings/ 2026-10-28T20:00:00+01:00 2026-10-28T20:00:00+01:00

What embeddings are, how semantic search and retrieval use them, which models OpenAI, Gemini, Voyage and Ollama offer, what they cost and the mistakes to avoid.

https://13k.eu/en/explained/text-detectors/ 2026-10-27T07:00:00+01:00 2026-10-27T07:00:00+01:00

Are machine-text detectors accurate? OpenAI withdrew its own, a study saw 61% of non-native essays flagged and Turnitin reports 4% false positives per sentence.

https://13k.eu/en/assistants/chatbots-for-excel/ 2026-10-27T20:00:00+01:00 2026-10-27T20:00:00+01:00

Copilot in Excel, Gemini in Sheets, ChatGPT data analysis and Claude for Excel compared: where each runs, the plan you need, what it can do and its limits.

https://13k.eu/en/agents/agents-for-business/ 2026-10-01T00:00:00Z 2026-10-26T00:00:00Z

Which business tasks suit an agent, whether you need one, three ways to get one, what model calls cost in a worked example, the main risks and EU rules.

https://13k.eu/en/apis/batch-api/ 2026-10-26T20:00:00+01:00 2026-10-26T20:00:00+01:00

How batch APIs work in OpenAI, Claude, Gemini and Mistral: the 50% discount, 24-hour windows, size limits, retention and when a batch is the wrong choice.

https://13k.eu/en/apis/llm-api-pricing/ 2026-10-01T00:00:00Z 2026-10-26T00:00:00Z

API prices for OpenAI, Anthropic, Google and DeepSeek models per million tokens, plus a calculator with caching, batch discounts and tokenizer differences.

https://13k.eu/en/explained/model-hallucinations/ 2026-10-06T00:00:00Z 2026-10-26T00:00:00Z

What model hallucinations are, why language models make things up (training and grading reward guessing), and the techniques Anthropic documents to reduce them.

https://13k.eu/en/apis/prompt-caching-explained/ 2026-10-06T00:00:00Z 2026-10-26T00:00:00Z

What prompt caching is, how OpenAI, Anthropic, Google and DeepSeek do it, minimum lengths, lifetimes, prices and how to structure prompts to cut your API bill.

https://13k.eu/en/explained/what-is-a-context-window/ 2026-10-06T00:00:00Z 2026-10-26T00:00:00Z

What a context window is, how big it is for Claude, GPT and Gemini in 2026, what happens when it fills up, why bigger is not always better and what it costs.

https://13k.eu/en/policy/prompt-injection/ 2026-10-26T07:00:00+01:00 2026-10-26T07:00:00+01:00

Prompt injection explained: how direct and indirect attacks hijack chatbots and agents, and why OWASP and the UK NCSC say it can only be reduced, not fixed.

https://13k.eu/en/explained/reasoning-models/ 2026-10-25T20:00:00+01:00 2026-10-25T20:00:00+01:00

What a reasoning model is: how thinking works in OpenAI, Claude, Gemini and DeepSeek, why you pay for reasoning you never see and how to control its depth.