Topic
Model Families & Naming Conventions: GPT-5, Claude, Gemini 3, Llama 4, Mistral, DeepSeek, Qwen, Grok
9 posts on model families & naming conventions: gpt-5, claude, gemini 3, llama 4, mistral, deepseek, qwen, grok — part of glossary on the n4n AI blog.
Why AI labs name models mini, nano, and pro
What mini, nano, and pro mean in model names — a practical guide to LLM size tiers, capability trade-offs, and how labs like Google, OpenAI, and Anthropic actually use these suffixes.
Grok 3 vs Grok 4: xAI's model naming explained
Understand xAI's Grok model naming convention, what Grok 3 delivers, and what engineers should expect from Grok 4 based on xAI's release patterns.
GPT naming history: GPT-3 to GPT-5 explained
A practical guide to OpenAI's GPT model naming evolution from GPT-3 through GPT-5, with version decoding, API implications, and migration patterns for engineers.
GPT-5 naming explained: GPT-5, mini, and nano
Understand OpenAI's GPT-5 model family naming — GPT-5, GPT-5-mini, and GPT-5-nano — with technical details on capabilities, trade-offs, and routing decisions.
Gemini 3 lineup: Pro, Flash, and Nano explained
A technical breakdown of Google's Gemini 3 model family — Pro, Flash, and Nano — covering architecture differences, token economics, and deployment trade-offs for engineers.
Flagship vs lightweight: comparing model tiers
A practitioner's comparison of flagship and lightweight LLM tiers across capabilities, cost, latency, and ecosystem — with a clear verdict for each use case.
DeepSeek V3 vs R1: what the model names mean
Understand the DeepSeek V3 vs R1 naming distinction, compare capabilities and trade-offs, and learn which model fits your inference workload.
Claude's model generations: Claude 1 to 4.5
A practical guide to Anthropic's Claude model generations, covering capabilities, tradeoffs, and migration paths from Claude 1 through 4.5 for engineers building production systems.
Claude's naming system: Opus, Sonnet, and Haiku
A technical breakdown of Anthropic's three-tier Claude model naming — Opus, Sonnet, Haiku — and what each tier means for latency, cost, and capability trade-offs.
More topics in glossary
- Structured Outputs & JSON Mode19
- AI Agents Fundamentals12
- Hallucination in LLMs11
- Sampling Parameters: Top-p, Top-k & Penalties11
- Context Window & Context Length10
- Fine-Tuning Fundamentals9
- Foundation Models: Base vs Instruct vs Chat9
- Grounding & Fact-Checking in AI8
- LLM Benchmarks: MMLU, HumanEval, SWE-bench & GPQA8
- Max Tokens, Stop Sequences & Output Truncation8
- Quantization Formats: GGUF, GPTQ, AWQ & INT4/INT88
- Chain-of-Thought Prompting7