Nishaglobal Education logo

Which model for which job?

A plain-English guide to AI model types and families: large and small language models, reasoning models, open-weight models, embedding, image, speech and code models, and the main families from OpenAI, Anthropic, Google, Meta, Mistral, Alibaba (Qwen) and DeepSeek. With a job-by-job table of which kind of model to use, and a live list of the latest releases.

Lesson 44 of 4418 min readQuiz: 5 questions

🎯 By the end of this lesson you will be able to:

  • Recognise the main types of AI model and what each is for
  • Know the major model families and their size tiers
  • Match common jobs to the right kind of model, and test the choice
In this lesson
  1. Types of AI model
  2. The main model families
  3. Which model for which job?
  4. A simple way to choose
  5. What this means for your role
  6. Key takeaways
  7. Quiz

Types of AI model

TypeWhat it doesExample jobs
Large language model (LLM)Understands and writes text, often also images and audioChat assistants, drafting, summarising, analysis
Reasoning model / modeThinks step by step before answering, slower but stronger on hard problemsComplex coding, maths, planning, difficult analysis
Small / fast modelA cheaper, quicker LLM for simpler tasksClassification, extraction, routing, high-volume work
Open-weight modelA model you can download and run yourself, under its licencePrivate or offline use, custom fine-tuning, cost control at scale
Embedding modelTurns text into vectors for search by meaning (Lesson 8)RAG, semantic search, recommendations, clustering
RerankerRe-orders search results by relevanceImproving RAG retrieval quality
Image modelsGenerate or edit images from textMarketing images, mock-ups, illustrations
Speech modelsSpeech to text and text to speechTranscription, voice assistants, accessibility
Code modelsLLMs tuned for programmingCoding assistants, code review, test generation

The main model families

New versions arrive every few months, so it is more useful to know the families and their tiers than any single version. Most providers offer a large, most capable tier and smaller, faster, cheaper tiers.

FamilyMakerNotes
GPTOpenAIWidely used general and reasoning models, with smaller "mini"-style variants; also open-weight gpt-oss models
ClaudeAnthropicTiers from most capable to fastest: Opus, Sonnet and Haiku; strong for coding, agents and long documents
GeminiGooglePro and Flash tiers, very long context, strong with images, video and audio; Gemma is Google's open-weight family
LlamaMetaPopular open-weight family in many sizes
MistralMistral AI (France)Open-weight and commercial models, including Codestral for code
QwenAlibabaOpen-weight family in many sizes, strong multilingual support
DeepSeekDeepSeekOpen-weight models known for strong reasoning at low cost
OthersVariousGrok (xAI), Command (Cohere, enterprise RAG), Nova (Amazon), Phi (Microsoft small models)
Cost and response time →Capability →Small / fastHaiku · Flash-Lite · mini GPTsMid tierSonnet · Flash · mid GPTsTop tier / reasoningOpus · Gemini Pro · top GPTsOpen-weight models (Llama, Qwen,Mistral, Gemma) come in all sizes
Within each family, bigger tiers are more capable but slower and more expensive. Use the smallest model that passes your quality bar.

Which model for which job?

JobKind of model to start withWhy
Customer chat assistantMid-tier LLM (e.g. Sonnet, Flash or a mid-size GPT) with RAGGood quality at reasonable cost and speed
Classify or route thousands of ticketsSmall, fast model (e.g. Haiku, Flash-Lite or a mini GPT)Simple task, high volume, low cost
Complex coding or long agent tasksTop-tier or reasoning model (e.g. Opus, a top GPT or Gemini Pro)Hard problems need the strongest reasoning
Search your documentsAn embedding model, plus a rerankerMeaning-based retrieval for RAG
Sensitive data that must stay in-houseOpen-weight model (e.g. Llama, Qwen, Mistral, Gemma) run with Ollama or vLLMData never leaves your infrastructure
Very long documents or videoA long-context or multimodal model (e.g. Gemini Pro or Claude)Fits large inputs in one request
Meeting transcriptionA speech-to-text model (e.g. Whisper or a provider's speech API)Built for accurate transcription
Marketing imagesAn image generation modelLLMs describe images; image models create them

A simple way to choose

  1. Start with the job: what type of model does it need (text, embeddings, images, speech)?
  2. Check the constraints: data rules, budget per request, speed, languages and context length.
  3. Shortlist two or three models from different families or tiers.
  4. Test them on your evaluation set with the same prompts, comparing quality, cost and speed (Lesson 43 shows promptfoo for this).
  5. Pick the smallest model that passes, and re-test when new versions are released.

What this means for your role

Developer

Keep the model name in configuration, not code, so switching tiers or providers is a config change plus an evaluation run.

Tester / QA

Run the same evaluation set on every candidate model and on each new version before switching.

Business Analyst / PO

Note data sensitivity and volume for each use case; they often decide between hosted, small or open-weight models.

Tech Lead / Architect

Maintain an approved model catalogue with the job each model is approved for, and review it when major releases arrive.

Project / Delivery Manager

Smaller models can cut running costs dramatically; ask whether the top tier is really needed for each feature.

Scrum Master / Agile

When a new model is released, timebox a quick comparison on the team's evaluation set instead of switching on hype.

Try it: pick models for three jobs

  1. Write three AI jobs from your work, such as summarising meetings, tagging tickets and answering policy questions.
  2. For each, choose the model type and tier from the table, and note one constraint (cost, privacy, speed).
  3. Open the AI model releases page and see whether any new model might be worth testing for one of your jobs.

Key takeaways

  • Model types include LLMs, reasoning models, small fast models, open-weight, embedding, reranker, image, speech and code models.
  • Know the families (GPT, Claude, Gemini, Llama, Mistral, Qwen, DeepSeek) and their tiers, not just versions.
  • Match the job to a model type and tier, and use the smallest model that meets your quality bar.
  • Choose with your own evaluation set, and re-test when new models are released.

Key terms

Model family
A series of related models from one maker, released in versions and sizes.
Tier
A size level within a family, trading capability against speed and cost.
Open-weight
A model whose trained weights you can download and run yourself, under its licence.
Multimodal
Able to work with more than one kind of input, such as text, images, audio and video.

Check your understanding

Answer all 5 questions. Score 3 or more to complete the lesson.

  1. 1. You need to tag 200,000 support tickets into 8 categories cheaply. Which model kind should you test first?

  2. 2. Which kind of model powers search by meaning in RAG?

  3. 3. Patient data must never leave your servers. What fits?

  4. 4. What are Opus, Sonnet and Haiku?

  5. 5. What is the best final step when choosing a model?

Answer all 5 questions to check.

Practise more