Skip to content
AI Engineer Guide.

concept · concepts · intermediate · concept 3 of 28

Model landscape

0 of 28 complete

Why it matters

A team choosing a model faces dozens of names with overlapping claims and no shared measurement. The useful structure is a set of axes: what the model was trained to do, how much context it accepts, which modalities it handles, how it is served and what it costs at your volume. Without those axes, selection becomes fashion, and the choice is revisited every time a release appears.

Mental model

The landscape is a hardware catalogue: categories, sockets and power envelopes matter more than the model number. It breaks because model specs are not stable; a family can change tokeniser or behaviour between releases while keeping its name, so a part that fit last year may not fit now.

How it works

Mechanism, step by stepInteractive
  1. 1Group candidates by the capability the product needs: text generation, reasoning, code, vision, speech, embeddings or classification.
  2. 2Within a group, record context limit, modality support, tool-calling support and whether the weights are downloadable.
  3. 3Filter by deployment: hosted API, managed open-weight endpoint, or self-hosted on hardware you already operate.
  4. 4Shortlist two or three per role and test them on your own task set with your own prompts.
  5. 5Note the tokeniser family, since token counts and therefore cost differ for the same text.
  6. 6Re-check the shortlist on a schedule rather than on every announcement, so churn does not become the roadmap.

Step 1 of 6

Group candidates by the capability the product needs: text generation, reasoning, code, vision, speech, embeddings or classification.

Step 1/6 · step 1

Figure. The mechanism in this page's own steps. The figure adds sequence, not new claims.

What to notice. A step can be read alone, but the order is the mechanism. The control lets you stop on any one.

Text version

The page's steps: 1. Group candidates by the capability the product needs: text generation, reasoning, code, v… 2. Within a group, record context limit, modality support, tool-calling support and whether … 3. Filter by deployment: hosted API, managed open-weight endpoint, or self-hosted on hardwar… 4. Shortlist two or three per role and test them on your own task set with your own prompts. 5. Note the tokeniser family, since token counts and therefore cost differ for the same text. 6. Re-check the shortlist on a schedule rather than on every announcement, so churn does not…

  1. Group candidates by the capability the product needs: text generation, reasoning, code, vision, speech, embeddings or classification.
  2. Within a group, record context limit, modality support, tool-calling support and whether the weights are downloadable.
  3. Filter by deployment: hosted API, managed open-weight endpoint, or self-hosted on hardware you already operate.
  4. Shortlist two or three per role and test them on your own task set with your own prompts.
  5. Note the tokeniser family, since token counts and therefore cost differ for the same text.
  6. Re-check the shortlist on a schedule rather than on every announcement, so churn does not become the roadmap.

Trade-offs

ChoiceGood forCostFails when
Frontier general modelBroad capability, handles novel tasksPrice and latency at the top of the rangeThe task is narrow and high volume
Small open-weight modelCheap, controllable, self-hostableNarrower generalisation and more evaluation workInputs are open-ended and adversarial
Specialised model per taskBest quality per taskSeveral integrations and evaluation suitesThe product needs one model to do everything
Single family for all rolesShared tooling and tokeniserSome roles overpay for capabilityA role has a hard latency or cost ceiling
Trade-off mapInteractive

Good for

Broad capability, handles novel tasks

Cost

Price and latency at the top of the range

Fails when

The task is narrow and high volume

  1. The task is narrow and high volume
  2. Inputs are open-ended and adversarial
  3. The product needs one model to do everything
  4. A role has a hard latency or cost ceiling

Figure. Each choice with what it buys, what it costs, and the case where it loses.

What to notice. The fourth column is the decision: if the losing case describes your situation, the choice is wrong.

Text version

Four trade-offs: Frontier general model is good for Broad capability, handles novel tasks, costs Price and latency at the top of the range, and fails when The task is narrow and high volume. Small open-weight model is good for Cheap, controllable, self-hostable, costs Narrower generalisation and more evaluation work, and fails when Inputs are open-ended and adversarial. Specialised model per task is good for Best quality per task, costs Several integrations and evaluation suites, and fails when The product needs one model to do everything. Single family for all roles is good for Shared tooling and tokeniser, costs Some roles overpay for capability, and fails when A role has a hard latency or cost ceiling

Failure modes

  • Name-based selection. A team picks a model because it tops a leaderboard and finds it weak on their domain. Debug: score the candidate on a labelled slice of real requests before committing.
  • Ignoring tokeniser differences. The same prompt costs more or truncates earlier on the chosen model. Debug: tokenise a representative sample with each candidate tokeniser and compare counts.
  • Landscape churn as strategy. The team migrates every quarter and never accumulates evaluation history. Debug: count model migrations in the last year and check whether each one improved the frozen benchmark.

In production

Keep a table of approved models with context limits, tokeniser, price unit and evaluation score, and review it on a fixed cadence. Alert when a provider announces a deprecation for anything in the table.

Common misconceptions

People think: Newer always means better for your task.

Actually: Releases optimise different objectives; a newer model can regress on a narrow task or a specific output format.

People think: Parameter count is the main axis.

Actually: Training data, post-training, context handling and serving stack often matter more than size for a given application.

Interview angle

A strong answer organises the space by capability, deployment and constraints, then says how candidates are tested on real traffic. It mentions tokeniser and context differences as integration costs. A weak answer lists model names and recency without saying what task each was chosen for.

Sources