Models

Choosing a foundation model in 2026

Frontier vs. open-weights vs. fine-tuned small. A pragmatic decision tree, with cost numbers from real workloads.

Mindlytic AI Team · Research Engineer·2026-02-05·3 MIN READ·357 WORDS
MODELSBENCHMARKINGCOST

Choosing a foundation model in 2026 is not a religion. It's an engineering decision with cost numbers, latency numbers, and quality numbers. Here is how we pick — and how often we change our minds.

The four lanes

  1. Frontier closed-weight (the ones you talk about by company name). Best raw quality, best for hardest tasks, most expensive, slowest, least flexible.
  2. Mid-tier closed-weight. Often 70–90% of frontier quality, 5–10× cheaper, 3× faster. The default for most production paths.
  3. Open-weight, hosted. You pay for inference, not for the weights. Good for control over data residency and for cases where you want to fine-tune.
  4. Open-weight, self-hosted. You own the GPU bill. Cheapest at scale (above ~10M tokens/day). Most operational overhead.

How we pick

For each task, we run a benchmark on our internal eval set against three or four candidates. We measure quality, latency, and cost. We pick the cheapest model that hits 95% of the best model's quality on our eval. Surprisingly often, that is not the frontier model.

Cost numbers from real workloads

WorkloadFrontierMid-tierSelf-hosted 7B
Customer-service classify$0.0042/req$0.0008/req$0.0001/req
Summarization (1k tokens)$0.012/req$0.0021/req$0.0008/req
Long-form generation$0.18/req$0.043/reqnot viable
RAG answer with citations$0.038/req$0.009/req$0.003/req

When to use the frontier

Three cases. First: agent planning. Plans are short and high-leverage; pay for quality here. Second: anything legal, medical, or regulatory in tone, where a small mistake is catastrophic. Third: very long context with reasoning across the whole context — the frontier still has a lead.

When to use the mid-tier

Most things. Customer service, summarization, retrieval-augmented Q&A, classification, extraction. The mid-tier in 2026 is what the frontier was in 2024. Don't pay frontier prices for mid-tier work.

When to self-host

Three conditions, all of them: (a) your data residency requires it, (b) your volume is north of ~10M tokens/day so the GPU bill amortizes, (c) you have an SRE-trained engineer who wants to own the deployment. If any one of these is missing, hosted is cheaper all-in.

Don't fall for the leaderboard

Public leaderboards measure what the leaderboards measure. They do not measure your task. We have repeatedly found that the model that scored 4 points lower on a public benchmark scored 9 points higher on our internal eval. The leaderboard is a starting point. Your eval is the answer.

M
AUTHOR
Mindlytic AI Team
Research Engineer

Authored by the Mindlytic AI engineering practice — a senior-only team shipping production AI systems for clients across hospitality, fintech, insurance, healthcare, legal, and MSP.

Email →More about the team →
Related reading

More from the blog.

Models
The quiet revolution of small models
2025-09-04 · 12 MIN
Cost
Designing for cost from day one
2025-12-18 · 11 MIN
Models
When to fine-tune — and how to know it worked
2025-10-30 · 12 MIN

Want to ship something like this?

Mindlytic builds production AI for hospitality, fintech, insurance, and more. Book a 30-minute discovery call.