Skip to main content
Sign inSign up

Mistral Medium 3.5 vs Mistral Small 4

Mistral's capability tier against its efficiency tier.

Figures as of , read live from the model registry Zeplik bills against.

What the numbers say

Derived from the live registry Zeplik routes and bills against. Credits: 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin.

Side by side

Mistral Medium 3.5

Mistral

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI.

Provider
Mistral
Context window
262K tokens
Input price
18.0 credits / 1M tokens ($1.50 raw)
Output price
90.0 credits / 1M tokens ($7.50 raw)
Vision (image input)
Yes
Tool calling
Yes
Extended reasoning
No

Best for

  • Hard problems where answer quality matters more than cost: strategy, analysis, difficult writing
  • Long documents: the 262K-token window holds lengthy reports, contracts or papers whole
  • Working with images: screenshots, charts, photos and scanned documents alongside text
  • Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows

Mistral Small 4

Mistral

Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system.

Provider
Mistral
Context window
262K tokens
Input price
1.8 credits / 1M tokens ($0.15 raw)
Output price
7.2 credits / 1M tokens ($0.60 raw)
Vision (image input)
Yes
Tool calling
Yes
Extended reasoning
No

Best for

  • High-volume everyday tasks where speed and cost matter: summaries, drafts, quick questions
  • Long documents: the 262K-token window holds lengthy reports, contracts or papers whole
  • Working with images: screenshots, charts, photos and scanned documents alongside text
  • Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows

Try both on Zeplik

The honest answer to most model debates is to run your own prompt on both. Zeplik puts Mistral Medium 3.5 and Mistral Small 4 in the same chat, so you can switch mid-conversation and compare answers on the work you actually do.

Pick a model and ask. Your prompt opens in the Zeplik app with that model selected.

Model to ask

Frequently asked questions

What is the difference between Mistral Medium 3.5 and Mistral Small 4?
Mistral Small 4 is about 13x cheaper on output tokens (7.2 vs 90.0 credits per 1M). Both take the same 262K-token context window. Mistral Medium 3.5 is the newer release (April 2026 vs March 2026).
Is Mistral Medium 3.5 or Mistral Small 4 cheaper?
Mistral Small 4 is cheaper: 7.2 credits per million output tokens against 90.0. 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin.
Which has the larger context window, Mistral Medium 3.5 or Mistral Small 4?
Neither: both take 262K tokens.
Can I use both Mistral Medium 3.5 and Mistral Small 4 on Zeplik?
Yes. Zeplik is a multi-model chat, so both sit behind one account and you can switch between them mid-conversation to compare answers on your own prompt.
Do Mistral Medium 3.5 and Mistral Small 4 need a paid plan?
Both need a paid plan (Plus or above). Usage is then billed in credits from your monthly allowance.

Related comparisons

Mistral Medium 3.5 detailsMistral Small 4 detailsAll comparisons

Explore Zeplik