Mistral Medium 3.5 vs Mistral Small 4
Mistral's capability tier against its efficiency tier.
What the numbers say
- Mistral Small 4 is about 13x cheaper on output tokens (6.6 vs 82.5 credits per 1M).
- Both take the same 262K-token context window.
- Mistral Medium 3.5 is the newer release (April 2026 vs March 2026).
Derived from the live registry Zeplik routes and bills against. Credits: 1 credit = $0.10, raw provider rate with a 1.10x margin.
Side by side
Mistral Medium 3.5
Mistral
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...
- Provider
- Mistral
- Context window
- 262K tokens
- Input price
- 16.5 credits / 1M tokens ($1.50 raw)
- Output price
- 82.5 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. It combines strong reasoning from...
- Provider
- Mistral
- Context window
- 262K tokens
- Input price
- 1.7 credits / 1M tokens ($0.15 raw)
- Output price
- 6.6 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.