ModelRefs / Mistral Small 3.1 vs Mistral Large 2 — Benchmarks, Pricing…

Mistral Small 3.1 vs Mistral Large 2 — Benchmarks, Pricing…

Mistral Small 3.1 vs Mistral Large 2: side-by-side benchmarks, pricing, context windows, coding ability and deployment. Pick the right model for your stack.

Overview

Mistral Large 2: Mistral Large 2 is Mistral AI's flagship commercial model with a 128K context window, optimized for instruction-following, multilingual tasks, and function-calling in agentic workflows. It is available via la Plateforme and all major cloud providers.

Context window: Mistral Large 2 accepts up to 128,000 tokens, Mistral Small 3.1 up to 128,000. Confirm the limit for your specific deployment channel before relying on it.

Mistral Large 2 vs Mistral Small 3.1 at a glance

AttributeMistral Large 2Mistral Small 3.1
ProviderMistral AIMistral AI
Released2024-11-012025-03-17
Context window128,000 tokens128,000 tokens
Input price$2/M tokens$0.1/M tokens
Output price$6/M tokens$0.3/M tokens
LicenceMistral CommercialApache-2.0
Self-hostableNo, hosted onlyYes, open weights
Modalitiestexttext, vision

Where they differ most

  • Cost Efficiency: Mistral Large 2 56%, Mistral Small 3.1 95%. Mistral Small 3.1 leads on this dimension.
  • Reasoning: Mistral Large 2 86%, Mistral Small 3.1 67%. Mistral Large 2 leads on this dimension.

Capability scores are ModelRefs' own derived signals, not vendor claims or benchmark results. Validate against your own workload before relying on them.

Continue your research

Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Mistral Small 3.1 vs Mistral Large 2 — Benchmarks, Pricing….

Frequently asked questions

Which is better, Mistral Small 3.1 or Mistral Large 2?

Mistral Small 3.1 and Mistral Large 2 target different workloads — see the benchmark and pricing tables for a side-by-side answer.

Is Mistral Small 3.1 cheaper than Mistral Large 2?

Compare $0.00010 vs $0.00200 on this page.