Model comparison

Mistral Large 3 vs Mistral Medium 3

Compare Mistral Large 3 vs Mistral Medium 3 API pricing: input/output token costs, cache pricing, context windows, workload estimates, and routing fit.

Mistral Large 3

mistral · mistral/mistral-large-3

Input
$0.5
Output
$1.5
Context
262.1K

Mistral Medium 3

mistral · mistral/mistral-medium-2505

Input
$0.4
Output
$2
Context
131.1K

Quick take

Mistral Medium 3 has the lower input price at $0.4 per 1M input tokens. Mistral Large 3 is cheaper for the example blended workload below. Mistral Large 3 has the larger context window at 262.1K tokens.

Choose Mistral Large 3 if...

  • Mistral Large 3 is the better default for cost-sensitive traffic and repeated high-volume calls.
  • Mistral Large 3 is safer for long documents, repository analysis, and RAG prompts because it has the larger context window.
  • Mistral Large 3 gives more room for long generated answers, reports, or code output.

Choose Mistral Medium 3 if...

  • Mistral Medium 3 is the better default for cost-sensitive traffic and repeated high-volume calls.

Example workload cost

Estimates use input tokens plus 20% output tokens. They exclude provider discounts, cache hits, and tool/search surcharges.

Workload Mistral Large 3 Mistral Medium 3 Cheaper
1M input + 200K output $0.80 $0.80 Mistral Large 3
10M input + 2M output $8.00 $8.00 Mistral Large 3
100M input + 20M output $80.00 $80.00 Mistral Large 3

Context, output, and capability fit

Mistral Large 3 provides the larger context window. Check max output separately when the task needs long reports, code generation, or full-document rewrites.

Mistral Large 3 max output
262.1K
Mistral Medium 3 max output
8.2K
Mistral Large 3 features
function calling, vision
Mistral Medium 3 features
function calling

Risk notes for Mistral Large 3

  • No prompt caching in this snapshot: repeated long-context calls may be more expensive.

Risk notes for Mistral Medium 3

  • Smaller context window: long PDFs, codebases, or RAG prompts may need chunking.
  • No prompt caching in this snapshot: repeated long-context calls may be more expensive.

Routing tags

frontiercodingreasoningagentsopen-weightenterpriselocal-openbudget

Related comparisons