Model comparison

Mistral Medium 3.5 vs Cohere Command A

Compare Mistral Medium 3.5 vs Cohere Command A API pricing: input/output token costs, cache pricing, context windows, workload estimates, and routing fit.

Mistral Medium 3.5

mistral · mistral/mistral-medium-3-5

Input
$1.5
Output
$7.5
Context
262.1K

Cohere Command A

cohere_chat · command-a-03-2025

Input
$2.5
Output
$10
Context
256K

Quick take

Mistral Medium 3.5 has the lower input price at $1.5 per 1M input tokens. Mistral Medium 3.5 is cheaper for the example blended workload below. Mistral Medium 3.5 has the larger context window at 262.1K tokens.

Choose Mistral Medium 3.5 if...

  • Mistral Medium 3.5 is the better default for cost-sensitive traffic and repeated high-volume calls.
  • Mistral Medium 3.5 is safer for long documents, repository analysis, and RAG prompts because it has the larger context window.
  • Mistral Medium 3.5 gives more room for long generated answers, reports, or code output.

Choose Cohere Command A if...

  • Cohere Command A is a reasonable pick when its provider, latency, or integration path fits your stack better.

Example workload cost

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

Workload Mistral Medium 3.5 Cohere Command A Cheaper
1M input + 200K output $3.00 $4.50 Mistral Medium 3.5
10M input + 2M output $30.00 $45.00 Mistral Medium 3.5
100M input + 20M output $300.00 $450.00 Mistral Medium 3.5

Context, output, and capability fit

Mistral Medium 3.5 provides the larger context window. Check max output separately when the task needs long reports, code generation, or full-document rewrites.

Mistral Medium 3.5 max output
262.1K
Cohere Command A max output
8K
Mistral Medium 3.5 features
function calling, vision
Cohere Command A features
function calling

Risk notes for Mistral Medium 3.5

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

Risk notes for Cohere Command A

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

Routing tags

frontiercodingreasoningagentsmultimodalopen-weightenterpriseraglocal-openenterprise-raglong-context

Related comparisons