Mistral Medium 2505 vs Mistral Small latest

Mistral Medium 2505 vs Mistral Small latest: Mistral Small latest is cheaper by 91% on average. Mistral Medium 2505 from Mistral AI (131,072-token context, tool calls) vs. Mistral Small latest from Mistral AI (131,072-token context, tool calls). Use Agent Command Center to A/B both in shadow mode and pick the winner per workload.

Side-by-side cost

Live workload comparison

Same workload run through both models. The cheaper one is highlighted.

3,000
0131,072
400
0131,072
5,000
01,000,000
Mistral AI
$304/mo
Input $0.400/M · Output $2.00/M
Mistral AI
$38.35/mo
Input $0.0600/M · Output $0.180/M
At this workload, Mistral Small latest is 87% cheaper than Mistral Medium 2505 — a savings of $266/month ($3,192/year).
Production recipe — Agent Command Center
strategy: cost-optimized
primary:
  model: mistral-small-latest
  provider: mistral
fallback:
  model: mistral-medium-2505
  provider: mistral
shadow: { sample_rate: 0.05 }   # mirror 5% of traffic to compare quality live
Mistral Medium 2505 Mistral Small latest
Input price $0.400/M $0.0600/M
Output price $2.00/M $0.180/M
Context window 131,072 131,072
Max output 8,191 131,072
Function calling
Vision
Audio input
Reasoning
Prompt caching
Structured output
Pricing verified May 12, 2026 May 12, 2026
Cheaper option
~91% cheaper than Mistral Medium 2505
Larger context
131,072 tokens
More capabilities
3 of 6 capability flags advertised