AI Calculator Pro

Devstral 2 vs Mistral Small 4

Cost and capability comparison. For a sample workload of 1,000 input and 500 output tokens across 100,000 requests/month, Mistral Small 4 is cheaper by about $40.00/month.

Devstral 2Mistral Small 4
Providermistralmistral
Input / 1M$0.4000$0.1500
Output / 1M$0.9000$0.6000
Per request (sample)$0.000850$0.000450
Monthly (sample)$85.00$45.00
Context window262,000131,000
VisionNoNo
ReasoningNoNo
Arena · Overall13401325
Arena · Coding11941328
Arena · Math & reasoning13301320

Intelligence scores are community Arena ratings from LMArena / arena.ai, used under CC BY 4.0. Snapshot last refreshed 28 July 2026. Scores are a relative signal, not an absolute measure of capability. A Measured score was voted on directly; an Estimated score is inherited from an identical base model (a regional/creator-prefixed hosting duplicate). See our methodology.

Compare on your own workload

Devstral 2 and Mistral Small 4 are pre-loaded. Adjust the tokens and monthly volume to see which is cheaper for your usage.

Used unless you set active users below.

Results update automatically as you type.

Result
Cheapest: Mistral Small 4 at $45.00/month
Workload: 1,000 in / 500 out × 100,000 requests/month
Mistral Small 4Mistral AI$0.000450$45.00$540.00131,000
Devstral 2Mistral AI$0.000850$85.00$1,020.00262,000

FAQ

Which is cheaper, Devstral 2 or Mistral Small 4?

For a workload of 1,000 input and 500 output tokens over 100,000 requests/month, Mistral Small 4 is cheaper, costing about $45.00/month versus $85.00/month.

What is the context window of Devstral 2 and Mistral Small 4?

Devstral 2 supports 262,000 tokens, while Mistral Small 4 supports 131,000 tokens.

Estimates for planning only. Verify current pricing with each provider.