Is Mistral Small 24B or MiniMax M2.5 cheaper?

Mistral Small 24B is cheaper on output tokens ($0.35 vs $1.20 per 1M).

Which has the larger context window, Mistral Small 24B or MiniMax M2.5?

MiniMax M2.5 has the larger context window (205K tokens).

Mistral Small 24B vs MiniMax M2.5

Mistral Small 24B is cheaper on output tokens, while MiniMax M2.5 offers a larger context window. Choose Mistral Small 24B or MiniMax M2.5 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Mistral Small 24B	MiniMax M2.5
Provider	NanoGPT	NanoGPT
Input / 1M tokens	$0.12	$0.30
Output / 1M tokens	$0.35	$1.20
Context window	33K	205K
Parameters	—	—
Open weights	Yes	Yes
Released	Jan 2025	Feb 2026

Mistral Small 24B details →MiniMax M2.5 details →

FAQ

Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.