Is Mistral Medium 3.5 Thinking or MiniMax M2.5 cheaper?

MiniMax M2.5 is cheaper on output tokens ($1.20 vs $7.50 per 1M).

Which has the larger context window, Mistral Medium 3.5 Thinking or MiniMax M2.5?

Mistral Medium 3.5 Thinking has the larger context window (256K tokens).

Mistral Medium 3.5 Thinking vs MiniMax M2.5

MiniMax M2.5 is cheaper on output tokens, while Mistral Medium 3.5 Thinking offers a larger context window. Choose Mistral Medium 3.5 Thinking or MiniMax M2.5 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Mistral Medium 3.5 Thinking	MiniMax M2.5
Provider	NanoGPT	NanoGPT
Input / 1M tokens	$1.50	$0.30
Output / 1M tokens	$7.50	$1.20
Context window	256K	205K
Parameters	—	—
Open weights	Yes	Yes
Released	Apr 2026	Feb 2026

Mistral Medium 3.5 Thinking 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.