Skip to content

MiniMax 2.5 vs GPT-OSS-120B

MiniMax 2.5 is cheaper on output tokens, while MiniMax 2.5 offers a larger context window. Choose MiniMax 2.5 or GPT-OSS-120B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

SpecMiniMax 2.5GPT-OSS-120B
ProviderRegolo AIRegolo AI
Input / 1M tokens$0.80$1.00
Output / 1M tokens$3.50$4.20
Context window190K128K
Parameters117B
Open weightsNoNo
ReleasedMar 2026Aug 2025

FAQ

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