Skip to content

GPT-OSS-120B vs MiniMax 2.5

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

SpecGPT-OSS-120BMiniMax 2.5
ProviderRegolo AIRegolo AI
Input / 1M tokens$1.00$0.80
Output / 1M tokens$4.20$3.50
Context window128K190K
Parameters117B
Open weightsNoNo
ReleasedAug 2025Mar 2026

FAQ

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