Polarison

MiniMax · open weights

MiniMax M3 API pricing by provider

MiniMax M3 is available from 13 providers. The cheapest is CoreWeave at $0.23 input / $0.96 output per 1M tokens (FP4). MiniMax’s own API charges $0.30 / $1.20, 21% more than the cheapest host. The priciest host, ModelRun, charges 3.2x the cheapest.

Prices from the OpenRouter API, retrieved September 15, 2026. Weights: MiniMaxAI/Minimax-M3.

ProviderPrecisionInput / 1MOutput / 1MDocument Q&A / monthContextMax output
CoreWeavefp4$0.23$0.96$120.80262K236K
GMICloudfp8$0.24$0.96$124.801.05M524K
DeepInfrafp8$0.28$1.10$145.00524K512K
StreamLakefp8$0.30$1.20$156.001M512K
Venicefp8$0.30$1.20$156.00524K66K
Together—$0.30$1.20$156.00524K472K
Parasailfp8$0.30$1.20$156.001.05M524K
AtlasCloudfp8$0.30$1.20$156.00524K524K
Novitafp8$0.30$1.20$156.001M131K
Minimaxcreatorfp8$0.30$1.20$156.00524K512K
Mara—$0.60$2.40$312.001.05M944K
SambaNova—$0.60$2.40$312.001.05M944K
ModelRunfp4$0.75$3.00$390.001.05M944K

Sorted by blended price (3 input : 1 output). Document Q&A assumes 50,000 questions a month with 8,000 input and 600 output tokens each. Precision is reported by the provider; “—” means not disclosed.

Frequently asked questions

What is the cheapest MiniMax M3 API provider?
CoreWeave is the cheapest healthy provider we track at $0.23 per 1M input tokens and $0.96 per 1M output tokens.
How much does MiniMax M3 cost?
Across 13 providers, input prices range from $0.23 to $0.75 per 1M tokens and output prices from $0.96 to $3.00.
What is MiniMax M3’s context window?
MiniMax M3 supports up to 1.05M tokens, but some providers serve a smaller context window — check the table before choosing.

Other open-weight models