MiniMax models & pricing

MiniMax hosts 9 models (5 with public pricing) covering 2 modalities. MiniMax M2 reasoning, abab chat, and speech models. Cheapest input starts at $0.300/M tokens; the most premium goes up to $0.300/M. Use Future AGI's Agent Command Center to route any MiniMax model with cost-optimized fallback and unified observability.

Homepage ↗ Docs ↗

chat 5

Model Input / 1M Output / 1M Context Caps
Minimax M2 $0.300/M $1.20/M 200,000 tools · reasoning · cache
Minimax M2.1 $0.300/M $1.20/M 1,000,000 tools · reasoning · cache
Minimax M2.1 Lightning $0.300/M $2.40/M 1,000,000 tools · reasoning · cache
Minimax M2.5 $0.300/M $1.20/M 1,000,000 tools · reasoning · cache
Minimax M2.5 Lightning $0.300/M $2.40/M 1,000,000 tools · reasoning · cache

audio speech 4

Model Input / 1M Output / 1M Context Caps
Speech 02 Hd
Speech 02 Turbo
Speech 2.6 Hd
Speech 2.6 Turbo

FAQ

How many MiniMax models are there?

9 MiniMax models are listed across 2 modalities on this page. 5 have public per-token pricing.

How is MiniMax pricing verified?

Pricing is aggregated from BerriAI/litellm, models.dev, and OpenRouter and refreshed weekly. Each row shows a per-model "verified" date. If a price is wrong, click the row to open the model page and use the inline "suggest edit" link — submissions go into a public review queue.

Which MiniMax model is cheapest?

Input pricing on MiniMax starts at $0.300 per 1M tokens. Sort the table by price (or use the in-page filter at the top) to find the cheapest model that matches your capability requirements.

Can I route to MiniMax via an OpenAI-compatible API?

Yes — point your OpenAI client at Future AGI's Agent Command Center, configure a MiniMax target, and call MiniMax models with the standard /v1/chat/completions surface. The same gateway can route to other providers as fallback. Free for the first 100K requests/month.

Route any MiniMax model via Agent Command Center →
OpenAI-compatible endpoint. Caching, fallback, guardrails, observability. Free for 100K requests/month.