Skip to content
OpenSmartRoute
All vendors
MiniMax

Vendor

MiniMax models

10 models in the reference catalogue, vendor list prices per million tokens. 0 are routable on this deployment today.

Models

10

0 routable here

Cheapest (blended)

free

MiniMax M3 (free)

Median list price

$0.50

3:1 input to output per 1M tokens

Strongest

MiniMax M3

intelligence index 36

Every MiniMax model

Newest first. Prices are the vendor's published rates per million tokens; click a model for the full specification.

ModelReleasedContextInput / 1MOutput / 1MIntelligenceCapabilities
MiniMax M3minimax/minimax-m3May 31, 20261.0M$0.30$1.2036
reasoning tools open weights
MiniMax M3 (free)minimax/minimax-m3:freeMay 31, 20261.0Mfreefree36
reasoning tools open weights
MiniMax M2.7minimax/minimax-m2.7Mar 18, 2026205K$0.30$1.20-
reasoning tools open weights
MiniMax M2.7 (free)minimax/minimax-m2.7:freeMar 18, 2026197Kfreefree-
reasoning tools open weights
MiniMax M2.5minimax/minimax-m2.5Feb 12, 2026205K$0.27$1.08-
reasoning tools open weights
MiniMax M2-herminimax/minimax-m2-herJan 23, 202666K$0.30$1.20-
MiniMax M2.1minimax/minimax-m2.1Dec 23, 2025205K$0.30$1.20-
reasoning tools open weights
MiniMax M2minimax/minimax-m2Oct 23, 2025205K$0.26$1.02-
reasoning tools open weights
MiniMax M1minimax/minimax-m1Jun 17, 20251M$0.55$2.20-
reasoning tools
MiniMax-01minimax/minimax-01Jan 15, 20251.0M$0.20$1.10-
open weights

Frequently asked

What is the cheapest MiniMax model?
MiniMax M3 (free) at free per 1M input tokens and free per 1M output tokens (vendor list price).
Which MiniMax model has the largest context window?
MiniMax M3 accepts 1.0M tokens of context.
How do I route to MiniMax models with OpenSmartRoute?
Declare a target in targets.yaml with metadata.model set to the catalogue id (for example minimax/minimax-m3); the router scores it against every other target on cost, quality, latency and your policies for each request.

Route MiniMax with everything else

OpenSmartRoute picks the cheapest model that meets your quality bar per request, so a MiniMax flagship handles hard prompts while small models take the rest. Price a workload or try a routing decision live.