MiniMax M3

minimax/minimax-m3
by MiniMax·Text·1000K context·Released 2026-04-22·Proprietary
long-context

Overview

MiniMax's efficient long-context model with a launch-priced cheap input tier and a million-token context window. Strong at long-document reasoning and retrieval, increasingly used for agents that need to hold a lot of state. Hosted with growing provider coverage.

Benchmarks

Standardized scores (0–100), normalized across the catalog.

Intelligence78
Coding79
Instruction following87

Providers

LLMRouteHub routes to the cheapest healthy provider by default. Showing the top 1 of 3 providers by routed volume.

ProviderInputOutputThroughputUptime
MiniMax$0.30$1.1084 tok/s99.4%

Use this model

curl https://llmroutehub.com/api/v1/chat/completions \
  -H "Authorization: Bearer $LLMROUTEHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax/minimax-m3",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'