Log in
← All models

MiniMax M3

Balanced

An open-weight model built for agents — strong tool use with a 1M context at low cost.

MiniMax
Maker
85/100
Overall
80
Value score
$0.57
Blended /1M
1.0M
Context
Open
Weights
Pricing: $0.30 in · $1.20 out / 1M tokens · synced from OpenRouter · updated 2026-06-22

Scorecard

Output Quality8.4/10 · 74% community
Agentic Ability8.7/10 · 76% community
Speed7.8/10 · 72% community
Value for $9.1/10 · 78% community
Reliability8.6/10 · 75% community

MiniMax M3 is the latest in MiniMax's agent-focused open-weight line, which earned a following for reliable tool use and long-horizon tasks. It carries a 1M-token context at a low price, making it a strong open backbone for autonomous agents.

Strengths
  • Built for agentic tool use
  • 1M context
  • Open weights, low cost
Trade-offs
  • Below frontier on raw quality
  • Newer, less battle-tested than V3.2/GLM

Agents that run MiniMax M3 well

Open-weight autonomous agents that lean on tool use.

Best model for OpenClawBest model for HermesBest model for ClineBest model for OpenCodeBest model for Aider

MiniMax M3 FAQ

Is MiniMax M3 good for AI agents?
Open-weight autonomous agents that lean on tool use. On our editorial scoring it rates 8.7/10 for agentic ability and 8.4/10 for output quality. Built for agentic tool use.
How much does MiniMax M3 cost?
Via OpenRouter, MiniMax M3 is priced at $0.30 in · $1.20 out / 1M tokens — a blended rate of about $0.57 per 1M tokens for typical input-heavy agent use.
What is MiniMax M3's context window?
MiniMax M3 has a 1.0M-token context window — large enough to hold sizeable codebases or document sets in a single run. MiniMax is the maker.
Is MiniMax M3 open source?
Yes — MiniMax M3 ships with open weights, so you can self-host it for privacy or run it through a hosted provider like OpenRouter. That openness is a big reason it's popular in open agent stacks.
What are the downsides of MiniMax M3?
The main trade-offs: below frontier on raw quality; newer, less battle-tested than v3.2/glm. It's strongest for open-weight autonomous agents that lean on tool use.

MiniMax M3 compared

MiniMax M3 vs Sonnet 4.6MiniMax M3 vs GPT-5.4MiniMax M3 vs Gemini 3.5 FlashMiniMax M3 vs GPT-5.3-CodexMiniMax M3 vs Kimi K2.7 CodeMiniMax M3 vs Qwen3.7 PlusMiniMax M3 vs Devstral 2MiniMax M3 vs GLM 4.7

The model is half the story — the agent is the other half

The model picks the moves; the agent runs the loop, the tools, and the guardrails. Once you've chosen a model, see which agent gets the most out of it.

Compare AI agents →