MiniMax M3
MiniMax M3Alternatives?
CheaperGLM 5.3 FlashunstatedOpenwins 54%-55%$0.15 / $0.50Defaults to max · Self-hosted+4
BetterGPT-5.6 Terraxhighwins 53%+757%$0.63Prompts with >272K input tokensOpenGLM 5.2maxwins 57%+310%$1.47Memory (4-bit): 256 GB → 452 GB+1
CheaperHy3unstatedOpenwins 52%-56%$0.13 / $0.53Context: 524K → 256K+1
CheaperGemma 4 31BunstatedOpensame-70%$0.10 / $0.34Context: 524K → 256KGLM 5.3 FlashunstatedOpenwins 54%-55%$0.15 / $0.50Defaults to max · Self-hosted+4Hy3unstatedOpenwins 52%-56%$0.13 / $0.53Context: 524K → 256K+1Gemma 4 31BunstatedOpensame-70%$0.10 / $0.34Context: 524K → 256KGPT-6 Lunamaxsame-62%$0.068Function calling only with none · Chat Completions+3GPT-5.6 Lunaxhighsame-14%$0.085GPT-5.6 Terraxhighwins 53%+757%$0.63Prompts with >272K input tokensGPT-6.1 Solmaxwins 58%+662%$0.72Remove unsupported parameters+5
Muse Spark 1.2xhighwins 56%+281%$0.97Only auto tool_choice is supported+1GPT-6 Solmaxwins 55%+662%$1.04GPT-5.6 Solxhighwins 59%+1,424%$1.18GLM 5.2maxOpenwins 57%+310%$1.47Memory (4-bit): 256 GB → 452 GB+1GLM 5.3maxOpenwins 57%+310%$2.01Memory (4-bit): 256 GB → 452 GB+5GLM 5unstatedOpenwins 56%+195%$1 / $3.20Context: 524K → 203K+2GLM 5.1unstatedOpenwins 56%+310%$1.40 / $4.40Context: 524K → 203K+2
MiMo v2.6 ProunstatedOpenwins 56%+4%$0.43 / $0.87Memory (4-bit): 256 GB → 615 GB+4MiniMax M2.7unstatedOpenwins 44%—$0.30 / $1.20Context: 524K → 205K+1MiniMax M2.5unstatedOpenwins 43%—$0.30 / $1.20Context: 524K → 205K+1MiniMax M1unstatedOpenwins 38%—$0.40 / $2.20Memory (4-bit): 256 GB → 274 GB+1MiniMax M2unstatedOpenwins 33%—$0.30 / $1.20Context: 524K → 205K+1MiniMax M2.1thinkingOpenn/a—$0.30 / $1.20Context: 524K → 205K+1MiniMax M1 40kOpenn/a——Memory (4-bit): 256 GB → 274 GB+1MiniMax M1 80kOpenn/a—$0.55 / $2.20Memory (4-bit): 256 GB → 274 GB+1MiniMax M2-herunstatedn/a—$0.30 / $1.20Context: 524K → 66K+1All MiniMax models →Run it yourself
estimateHistory
6 versionsWatch out 1
Deployment status experimental · Self-hosted›
The documented MiniMax M3 baseline uses an experimental SGLang development image; pin its model revision and image digest and validate your workload. Source ↗
FAQ
How much does MiniMax M3 cost?›
$0.30 per 1M input tokens and $1.20 per 1M output tokens; cached input $0.06 per 1M; cheapest via CoreWeave at $0.23 / $0.96. A typical benchmark task costs about $0.51 at default effort.
Is MiniMax M3 free to use?›
There is no free API; the cheapest paid price is $0.23 per 1M input tokens. The weights are open, so you can run it yourself.
How good is MiniMax M3, and what is it best at?›
#49 of 334 in Chat & Knowledge, #49 of 132 in Coding, #58 of 133 in Agents & Tool Use, #62 of 195 in Writing & Language, #29 of 124 in Vision & Documents. Strongest at: Tool calling, Reasoning, Science, Long context, Knowledge, Instructions, Vision.
Is MiniMax M3 better than MiniMax M2.7?›
On Arena Text · creative writing, MiniMax M3 scores 1,405 vs 1,364 — higher.
How can I use MiniMax M3?›
Through the API of CoreWeave, DeepInfra, Featherless, Mara, Minimax and 6 more.
What is the context window of MiniMax M3?›
524K tokens, with up to 512K output tokens.
When was MiniMax M3 released? Is there a newer version?›
Released 2026-06-01. It is the current version in its line.
Is MiniMax M3 open source?›
Yes, the weights are open (minimax-community licence).
Can I run MiniMax M3 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can MiniMax M3 read images?›
It accepts text and images, video as input.
What is MiniMax M3?›
MiniMax M3 is an open-weights language model from MiniMax, released Jun 2026, the successor to MiniMax M2.7.
What are the best alternatives to MiniMax M3?›
GLM 5.3 Flash (cheaper), GPT-5.6 Terra (better), GLM 5.2 (open weights).