MiniMax M2.1
MiniMax M2.1Rankingin thinking mode?
Alternatives?
CheaperClaude Haiku 5.5max×2.1-62%$0.21Remove sampling parameters+5
BetterGPT-5.6 Lunamedium+20%-14%$0.016
OpenGLM 5.3 Flashmax+100%-55%$0.28Memory (4-bit): 137 GB → 193 GB+5CheaperMiniMax M3.1 Flashthinking×2-50%$0.22Complete model response must be appended
CheaperLing 3.1 FlashOpen+96%-14%$1.00Memory (4-bit): 137 GB → 343 GBClaude Haiku 5.5max×2.1-62%$0.21Remove sampling parameters+5MiniMax M3.1 Flashthinking×2-50%$0.22Complete model response must be appendedGLM 5.3 FlashmaxOpen+100%-55%$0.28Memory (4-bit): 137 GB → 193 GB+5Ling 3.1 FlashOpen+96%-14%$1.00Memory (4-bit): 137 GB → 343 GB
Qwen3.8 FlashthinkingOpen+90%-56%$0.37max_tokens range · QwenCloud+5GPT-5.6 Lunamedium+20%-14%$0.016GPT-6 Lunamedium+43%-62%$0.017Function calling only with none · Chat Completions+3Claude Haiku 5.5low+41%-62%$0.024Remove sampling parameters+5
MiMo v2.5 ProthinkingOpen+24%+4%$0.054Memory (4-bit): 137 GB → 614 GBMiMo v2.6 FlashthinkingOpen+81%-67%$0.062Memory (4-bit): 137 GB → 186 GB+4GLM 5.3 FlashmaxOpen+100%-55%$0.28Memory (4-bit): 137 GB → 193 GB+5Qwen3.8 FlashthinkingOpen+90%-56%$0.37max_tokens range · QwenCloud+5MiMo v2.6 FlashthinkingOpen+81%-67%$0.062Memory (4-bit): 137 GB → 186 GB+4Qwen3.8 27BxhighOpen+61%+82%$1.01max_tokens range · QwenCloud+4MMotif 3Open+60%+67%$0.50 / $2Memory (4-bit): 137 GB → 189 GBMiniMax M3.1 Flashthinking×2—$0.22Complete model response must be appendedMiniMax M3thinkingOpen+40%—$0.51Memory (4-bit): 137 GB → 256 GB+2MiniMax M2.5thinkingOpen+9%—$0.30 / $1.20MiniMax M2.7thinkingOpen+9%—$0.30 / $1.20MiniMax M2thinkingOpen-11%—$0.30 / $1.20MiniMax M1 80kOpen-44%—$0.55 / $2.20Memory (4-bit): 137 GB → 274 GBMiniMax M1 40kOpen-52%——Memory (4-bit): 137 GB → 274 GBMiniMax M1unstatedOpenn/a—$0.40 / $2.20Memory (4-bit): 137 GB → 274 GB+1All MiniMax models →Run it yourself
estimateHistory
6 versionsBenchmarks
all categoriesFAQ
How much does MiniMax M2.1 cost?›
$0.30 per 1M input tokens and $1.20 per 1M output tokens; cached input $0.03 per 1M; cheapest via DeepInfra at $0.27 / $0.95.
Is MiniMax M2.1 free to use?›
There is no free API; the cheapest paid price is $0.27 per 1M input tokens. The weights are open, so you can run it yourself.
How good is MiniMax M2.1, and what is it best at?›
#107 of 334 in Chat & Knowledge, #62 of 239 in Coding, #62 of 242 in Agents & Tool Use, #54 of 95 in Writing & Language. Strongest at: Instructions.
Is MiniMax M2.1 better than MiniMax M2?›
On AA Intelligence Index 4.3.2, MiniMax M2.1 scores 20.9 vs 18.6 — higher.
How can I use MiniMax M2.1?›
Through the API of AWS Bedrock, DeepInfra, Featherless, Minimax.
What is the context window of MiniMax M2.1?›
205K tokens, with up to 131K output tokens.
When was MiniMax M2.1 released? Is there a newer version?›
Released 2025-12-23. It has been superseded by MiniMax M2.5.
Is MiniMax M2.1 open source?›
Yes, the weights are open (modified-mit licence).
Can I run MiniMax M2.1 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can MiniMax M2.1 read images?›
No, it accepts text only.
What is MiniMax M2.1?›
MiniMax M2.1 is an open-weights language model from MiniMax, released Dec 2025, the successor to MiniMax M2.
What are the best alternatives to MiniMax M2.1?›
Claude Haiku 5.5 (cheaper), GPT-5.6 Luna (better), GLM 5.3 Flash (open weights).