MiniMax M2.5
MiniMax M2.5Rankingin thinking mode?
Alternatives?
CheaperClaude Haiku 5.5max+90%-62%$0.21Remove sampling parameters+5
BetterGPT-5.6 Lunamedium+10%-14%$0.016
OpenGLM 5.3 Flashmax+83%-55%$0.28Memory (4-bit): 137 GB → 193 GB+5CheaperMiniMax M3.1 Flashthinking+87%-50%$0.22Complete model response must be appended
CheaperLing 3.1 FlashOpen+80%-14%$1.00Memory (4-bit): 137 GB → 343 GBClaude Haiku 5.5max+90%-62%$0.21Remove sampling parameters+5MiniMax M3.1 Flashthinking+87%-50%$0.22Complete model response must be appendedGLM 5.3 FlashmaxOpen+83%-55%$0.28Memory (4-bit): 137 GB → 193 GB+5Ling 3.1 FlashOpen+80%-14%$1.00Memory (4-bit): 137 GB → 343 GB
Qwen3.8 FlashthinkingOpen+75%-56%$0.37max_tokens range · QwenCloud+5GPT-5.6 Lunamedium+10%-14%$0.016GPT-6 Lunamedium+31%-62%$0.017Function calling only with none · Chat Completions+3Claude Haiku 5.5low+29%-62%$0.024Remove sampling parameters+5
MiMo v2.5 ProthinkingOpen+14%+4%$0.054Memory (4-bit): 137 GB → 614 GBMiMo v2.6 FlashthinkingOpen+66%-67%$0.062Memory (4-bit): 137 GB → 186 GB+4GLM 5.3 FlashmaxOpen+83%-55%$0.28Memory (4-bit): 137 GB → 193 GB+5Qwen3.8 FlashthinkingOpen+75%-56%$0.37max_tokens range · QwenCloud+5MiMo v2.6 FlashthinkingOpen+66%-67%$0.062Memory (4-bit): 137 GB → 186 GB+4Qwen3.8 27BxhighOpen+48%+82%$1.01max_tokens range · QwenCloud+4MMotif 3Open+47%+67%$0.50 / $2Memory (4-bit): 137 GB → 189 GBMiniMax M3.1 Flashthinking+87%—$0.22Complete model response must be appendedMiniMax M3thinkingOpen+28%—$0.51Memory (4-bit): 137 GB → 256 GB+2MiniMax M2.7thinkingOpensame—$0.30 / $1.20MiniMax M2.1thinkingOpen-8%—$0.30 / $1.20MiniMax M2thinkingOpen-18%—$0.30 / $1.20MiniMax M1 80kOpen-49%—$0.55 / $2.20Memory (4-bit): 137 GB → 274 GBMiniMax M1 40kOpen-56%——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 M2.5 cost?›
$0.30 per 1M input tokens and $1.20 per 1M output tokens; cached input $0.03 per 1M; cheapest via Azure AI Foundry at $0.033 / $1.32.
Is MiniMax M2.5 free to use?›
There is no free API; the cheapest paid price is $0.033 per 1M input tokens. The weights are open, so you can run it yourself.
How good is MiniMax M2.5, and what is it best at?›
#122 of 334 in Chat & Knowledge, #74 of 97 in Coding, #18 of 242 in Agents & Tool Use, #98 of 195 in Writing & Language. Strongest at: Tool calling, Instructions.
Is MiniMax M2.5 better than MiniMax M2.1?›
On AA Intelligence Index 4.3.2, MiniMax M2.5 scores 22.8 vs 20.9 — higher.
How can I use MiniMax M2.5?›
Through the API of AWS Bedrock, AtlasCloud, Azure AI Foundry, DeepInfra, DigitalOcean and 4 more.
What is the context window of MiniMax M2.5?›
205K tokens, with up to 131K output tokens.
When was MiniMax M2.5 released? Is there a newer version?›
Released 2026-02-12. It has been superseded by MiniMax M2.7.
Is MiniMax M2.5 open source?›
Yes, the weights are open (modified-mit licence).
Can I run MiniMax M2.5 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can MiniMax M2.5 read images?›
No, it accepts text only.
What is MiniMax M2.5?›
MiniMax M2.5 is an open-weights language model from MiniMax, released Feb 2026, the successor to MiniMax M2.1.
What are the best alternatives to MiniMax M2.5?›
Claude Haiku 5.5 (cheaper), GPT-5.6 Luna (better), GLM 5.3 Flash (open weights).