Minimax

MiniMax: MiniMax M2.1

Chat
minimax/minimax-m2.1
CompareGet Started

MiniMax M2.1 is MiniMax's lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world capability while maintaining exceptional latency, scalability, and cost efficiency. Capabilities include reasoning, function calling, prompt caching, and web search. Context: 200K tokens, output: 131K. Pricing is $0.30/M input and $1.20/M output tokens, with cached input reads at $0.03/M. Available via OpenAI and Anthropic protocols.

Context Window
205K
Max Output Tokens
131K
Released
2025-12-23
Capabilities
Function CallingReasoningPrompt CachingWeb Search
Available Providers
BaiLianAliyun
Supported Protocols
OpenAIopenaiAnthropicanthropic

Providers

BaiLianAliyun
Input Tokens
$0.3/M
Output Tokens
$1.2/M
Cache Read
$0.06/M
Cache Write
$0/M
$0.375/M
Web Search
$0.01/R
Protocols
OpenAIopenai/v1/chat/completions
Anthropicanthropic

Code Examples

from openai import OpenAI
client = OpenAI(
base_url="https://api.ofox.run/v1",
api_key="YOUR_OFOX_API_KEY",
)
response = client.chat.completions.create(
model="minimax/minimax-m2.1",
messages=[
{"role": "user", "content": "Hello!"}
],
)
print(response.choices[0].message.content)

Benchmarks

LMArenaEvaluated as minimax-m2.1-preview

MiniMax: MiniMax M2.1 scores 1384 in the Overall category of the LMArena text leaderboard (style control), ranking #147 of 374 models based on 17,095 human preference votes (updated 2026-07-12).

Benchmark scores for minimax-m2.1-preview on LMArena
CategoryArena Score95% CIRankVotes
Overall138413791390#147 of 37417,095
Hard Prompts140714001414#142 of 3749,046
Coding143914291449#131 of 3693,422
Math139313741411#138 of 3621,002
Creative Writing134613341357#147 of 3722,710
Instruction Following138513761394#132 of 3744,458
Chinese141413931435#135 of 344821

Source: LMArena · CC BY 4.0 · Updated 2026-07-12 · Methodology · Ranks compare models within each category of the LMArena text leaderboard (style control). Scores come from third-party human preference evaluations, not from OFOX.

Frequently Asked Questions

MiniMax: MiniMax M2.1 on Ofox.ai costs $0.3/M per million input tokens and $1.2/M per million output tokens. Pay-as-you-go, no monthly fees.