MiniMax: MiniMax M3

Chat
minimax/minimax-m3

MiniMax-M3 is MiniMax's flagship reasoning model from the official channel (api.minimaxi.com), featuring a 1M-token context window and 131K output. It embeds adaptive thinking and excels at complex reasoning, coding, and long-context tasks. Available via OpenAI-compatible and Anthropic protocols through Ofox.

Context Window
1M
Max Output Tokens
131K
Released
2026-06-01
Capabilities
VisionFunction CallingReasoningPrompt CachingWeb Search
Available Providers
MiniMax
Supported Protocols
openaianthropic

Providers

MiniMaxprovider.type: "minimax"
Input Tokens
$0.6/M
Output Tokens
$2.4/M
Cache Read
$0.12/M
Protocols
openai/v1/chat/completions/v1/responses
anthropic

Code Examples

from openai import OpenAI
client = OpenAI(
base_url="https://api.ofox.io/v1",
api_key="YOUR_OFOX_API_KEY",
)
response = client.chat.completions.create(
model="minimax/minimax-m3",
messages=[
{"role": "user", "content": "Hello!"}
],
)
print(response.choices[0].message.content)

Benchmarks

LMArena ↗Evaluated as minimax-m3

MiniMax: MiniMax M3 scores 1445 in the Overall category of the LMArena text leaderboard (style control), ranking #59 of 374 models based on 24,588 human preference votes (updated 2026-07-12).

Benchmark scores for minimax-m3 on LMArena
CategoryArena Score95% CIRankVotes
Overall14451440–1451#59 of 37424,588
Hard Prompts14661459–1472#57 of 37416,287
Coding15001492–1508#50 of 3697,179
Math14441427–1462#52 of 3621,163
Creative Writing14061396–1417#70 of 3723,934
Instruction Following14381431–1446#54 of 3748,188
Chinese14751455–1494#74 of 3441,081

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.

Further Reading on MiniMax M3

Frequently Asked Questions

MiniMax: MiniMax M3 on Ofox.ai costs $0.6 per million input tokens and $2.4 per million output tokens. Pay-as-you-go, no monthly fees.