LogoLMSpeed
  • Home
  • Free
  • Providers
  • Docs
LogoLMSpeed
LogoLMSpeed

The best API speed test tool

GitHubGitHubTwitterX (Twitter)Email
Product
  • Features
  • Pricing
  • FAQ
Leaderboard
  • Overview
  • Speed Ranking
  • Latency Ranking
  • Health Ranking
Models
  • All Models
  • GPT
  • Claude
  • Gemini
  • DeepSeek
  • Llama
  • Qwen
Free Models
  • All Free Models
  • Free GPT
  • Free Claude
  • Free Gemini
  • Free DeepSeek
  • Free Llama
  • Free Qwen
Resources
  • Speed Test
  • Provider Directory
  • Documentation
Legal
  • Cookie Policy
  • Privacy Policy
  • Terms of Service
© 2026 LMSpeed All Rights Reserved.Made by Nexmoe with ❤️
首页交流 QQ 群:1034193296,欢迎中转站站长加入讨论 AI 最热话题、newapi、openclaw 等,获取最新测速动态与反馈支持。
Back to models
publish

MiniMax-M2 API Pricing & Performance

minimax-m2

Also known as

MiniMax-M2MiniMax-M2-PreviewMiniMaxAI/MiniMax-M2minimax-m2minimax/minimax-m2

MiniMax-M2 is available through 40 API providers on LMSpeed. Compare API pricing from $0.0010 to $75.00 per million input tokens across providers. Free API access is offered by 1 provider. In speed benchmarks, the fastest provider reaches 64 tok/s.

Avg speed
48.30t/s
First token
10.12s
Total tests
35
Providers
40
Variants
47

Pricing Comparison

Compare MiniMax-M2 API pricing across 39 providers. Input prices range from $0.0010 to $75.00 per million input. Medu Chat offers the lowest rate at $0.0010/M.

ProviderModel VariantInput ($/M)Output ($/M)Speed (t/s)
wuer的api站Minimaxminimaxai/minimax-m2FreeFree—
Medu ChatMinimaxminimax-m2$0.0010$0.0010—
素墨APIMinimaxminimax-m2$0.010$0.010—
素墨APIMinimaxminimax/minimax-m2:free$0.010$0.010—
CookingAIMinimaxminimax-m2$0.010$0.010—
紫脑喵Minimaxminimax-m2$0.010$0.010—
Seamee APIMinimaxMiniMax-M2$0.170$1.53—
SMLC666 APIMinimaxminimax-m2$0.200$1.00—
Yuan APIMinimaxMiniMax-M2$0.200$0.200—
Seamee APIMinimaxminimax/minimax-m2$0.255$1.00—
OpenRouter FansMinimaxminimax/minimax-m2$0.255$1.00—
EasyMoreMinimaxMiniMax-M2$0.288$1.15—
352287 APIMinimaxMiniMax-M2$0.300$1.20—
Meta APIMinimaxMiniMaxAI/MiniMax-M2$0.372$1.49—
Seamee APIMinimaxminimax-m2$0.390$1.57—
蜜音AIMinimaxMiniMax-M2$0.630$2.52—
DuckDuck APIMinimaxminimax-m2$0.900$3.60—
SynapseMinimaxMiniMaxAI/MiniMax-M2$1.00$1.00—
SynapseMinimaxminimaxai/minimax-m2$1.00$1.00—
国产大模型 APIMinimaxminimax-m2$1.00$1.00—
Showing 20 of 40 providers.

Pricing data from provider public APIs

Free MiniMax-M2 API Tier & Credits

MiniMax-M2 is free to use through 1 provider with no per-token charges. These providers offer free API credits or a free tier:

ProviderSpeed (t/s)
wuer的api站—

API Speed Benchmarks by Provider

Compare speed and latency performance across all API providers.

Showing 1-2 of 2 providers

Most testedRecently testedA–Z
ProviderSpeedLatencyTests
SkyAISkyAI

minimax/minimax-m2

63.58 tok/s
12.69s
20
SCNET

MiniMax-M2

27.93 tok/s
6.68s
15

Recent API Speed Tests

20 records

Latest benchmark results measuring API response speed and first-token latency.

TimeModelSpeedLatency
02/14/2026, 03:59
MinimaxMiniMax-M2
29.48 tok/s
1.27s
02/14/2026, 03:59
MinimaxMiniMax-M2
28.17 tok/s
0.84s
02/14/2026, 03:59
MinimaxMiniMax-M2
27.96 tok/s
0.50s
02/14/2026, 03:59
MinimaxMiniMax-M2
29.17 tok/s
1.21s
02/14/2026, 03:59
MinimaxMiniMax-M2
25.31 tok/s
3.20s
02/14/2026, 03:25
MinimaxMiniMax-M2
27.34 tok/s
13.51s
02/14/2026, 03:25
MinimaxMiniMax-M2
25.71 tok/s
0.62s
02/14/2026, 03:25
MinimaxMiniMax-M2
27.69 tok/s
0.61s
02/14/2026, 03:25
MinimaxMiniMax-M2
29.66 tok/s
0.63s
02/14/2026, 03:25
MinimaxMiniMax-M2
29.53 tok/s
0.65s
02/06/2026, 13:14
MinimaxMiniMax-M2
28.59 tok/s
23.10s
02/06/2026, 13:14
MinimaxMiniMax-M2
26.51 tok/s
3.96s
02/06/2026, 13:14
MinimaxMiniMax-M2
26.10 tok/s
6.53s
02/06/2026, 13:14
MinimaxMiniMax-M2
28.13 tok/s
19.75s
02/06/2026, 13:14
MinimaxMiniMax-M2
29.62 tok/s
23.79s
11/09/2025, 01:28
Minimaxminimax/minimax-m2
81.31 tok/s
5.08s
11/09/2025, 01:28
Minimaxminimax/minimax-m2
74.47 tok/s
11.01s
11/09/2025, 01:28
Minimaxminimax/minimax-m2
81.15 tok/s
9.35s
11/09/2025, 01:28
Minimaxminimax/minimax-m2
80.40 tok/s
4.85s
11/09/2025, 01:28
Minimaxminimax/minimax-m2
94.27 tok/s
6.92s
See all free LLM models →

Frequently Asked Questions

Is MiniMax-M2 API free?
Yes, MiniMax-M2 is available for free through 1 API provider on LMSpeed, including wuer的api站. These providers offer free API credits or a free tier with no per-token charges.
How much does MiniMax-M2 API cost?
MiniMax-M2 API pricing ranges from $0.0010 to $75.00 per million input tokens across 40 providers. Medu Chat offers the cheapest rate at $0.0010/M. Output pricing varies by provider.
Which provider has the cheapest MiniMax-M2 API pricing?
The cheapest MiniMax-M2 API pricing is offered by Medu Chat at $0.0010 per million input tokens. Compare all 40 providers above to find the best pricing per token for your use case.

Alternatives & Similar Models

DeepSeek
DeepSeek V3.2deepseek-v3-2
37 shared providers
Gemini
Gemini 3 Flashgemini-3-flash
34 shared providers
DeepSeek
DeepSeek V3deepseek-v3
33 shared providers
DeepSeek
DeepSeek R1deepseek-r1
33 shared providers
Gemini
Gemini 2.5 Progemini-2-5-pro
33 shared providers
DeepSeek
DeepSeek V3.1deepseek-v3-1
33 shared providers