MiniMax M2 API Benchmarks, Pricing & Provider Data
Compare MiniMax M2 with another model
Choose a model to open its comparison page.
MiniMax M2 benchmark, API pricing, and provider data cover 108 API providers, with prices starting at $0.010/request. The page also shows measured API speed and first-token latency.
MiniMax M2 is a compact MoE language model (230B total, 10B active parameters) built for coding and agentic workflows, delivering strong tool use, reasoning, and high-throughput inference at low cost.
Category Performance
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
- Coverage
- 3 / 8
- Methodology
- V3.0
#1Coding53.4Provisional1/4 Measured dimensions
#2Reasoning52.1Estimated2/4 Measured dimensions
#3Math50.9Provisional1/4 Measured dimensions
Specifications
Input and output token limits for this model, plus how it ranks on long-context understanding.
Features
Technical Details
- Input
- Output
- Released
- Oct 2025
- Tokenizer
- Other
- Architecture
- text->text
- Moderated
- No
- Supported parameters
- frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Rankings
Excels at
Detailed scores
Updated: Aug 31, 2026Pricing
undefined metric} other undefined metrics}}
Input price$0.300/M#54 / 180Output price$1.20/M#49 / 180
Pricing
undefined metric} other undefined metrics}}
Agents
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Agents
V3.0undefined metric} other undefined metrics}} · No data
Coding
V3.0undefined metric} other undefined metrics}} · Provisional
Score53.480% interval39.5–67.31/4 Measured dimensionsLiveCodeBench82.6%#14 / 115SciCode36.1%#119 / 205
Coding
V3.0undefined metric} other undefined metrics}} · Provisional
Reasoning
V3.0undefined metric} other undefined metrics}} · Estimated
Score52.180% interval40.9–63.22/4 Measured dimensionsMMLU-Pro82.0%#50 / 129GPQA77.7%#104 / 212
Reasoning
V3.0undefined metric} other undefined metrics}} · Estimated
Knowledge
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Knowledge
V3.0undefined metric} other undefined metrics}} · No data
Math
V3.0undefined metric} other undefined metrics}} · Provisional
Score50.980% interval34.8–67.11/4 Measured dimensions
Math
V3.0undefined metric} other undefined metrics}} · Provisional
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
Multimodal
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Multimodal
V3.0undefined metric} other undefined metrics}} · No data
Instruction following
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Instruction following
V3.0undefined metric} other undefined metrics}} · No data
OpenRouter endpoints
3 endpointsThird-party OpenRouter endpoint data, shown separately from LMSpeed measurements. Some 30-minute live performance fields only appear after syncing with an OpenRouter API key.
| Provider endpoint | Input | Output | 1d uptime | 30m latency | 30m throughput | Context / output |
|---|---|---|---|---|---|---|
Google google-vertex | $0.300/M | $1.20/M | 99.2% | — | — | undefined tokens / undefined tokens |
Novita novita/fp8 | $0.300/M | $1.20/M | 98.6% | — | — | undefined tokens / undefined tokens |
Minimax minimax/fp8 | $0.255/M | $1.02/M | 96.8% | — | — | undefined tokens / undefined tokens |
Pricing Comparison
Compare MiniMax M2 API pricing across 108 providers. Prices range from $0.010/request to $1698.30/M. 素墨API offers the lowest rate at $0.010/request.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | MiniMax-M2 | default | -52%$0.144/M | -52%$0.575/M | — | — | — | |
L1 100% | MiniMax-M2 | default | -4%$0.288/M | -4%$1.15/M | — | — | — | |
L1 100% | minimax-m2 | default | -4%$0.288/M | -4%$1.15/M | — | — | — | |
L1 100% | MiniMaxAI/MiniMax-M2 | default | $6.30/M | $25.20/M | — | — | — | |
L1 100% | MiniMax-M2 | default | -52%$0.144/M | -52%$0.575/M | — | — | — | |
L1 99% | MiniMax-M2 | other | -58%$0.125/M | -58%$0.500/M | — | — | — | |
L1 100% | MiniMax-M2 | default | -4%$0.288/M Cache read$0.029/MCache write$0.360/MCache write 1h$0.575/M | -4%$1.15/M | — | — | — | |
L1 99% | minimax-m2 | default | $6.00/request | - | — | — | — | |
L1 99% | MiniMax-M2 | default | -23%$0.230/M | -23%$0.921/M | — | — | — | |
L1 100% L2 77% | MiniMax-M2 | default | $2.10/M Cache read$0.210/MCache write$2.63/MCache write 1h$4.20/M | $8.40/M | — | — | — | |
L1 100% | MiniMax-M2 | default | $3.00/M | $12.00/M | — | — | — | |
L1 99% | minimax-m2 | default | -9%$0.274/M | -9%$1.10/M | — | — | — | |
L1 98% | MiniMax-M2 | default | $1.03/M Cache read$0.103/MCache write$1.28/MCache write 1h$2.06/M | $4.11/M | — | — | — | |
L1 100% | MiniMax-M2 | default | $2.10/M | $8.40/M | — | — | — | |
L1 99% | minimax-m2 | default | $1.60/M | $1.60/M | — | — | — | |
L1 100% | minimax/minimax-m2:free | default | $0.010/request | - | — | — | — | |
L1 99% | MiniMax-M2 | default | -11%$0.268/M | -11%$1.07/M | — | — | — | |
L1 99% | MiniMax-M2 | default | -11%$0.268/M | -11%$1.07/M | — | — | — | |
L1 99% | MiniMax-M2 | default | -4%$0.288/M | -4%$1.15/M | — | — | — | |
L1 100% | MiniMax-M2 | default | $0.575/M | $2.30/M | — | — | — |
Alternatives & Similar Models
MiniMax M2.5
minimax-m2-5
MiniMax M2.5 is MiniMax's flagship text model for coding and agents, with SOTA-level programming and agentic performance, improved token efficiency, and fast high-TPS API deployment.
Kimi K2.5
kimi-k2-5
Moonshot Kimi K2.5 is an open-weight multimodal agent model with native vision and text input, strong coding performance, and a 256K context window.
GLM-5
glm-5
Zhipu GLM-5 is Zhipu flagship GLM series model with enhanced reasoning, agent capabilities, and strong performance on Chinese enterprise and coding scenarios.
MiniMax M2.7
minimax-m2-7
MiniMax M2.7 is a high-tier M2-series model tuned for complex reasoning, long-context dialogue, and production-grade API workloads.
GLM-5.1
glm-5-1
Zhipu GLM-5.1 is a next-generation GLM model aimed at frontier reasoning, coding, and bilingual agent applications.
DeepSeek V3.2
deepseek-v3-2
DeepSeek V3.2 is an upgraded V3-series MoE model with stronger reasoning, coding, and math performance, widely available through OpenAI-compatible API relays.
Frequently Asked Questions
- What benchmark data does MiniMax M2 include?
- LMSpeed shows MiniMax M2 benchmark context, API price, output speed, first-token latency, and provider data across 108 providers when those signals are available.
- What is the MiniMax M2 API price?
- MiniMax M2 has pricing from 108 providers, ranging from $0.010/request to $1698.30/M. 素墨API has the lowest listed price.
- What does the MiniMax M2 API pricing table include?
- The MiniMax M2 API pricing table compares 108 providers by input price, output price, free tier status, speed, first-token latency, and recent health data when available.
- Which provider has the cheapest MiniMax M2 API pricing?
- 素墨API currently has the lowest listed MiniMax M2 price at $0.010/request across 108 providers.
- Can I compare MiniMax M2 API price and speed together?
- Yes. LMSpeed shows MiniMax M2 API price, output speed, first-token latency, and provider health on the same page so you can compare cost and performance together.
- Is MiniMax M2 API free?
- MiniMax M2 does not currently have a free API tier on LMSpeed. All 108 providers charge per token.