MiniMax · Open weights
MiniMax M2
MiniMax M2 offers enhanced reasoning and strong general performance. Optimized for coding and agentic workflows.
- Reasoning
- Input
- Text
- Output
- Text
- Discovery tier
- Open weights
Pricing
USD per 1M tokens- Input
- $0.17
- Output
- $1.53
Reference prices as published by the model provider. API example
Specifications
- Context window
- 200K
- Max output
- 131.1K
Side by side
MiniMax M2 compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| MiniMax M2MiniMaxThis model | MiniMax M2.5MiniMaxRemove | |
|---|---|---|
| Provider | MiniMax | MiniMax |
| Discovery tier | Open weights | Open weights |
| Added | Jan 12, 2025 | Feb 12, 2026 |
| Limits | ||
| Context window | 200K | 204.8KBest |
| Max output | 131.07K | 131.07K |
| Average output | — | 653 tokens |
| Pricing, USD per 1M tokens | ||
| Input | $0.17Best | $0.27 |
| Output | $1.53 | $1.08Best |
| Cache read | — | $0.027 |
| Performance | ||
| Throughput | — | 110.4 tok/s |
| Time to first token | — | 1.8 s |
| Request success (24h) | 90.3% | 100.0%Best |
| Benchmark indexes | ||
| Intelligence Index | — | 22.8 |
| Capabilities | ||
| Reasoning | Yes | Yes |
| Tools | No | Yes |
| Structured output | No | Yes |
| Reasoning effort | — | — |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- MiniMax M2
- MiniMax M2.5
Intelligence Index
- MiniMax M2—
- MiniMax M2.522.8
Document reasoning
AA-LCRv1.1
Reasoning across long documents
- MiniMax M2: —
- MiniMax M2.5: 73.3%
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- MiniMax M2: —
- MiniMax M2.5: 20.5%
GPQA Diamond
Graduate-level science questions
- MiniMax M2: —
- MiniMax M2.5: 84.8%
IFBench
Following precise output instructions
- MiniMax M2: —
- MiniMax M2.5: 71.6%
Legacy evaluations
Terminal-Bench Hard
Earlier terminal task suite
- MiniMax M2: —
- MiniMax M2.5: 34.8%
τ²-Bench Telecom
Tool use in a customer-support simulation
- MiniMax M2: —
- MiniMax M2.5: 95.3%
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- MiniMax M2: —
- MiniMax M2.5: 73.3%
Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis
Live routing data
Performance and reliability
Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.
- Request success (24h)
- 90.3%
- Unstable
- Healthy (98% or more)
- Degraded (90–98%)
- Down (under 90%)
- No requests
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax/minimax-m2",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="minimax/minimax-m2",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)MiniMax
Related models
Other MiniMax models, starting with the same family.