MiniMax · Efficient
MiniMax M3.1 Flash
MiniMax M3.1 Flash is a multimodal model for coding, tool use, and long-context work. It accepts text, images, and video and produces text, with a 1,000,000-token context window and up to 524,288 output tokens within the remaining context. Thinking is always enabled, with low, medium, high, xhigh, and max effort levels; max is the default. Thinking tokens count toward the output limit. Temperature is fixed at 1 and top-p at 0.95; custom values have no effect.
- Reasoning
- Tools
- Vision
- Video input
- Input
- Text, Images, Video
- Output
- Text
- Reasoning effort
- low · medium · high · xhigh · max
- Discovery tier
- Efficient
Pricing
USD per 1M tokens- Input
- $0.15
- Output
- $0.60
- Cache read
- $0.015
Reference prices as published by the model provider. API example
Specifications
- Context window
- 1M
- Max output
- 524.3K
- Average output (7 days)
- 1.4K tokens
- Longer than 82% of 468 models
Side by side
MiniMax M3.1 Flash compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| MiniMax M3.1 FlashMiniMaxThis model | MiniMax LatestMiniMaxRemove | |
|---|---|---|
| Provider | MiniMax | MiniMax |
| Discovery tier | Efficient | Open weights |
| Added | Oct 19, 2026 | May 3, 2026 |
| Limits | ||
| Context window | 1.05MBest | 512K |
| Max output | 524.29KBest | 80K |
| Average output | 1.4K tokens | — |
| Pricing, USD per 1M tokens | ||
| Input | $0.15Best | $0.23 |
| Output | $0.60Best | $0.96 |
| Cache read | $0.015Best | $0.05 |
| Performance | ||
| Throughput | 119.8 tok/s | 127.0 tok/sBest |
| Time to first token | 7.0 s | 1.1 sBest |
| Request success (24h) | 99.7% | 99.9%Best |
| Benchmark indexes | ||
| Intelligence Index | 42.7Best | 29.2 |
| Coding Index | — | 58.6 |
| Capabilities | ||
| Reasoning | Yes | Yes |
| Tools | Yes | Yes |
| Vision | Yes | Yes |
| Structured output | No | Yes |
| Video input | Yes | No |
| Reasoning effort | low, medium, high, xhigh, max | — |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- MiniMax M3.1 Flash
- MiniMax Latest
Intelligence Index
- MiniMax M3.1 Flash42.7
- MiniMax Latest29.2
MiniMax M3.1 Flash: Better than 88% of 326 scored models
Indexes
Coding Index
Composite of the coding evaluations
- MiniMax M3.1 Flash: —
- MiniMax Latest: 58.6
Agentic work
AutomationBench-AA
Workflow automation, penalized for guardrail violations
- MiniMax M3.1 Flash: 72.5%Top
- MiniMax Latest: 21.3%
AutomationBench-AA tasks completed
Workflows finished end to end without a guardrail violation
- MiniMax M3.1 Flash: 38.1%Top
- MiniMax Latest: 4.4%
Harvey LAB-AAv1.1
Legal tasks passed in full, with no material hallucination
- MiniMax M3.1 Flash: —
- MiniMax Latest: 0.0%
AA-Briefcasev1.1
Agentic knowledge work, rated head to head
- MiniMax M3.1 Flash: 1,473 EloTop
- MiniMax Latest: 1,089 Elo
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- MiniMax M3.1 Flash: 1,458 EloTop
- MiniMax Latest: 1,243 Elo
Document reasoning
GDP.pdf
Professional reasoning over PDF documents, all-pass rate
- MiniMax M3.1 Flash: 20.8%Top
- MiniMax Latest: 9.8%
AA-LCRv1.1
Reasoning across long documents
- MiniMax M3.1 Flash: 79.7%
- MiniMax Latest: 83.0%Top
MLCR-AA
Long-context reasoning over medical records
- MiniMax M3.1 Flash: 16.7%Top
- MiniMax Latest: 4.4%
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- MiniMax M3.1 Flash: 48.0%Top
- MiniMax Latest: 39.0%
GPQA Diamond
Graduate-level science questions
- MiniMax M3.1 Flash: —
- MiniMax Latest: 92.9%
IFBench
Following precise output instructions
- MiniMax M3.1 Flash: —
- MiniMax Latest: 82.9%
Coding
Terminal-Benchv4.0
Practical software engineering in a terminal
- MiniMax M3.1 Flash: 25.8%Top
- MiniMax Latest: 2.0%
SciCode
Scientific computing in Python
- MiniMax M3.1 Flash: 53.4%Top
- MiniMax Latest: 47.1%
Legacy evaluations
Terminal-Bench Hard
Earlier terminal task suite
- MiniMax M3.1 Flash: —
- MiniMax Latest: 42.4%
τ²-Bench Telecom
Tool use in a customer-support simulation
- MiniMax M3.1 Flash: —
- MiniMax Latest: 88.9%
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- MiniMax M3.1 Flash: 79.7%
- MiniMax Latest: 83.0%Top
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.
- Throughput
- 119.8 tok/s
- Faster than 68% of 254 models
- Time to first token
- 7.0 s
- Quicker than 22% of 254 models
- Prompt cache hits
- 78.4%
- About $0.0441 per 1M input tokens with caching
- Request success (24h)
- 99.7%
- Reliable
Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.
- 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-m3.1-flash",
"reasoning_effort": "medium",
"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-m3.1-flash",
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.