minimax/minimax-m3.1-flash

模型发布 OpenRouter 模型 原文语言:中文

OpenRouter 于 2026-10-19 收录该模型(收录时间不等于模型正式发布日期);上下文:1,048,576 tokens;输入价:$0.0750/百万 tokens;输出价:$0.3000/百万 tokens;定位(来源描述):MiniMax-M3.1-Flash is a multimodal model from MiniMax.

全文

The free launch period ended Oct 22, 2026. MiniMax M3.1 Flash is now served at list price ($0.15/M input, $0.60/M output, $0.015/M cached input).

MiniMax: MiniMax M3.1 Flash

minimax/minimax-m3.1-flash

Model weights

Compare

MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex, multi-step co-work automation, understanding real codebases, fixing bugs, and building features, and visual understanding and creation, including frontend and presentation creation. It is an open-weight mixture-of-experts model with 23B active / 428B total parameters.

Modalities

In / out price

$0.075 / $0.30per 1M

Context

1.0M

Released

Oct 19, 2026

Compare

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput

$0.075$0.30$0.00751.03s105 tok/s

99.39%

10% off

$0.15$0.135$0.60$0.54$0.015$0.01353.06s150 tok/s

100.00%

$0.135$0.54$0.01350.55s157 tok/s

99.90%

$0.150$0.60$0.01500.38s108 tok/s

99.25%

$0.150$0.60$0.01500.19s68 tok/s

98.75%

$0.150$0.60$0.01500.73s171 tok/s

100.00%

$0.150$0.60$0.01500.69s125 tok/s

100.00%

50% off

$0.30$0.150$1.20$0.60$0.03$0.01501.33s62 tok/s

100.00%

$0.150$0.60$0.01501.01s106 tok/s

99.92%

$0.150$0.60$0.01500.19s69 tok/s

97.83%

$0.150$0.60$0.01500.28s159 tok/s

99.65%

$0.150$0.60$0.01502.84s109 tok/s

99.73%

$0.075$0.30$0.00750.49s197 tok/s

99.68%

ProviderInput / Output /M

Input $0.075 / Output $0.30

105 tok/s99.39% uptime

Input $0.135 / Output $0.54

10% off

150 tok/s100.00% uptime

Input $0.135 / Output $0.54

157 tok/s99.90% uptime

Input $0.15 / Output $0.60

108 tok/s99.25% uptime

Input $0.15 / Output $0.60

68 tok/s98.75% uptime

Input $0.15 / Output $0.60

171 tok/s100.00% uptime

Input $0.15 / Output $0.60

125 tok/s100.00% uptime

Input $0.15 / Output $0.60

50% off

62 tok/s100.00% uptime

Input $0.15 / Output $0.60

106 tok/s99.92% uptime

Input $0.15 / Output $0.60

69 tok/s97.83% uptime

Input $0.15 / Output $0.60

159 tok/s99.65% uptime

Input $0.15 / Output $0.60

109 tok/s99.73% uptime

Input $0.075 / Output $0.30

197 tok/s99.68% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.02159/M tokens

Output

$0.5123/M tokens

MiniMax M3.1 Flash — Price history

Price history

No effective price data for this selection

$0.0166$0.30086.5%0.7%

$0.0209$0.60095.6%2.6%

$0.0209$0.54093.9%0.7%

$0.0212$0.50492.4%87.3%

$0.0225$0.60094.4%2.2%

$0.0249$0.59992.6%1.9%

$0.0268$0.59991.2%1.0%

$0.0285$0.59890.0%2.4%

$0.0290$0.54087.2%1.2%

$0.0336$0.60086.2%0.1%

$0.0388$0.59882.3%0.0%

$0.0397$0.59881.6%0.0%

$0.0859$0.59947.4%0.0%

ProviderInput / Output /M

Token share

Effective in $0.0166 / Effective out $0.300

Token share

0.7%

Effective in $0.0209 / Effective out $0.600

Token share

2.6%

Effective in $0.0209 / Effective out $0.540

Token share

0.7%

Effective in $0.0212 / Effective out $0.504

Token share

87.3%

Effective in $0.0225 / Effective out $0.600

Token share

2.2%

Effective in $0.0249 / Effective out $0.599

Token share

1.9%

Effective in $0.0268 / Effective out $0.599

Token share

1.0%

Effective in $0.0285 / Effective out $0.598

Token share

2.4%

Effective in $0.0290 / Effective out $0.540

Token share

1.2%

Effective in $0.0336 / Effective out $0.600

Token share

0.1%

Effective in $0.0388 / Effective out $0.598

Token share

0.0%

Effective in $0.0397 / Effective out $0.598

Token share

0.0%

Effective in $0.0859 / Effective out $0.599

Token share

0.0%

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

197tok/s

P50, best across providers

Latency

0.19s

P50, best provider

Reasoning effortLatency / throughput

AutoExacto benchmarks

GPQA DiamondTAU-BenchRelace86.5%74.7%Inferact vLLM88.5%72.3%Novita89.3%70.9%Nebius Token Factory87.5%72.6%inference.net87.0%73.0%inference.net (US)85.0%67.3%

+12 more providers

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)The model was reachable. Request routed to a provider.

100.00%

Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.

99.67%

Availability over the last 3 days

Last 72 hours

Availability 99.67%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.95%

Without Routing

98.07%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for MiniMax: MiniMax M3.1 Flash (Artificial Analysis and Vals AI)

SourceBenchmarkScore

Artificial AnalysisMiniMax-M3.1-Flash Intelligence Index29.1

Artificial AnalysisMiniMax-M3.1-Flash HLE48.0%

Artificial AnalysisMiniMax-M3.1-Flash AA-LCR79.7%

Artificial AnalysisMiniMax-M3.1-Flash GDPval-AA48.3%

Artificial AnalysisMiniMax-M3.1-Flash CritPt22.3%

Artificial AnalysisMiniMax-M3.1-Flash SciCode53.4%

Artificial AnalysisMiniMax-M3.1-Flash Terminal-Bench 4.025.8%

Artificial AnalysisMiniMax-M3.1-Flash AA-Omniscience Accuracy45.1%

Artificial AnalysisMiniMax-M3.1-Flash AA-Omniscience Non-Hallucination Rate6.3%

Vals AIMiniMax-M3.1-Flash Access to Justice Benchmark73.3%

Vals AIMiniMax-M3.1-Flash EMB v1.167.8%

Vals AIMiniMax-M3.1-Flash Finance Agent v2.158.8%

Vals AIMiniMax-M3.1-Flash Vals Finance Index55.9%

Vals AIMiniMax-M3.1-Flash HLAB-Vals-1.17.5%

Vals AIMiniMax-M3.1-Flash Vals Legal Index67.1%

Vals AIMiniMax-M3.1-Flash Legal Research Bench34.1%

Vals AIMiniMax-M3.1-Flash SAGE85.3%

Vals AIMiniMax-M3.1-Flash Tax Agent Bench32.1%

Vals AIMiniMax-M3.1-Flash Terminal-Bench 4.025.3%

Vals AIMiniMax-M3.1-Flash Vals Index53.8%

Vals AIMiniMax-M3.1-Flash Vibe Code Bench 1-100 v1.119.8%

Vals AIMiniMax-M3.1-Flash Vibe Code Bench v1.173.9%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

1.

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

2.12Ttokens

2.

OpenClaw

OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.

1.11Ttokens

3.

Kilo Code

Kilo Code is an open-source AI coding agent that works across VS Code, JetBrains, and CLI to help developers ship code faster with agentic workflows.

733Btokens

4.

Mira is the leading AI agent inside Telegram

Mira is a Telegram-native AI assistant.

423Btokens

5.

pi

There are many coding agents, but this one is yours.

164Btokens

Rest of OpenRouter

308B

Top 5 Apps

141B

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Not currently available through EU in-region routing. In-region routing docs

Frequently asked questions

MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity.

MiniMax M3.1 Flash costs $0.075/M input tokens and $0.30/M output tokens, with separate rates for Cache Read at $0.0075/M tokens.

MiniMax M3.1 Flash has a 1,048,576 token context window. It supports up to 131,072 completion tokens.

Yes. MiniMax M3.1 Flash accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

MiniMax M3.1 Flash accepts text, images, and video as input and returns text.

MiniMax M3.1 Flash is served by 12 providers on OpenRouter: Inferact vLLM, MiniMax, StreamLake, Wafer, Fireworks, inference.net, DigitalOcean, Nebius Token Factory and 4 more. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

MiniMax M3.1 Flash was released on October 19, 2026.

正文以来源语言显示。

参考来源

← 返回每日简报