SSyncDev

MiniMax M3.1 Flash

SyncDev model directory · Profile updated Nov 17, 2026

Compare with another model

MiniMax M3.1 Flash is MiniMax's GA open-weight multimodal MoE for coding agents: 428B total, 23B active, 1M context, from $0.15 per 1M input tokens.

Key specifications

Specification score
56.5
Context window
1M
Input / 1M tokens
From $0.15
Output / 1M tokens
From $0.60
License
MiniMax Community License (non-OSI; commercial use needs attribution/notification, written authorisation above ~$20M annual revenue per secondary reports)

The specification score summarizes recorded features and limits. It is not a benchmark result.

Pricing conditions: Indicative USD per 1M tokens (MiniMax pay-as-you-go): $0.15 input, $0.60 output, $0.015 cache read. No highspeed tier listed. Confirm on your own account.

Inputs and outputs

Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.

Accepts

  • Text input
  • Image input
  • Video input

Produces

  • Text output

Capabilities

ReasoningVisionOpen weights

What is MiniMax M3.1 Flash?

Fifteen cents per million input tokens. Sixty cents out. For a model that reads text, images and video across a million-token window, that is the price point that makes MiniMax's general-availability release worth a look before anything else about it.

This is the finished version of the M3.1 Flash Preview that appeared in late September. Before launch it also ran anonymously on OpenRouter under the name "Space Bunny". The API went live on 19 October 2026 and weights reached Hugging Face on 23 October.

Quick reference

Field Value
API ID MiniMax-M3.1-Flash
Architecture Native multimodal mixture-of-experts
Parameters About 428B total, 23B active (model card)
Context Up to 1,000,000 tokens
Input / output Text, image, video / text
Reasoning Always on; effort low, medium, high, xhigh, max
Recommended sampling temperature 1.0, top_p 0.95
Licence MiniMax Community License

Why it is cheap to run

Two engineering choices do most of the work. First, MiniMax Sparse Attention now runs through the whole stack; the three full-attention layers at the start of the previous design were replaced with sparse ones. Second, a DSpark speculative-decoding draft head ships with the weights, replacing the earlier multi-token-prediction approach. Quantisation-aware training covers the routed experts and attention paths too.

MiniMax claims about 70% lower cost on agent tasks and roughly three times faster inference than its prior model. Those are vendor claims. They are also exactly the kind of claim you can check in an afternoon.

Publisher-reported scores

  • DeepSWE v1.1: 73.7
  • BankerToolBench: 76.2
  • OSWorld 2.0: 61.7
  • Terminal Bench 4.0: 38.1
  • CyberGym: 82.2

MiniMax notes these were measured on the official weights and that third-party quantisations may score differently.

The parameter mismatch

The model card describes about 428B total and 23B active. The Hugging Face file metadata, however, reads 220B. We cannot tell from the outside which tensors account for the difference. If you are planning GPU memory, measure the downloaded checkpoint rather than trusting either figure.

Pricing and terms

Pay-as-you-go, indicative USD per 1M tokens: $0.15 input, $0.60 output, $0.015 for cached prompt reads. No highspeed tier is listed for this model, which is a change from older lines such as MiniMax-M2.7-highspeed. Confirm current rates on your own MiniMax account.

The licence is MiniMax's own community licence, not an OSI-approved one. Commercial use needs attribution or notification, and written authorisation is said to be required above roughly $20M in annual revenue. Read the licence file yourself if you are near that line.

For self-hosting, SGLang and vLLM are the recommended engines, with TokenSpeed also supported. Transformers, KTransformers and others were listed as in progress.

A test plan that fits the price

Take one agent workflow you already run on MiniMax-M3 or a competitor. Run it at medium effort, then at high. Track three numbers: tasks completed, total tokens, and wall-clock time. Because reasoning cannot be switched off, short classification calls will always carry some thinking overhead; if that matters, measure it explicitly.

The rest of the lineup sits on the MiniMax provider page.

How to evaluate MiniMax M3.1 Flash

Compare the model on the work you need to complete.

Tasks and inputs

MiniMax M3.1 Flash is listed for Image-text-to-text, Text generation, Video-text-to-text, Coding & Code Generation. It accepts text, image, video and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.

Capacity and cost

Documented limits: 1M context. The listed route has starting rates of $0.15 input and $0.60 output per million tokens. Measure a completed task using the prompts, documents and tools your application will use. Include reasoning and retries in the result.

Choosing a deployment

The weights are downloadable under MiniMax Community License (non-OSI; commercial use needs attribution/notification, written authorisation above ~$20M annual revenue per secondary reports). Check runtime support and size the complete model and working context for your expected concurrency.

Frequently asked questions

`MiniMax-M3.1-Flash` on the MiniMax platform. Weights are on Hugging Face as MiniMaxAI/MiniMax-M3.1-Flash.

These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.

Google

Gemini 4 Hydrogen

Gemini 4 Hydrogen is Google's fast, lower-cost Gemini 4 model for everyday coding and agentic execution, with a 1M context, xhigh thinking and a free tier.

1.05M context

OpenAI

GPT-6 Cyber

GPT-6 Cyber is OpenAI's restricted security model for authorised vulnerability investigation, reproduction and fix verification, for Daybreak Red customers.

1.05M context

particle-ai

Particle-1

Particle-1 is Particle's first software-engineering model, an RL-tuned DeepSeek V4.1 Flash that aims to solve coding tasks with fewer tokens.

1.05M context

Microsoft

MAI-Cyber-1.1-Flash

MAI-Cyber-1.1-Flash is Microsoft AI's vulnerability-discovery model, available only inside its MDASH scanning harness to verified security customers.

— context

recursive

Flint

Recursive Flint is an open-weight 39.8B MoE coding-agent model with 2.5B active parameters, free to try via OpenCode and OpenRouter.

262.14K context

Deepreinforce

Ornith-1.5 122B

Ornith-1.5 122B is an open MIT-licensed MoE coding and agent model with a 262K context, reasoning by default and single-80GB-GPU serving.

262.14K context