Model Detail
MiniMax-M3.1-Flash
▲ 19.4%MiniMax-M3.1-Flash is a code generation model with 110.2B parameters released by MiniMaxAI. The model is registered under the image-text-to-text pipeline tag on Hugging Face, and supports text+image+video->text inputs, distributed under a other license.
MiniMax-M3.1-Flash is priced at $0.15/M input tokens and $0.6/M output tokens. Operationally the model offers a 1049K-token context window, which matters when sizing it for prompt-heavy or latency-sensitive workloads. At this input rate the model sits in the commodity tier and is suitable for high-volume workloads where per-call cost dominates the decision.
MiniMax-M3.1-Flash ships with 110.2B parameters. Total weight footprint is approximately 220.5 GB, which is the relevant figure when planning local-inference VRAM. Distribution is governed by the other license — review the exact terms before commercial deployment.
Downloads of MiniMax-M3.1-Flash have moved +19.4% over the past 24 hours. That is a slight downtrend, consistent with normal cooling as newer models compete for the same workloads. These numbers are signal, not guarantee — week-over-week download counts on Hugging Face also reflect mirror traffic, CI scrapes, and one-off benchmarking runs.
MiniMax-M3.1-Flash is best fit for code completion, repository-scale Q&A, and pair-programming integrations, high-volume batch jobs where per-call cost dominates the budget, and long-context tasks such as full-codebase analysis or book-length summarization (1049K tokens). It is a less obvious choice for one-shot generation of security-critical code without review. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
Transient Amplification in Cascaded Gradient Methods: Exact Minimax Laws and Tracking without Resonance
arXiv:2606.04031v3 Announce Type: replace Abstract: Leader-follower gradient iterations, including bilevel and two-time-scale methods, can exhibit large finite-time excursions despite asymptotic stability. For cascaded iterations with block matrix J = [[A,0],[C,D]], symmetric diagonal blocks of norm
Exact Global Minimax Risk near Nonidentification
arXiv:2610.32546v1 Announce Type: cross Abstract: We study squared-error estimation when a nuisance parameter is unidentified on a submodel but affects a target that vanishes there. For models with higher-order profile expansions, we give sufficient conditions under which the largest critical-path m
Near Minimax Rate for Quantile Distributional Reinforcement Learning
arXiv:2610.29595v1 Announce Type: cross Abstract: In this paper, we study quantile distributional policy evaluation, where the return distribution under a given policy is approximated by the quantile Bellman fixed point $\bm\eta_m$. We investigate the statistical accuracy of estimating $\bm\eta_m$ a
Minimax-Optimal Predictive Flow Matching under Distribution Drift
arXiv:2610.28898v1 Announce Type: new Abstract: Flow matching learns a generative velocity field by regression, but under distribution drift a field must be deployed before the current data arrive. We study this predictive problem for a fixed, possibly nonconvex, neural class, with dynamic regret ag
Minimax Optimality of the NPMLE for Gaussian Mixtures in Hellinger Distance
arXiv:2610.30109v1 Announce Type: cross Abstract: We analyze the problem of estimating univariate Gaussian mixture densities using the nonparametric maximum likelihood estimator (NPMLE) based on $n$ independent and identically distributed samples. We show that the unconstrained NPMLE achieves the mi
Minimax-optimal Scaling Laws in Ridge Regression via Transfer Learning
arXiv:2610.23337v1 Announce Type: new Abstract: Pretrained models are often reused across downstream tasks, motivating the question of whether this transfer learning procedure can provide a substantial performance improvement, namely, in terms of the scaling law. We address this question in the prot
