MiniMax-M3.1-Flash
MiniMaxMiniMaxProprietary
Description
MiniMax M3.1 Flash is the flash successor in the MiniMax M3 family, released 2026-10-19. It is a multimodal reasoning model with a 1M-token context window, native image and video input, and text output. Thinking is always on (cannot be disabled) with effort levels low/medium/high/xhigh/max (default max). Described as open-weight with weights to be released later; no Hugging Face checkpoint is available yet. The anonymous "Space Bunny" model was an early version. Available via the MiniMax API (Anthropic-compatible and OpenAI-compatible endpoints), M Plan, and MiniMax Code.
Date de sortie
2026-10-19
Paramètres
—
Longueur du contexte
1.0M
Modalités
image, text, video
Radar de capacités
44
general
53
coding
40
reasoning
51
science
50
agents
60
multimodal
Classements
| Domaine | #Rang | Score | Source |
|---|---|---|---|
| Capacité agentique | 22 | 61.0 | LS |
| Classement codage | 35 | 90.0 | AA |
| Classement général | 33 | 73.0 | AA |
| Classement multimodal | 40 | 59.0 | LS |
| Raisonnement | 36 | 83.0 | LB |
| Science | 45 | 78.0 | AA |
Scores de benchmarks (LLM Stats)
(LLM Stats (zeroeval))Agents
BankerToolBench
76.2%Aut.
AutomationBench v1.0.6
62.8%Aut.
LOCA-Bench (256k)
60.3%Aut.
PostTrainBench
39.3%Aut.
Agents' Last Exam
29.6%Aut.
Code
CyberGym
82.2%Aut.
DeepSWE 1.1
73.7%Aut.
NL2Repo
61.2%Aut.
SWE Refactor Bench
23.0%Aut.
General
GDP.pdf
20.8%Aut.
Multimodal
OSWorld 2.0
61.7%Aut.
Reasoning
CharXiv-R
82.5%Aut.
Humanity's Last Exam (no tools, text-only)
43.4%Aut.
Terminal-Bench 4.0
38.1%Aut.
Vision
BabyVision
91.0%Aut.
Indices d'évaluation AA
(Artificial Analysis)Lcr(Artificial Analysis)79.7
Scicode(UIUC + Argonne National Lab (2024))53.4
Hle(Center for AI Safety + Scale AI (2025))48.0
Intelligence Index(Artificial Analysis)42.7
Terminalbench V4 025.8
Scores par catégorie LLM Stats
(LLM Stats (zeroeval))Safety80
Finance80
Multimodal60
General60
Agents60
Code60
Vision60
Reasoning50
Tool Calling50
Math40
Systems40
Tarification
Prix d'entrée$0.15 / 1M tokens
Prix de sortie$0.6 / 1M tokens
Prix mixte (3:1)$0.262 / 1M tokens
Prix de lecture cache$0.015 / 1M tokens
Vitesse
Tokens/sec106.3
Délai du premier token0.88s
Temps de réponse19.69s
Classement des Prix par Fournisseur
Classement des Prix par Fournisseur
13 fournisseurs
Moins cher: MiniMaxPlus cher: Venice AI
FournisseurEntréeSortie
1MiniMaxMoins cher
$0
$0
2Kilo Gateway
$0.1
$0.55
3EmpirioLabs AI
$0.1125
$0.45
4MiniMax (minimax.cn)
$0.1494
$0.5976
5NanoGPT
$0.15
$0.6
6OpenRouter
$0.15
$0.6
7ZenMux
$0.15
$0.6
8Novita AI
$0.15
$0.6
9Vercel AI Gateway
$0.15
$0.6
10MiniMax (minimax.io)
$0.15
$0.6
11Merge Gateway
$0.15
$0.6
12LLM Gateway
$0.15
$0.6
13Venice AI
$0.1875
$0.75
Comparer les prix entre différents fournisseurs API pour ce modèle.