Xiaomi
MiMo v2.6 FlashAperto
Xiaomi open-weights hybrid active parameter MoE running at 100+ tok/s with 1M context and frontier terminal agent benchmarks.
Intelligenza
88.4 #27
AAQI 88.0
Velocità Uscita
118 t/s
ITL 8.5 ms/tok
Prezzo combinato (3:1)
$0.18 /1M
Input $0.1/M · Output $0.3/M
Contesto
1M
≈ 2,500 pagine A4 · output max 32,768
Quality Domain Radar
6-Axis Frontier Evaluation vs Category Average & Flagship
MiMo v2.6 Flash
Claude Mythos Preview (#1)
Average (68)
Gli assi radar sono approssimati dai punteggi di categoria dove mancano misurazioni dirette — vedi Metodologia.
Punti di forza e compromessi
Dove vince
- Fastest open-weights flagship — 118 tok/s
- SWE-bench-tier coding at flash pricing ($0.10/$0.30)
- 1M context self-hostable for regulated stacks
- Strong thinking/non-thinking dual-mode scores
A cosa fare attenzione
- Nuance and long-tail reasoning below frontier closed models
- 310B weights still need serious VRAM even at 15B active
- Smaller ecosystem than DeepSeek/Qwen
Casi d'uso killer
High-throughput coding agents
Flash-speed agent loops at open-model prices.
On-prem copilots
Self-hosted coding assistants for enterprises.
Batch document processing
1M-context extraction at $0.10/M input.
Quickstart per sviluppatori e API
Imposta prima
MIMO_API_KEY — ottieni una chiave APIcurl https://api.mimo.mi.com/v1/chat/completions \
-H "Authorization: Bearer $MIMO_API_KEY" \
-H "content-type: application/json" \
-d '{
"model": "mimo-v2.6-flash",
"messages": [{"role": "user", "content": "Refactor this function for O(n) time and explain the change."}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.mimo.mi.com/v1",
api_key=os.environ["MIMO_API_KEY"],
)
resp = client.chat.completions.create(
model="mimo-v2.6-flash",
messages=[{"role": "user", "content": "Refactor this function for O(n) time and explain the change."}],
)
print(resp.choices[0].message.content)const res = await fetch("https://api.mimo.mi.com/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.MIMO_API_KEY}`,
"content-type": "application/json",
},
body: JSON.stringify({
model: "mimo-v2.6-flash",
messages: [{ role: "user", content: "Refactor this function for O(n) time and explain the change." }],
}),
});
console.log((await res.json()).choices[0].message.content);Risorse e link ufficiali
Deployment API
Confronta host e latenza
Throughput, TTFT e prezzi cache su Groq, Cerebras, Together, DeepInfra, Fireworks, Bedrock e Azure.
GroqCerebrasTogether AIDeepInfraFireworks AIAWS BedrockAzure AI
Punteggi per Fonte
Punteggi per Categoria
Risultati dei Benchmark
Specifiche live e architettura
Sotto il cofano
310B hybrid MoE, ~15B active per token
- Hybrid active-parameter MoE — 310B total, ~15B live per token
- 1M context at 100+ tok/s sustained
- Open weights under a permissive license
- Pretraining-to-posttraining pipeline detailed in the MiMo paper
Data di Rilascio
2 ott 2026
Architettura
310B hybrid MoE, ~15B active per token
Parametri
310B/15B MoE
Licenza
Open Weights
Finestra di Contesto
1,000,000 tokens
Output max
32,768 tokens
Modalità
text + image
Prezzi cache
lettura $0.02 · scrittura $0.1 /1M
Ragionamento
—
Prezzo Ingresso
$0.1/M
Prezzo Uscita
$0.3/M
Velocità Uscita
118 t/s
Tempo al Primo Token
—
Dati aggiornati
4 ott 2026
Stima bolletta mensile
Spesa mensile stimata
$0.00
Calcolo risparmio vs GPT-4o…
Cita e incorpora
Badge Markdown GitHub
Loading badge markdown...BibTeX
@misc{llmpodium2026mimov26flash,
title = {Benchmark Analysis and Intelligence Evaluation of MiMo v2.6 Flash},
author = {LLMPodium Research},
year = {2026},
url = {https://llmpodium.com/models/mimo-v2-6-flash}
}Incorpora il badge del punteggio
Aggiungi un badge Podium Score live al tuo README su GitHub o Hugging Face — rimanda alla classifica live.
Anteprima
Markdown
Loading badge snippet...HTML
Loading badge snippet...Altri modelli di Xiaomi
Modelli alternativi
Migliori alternative a MiMo v2.6 Flash in base a capacità, prezzi e benchmark.