Modèles
MiMo V2.6 Pro
Compare
Xiaomi logo

MiMo V2.6 Pro

mimo-v2.6-prollms.txt
Xiaomi
MiMo-V2.6-Pro is Xiaomi’s trillion-parameter, natively omni-modal flagship reasoning model for complex projects, long-horizon agentic tasks, coding, research, and professional knowledge work. It supports a 1M-token context window and up to 128K output tokens. Compared with V2.5, it delivers stronger reasoning and long-task performance while retaining the same API pricing.

Pricing

PricingCache ReadWeb Search
$0.48$0.96
$0.0038/M tokens$0.005/request

Modalités d'entrée

  • Text
  • Vision
  • Audio
  • Video

Modalités de sortie

  • Text

Context length

  • 1.05M tokens

Max output

  • 131K tokens

Capabilities

  • Thinking
  • Streaming
  • Tool calling
  • Web search
  • URL context
  • Code interpreter
  • Computer use
  • File search
  • Memory tool
  • Structured outputs
  • Structured decision
  • Citations
  • Prompt caching
  • Background mode
  • Server-side sessions

Fournisseurs

Xiaomi xiaomi-mimo-v2.6-pro
Pricing$0.48$0.96
Cache Read$0.0038/M tokens
Web Search$0.005/request
PrecisionⓘNot Disclosed
Latency5.1S
Throughput36.6TPS
Uptime
100.00% uptime 2 days ago
99.93% uptime yesterday
100.00% uptime today

Performance for mimo-v2.6-pro

Uptime est le pourcentage de requêtes réussies au cours des 72 dernières heures. AIHubMix surveille en continu chaque fournisseur et réessaie automatiquement avec le meilleur fournisseur suivant lorsqu'un fournisseur renvoie une erreur ou répond trop lentement; Latency est le temps total d'aller-retour d'une requête (plus elle est faible, mieux c'est); Throughput correspond à la vitesse d'écriture du modèle (tokens par seconde ; plus il est élevé, mieux c'est).

Uptime
Loading...
Latency
Loading...
Throughput
Loading...

Try this model

Python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AIHUBMIX_API_KEY"],
    base_url="https://aihubmix.com/v1",
)

response = client.chat.completions.create(
    model="mimo-v2.6-pro",
    messages=[
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    max_tokens=1024,
    stream=False,
)

print(response.choices[0].message.content)

Frequently asked questions

What is MiMo V2.6 Pro?

MiMo-V2.6-Pro is Xiaomi’s trillion-parameter, natively omni-modal flagship reasoning model for complex projects, long-horizon agentic tasks, coding, research, and professional knowledge work. It supports a 1M-token context window and up to 128K output tokens. Compared with V2.5, it delivers stronger reasoning and long-task performance while retaining the same API pricing.

© 2023 - 2026 AIHubMix, LLC

Produit

Développeurs

Entreprise

Conditions et politiques