Early access: features, availability, and pricing may change as Kyara Intelligence evolves.

Below baseline Reasoning

Xiaomi: MiMo-V2.5

Xiaomi's 1M-context omnimodal model for coherent, affordable long-form RP.

Model ID xiaomi/mimo-v2.5

Quick start

Drop this model into any OpenAI-compatible client by setting the base URL, your API key, and the model ID below.

curl https://api.kyara-intelligence.com/v1/chat/completions \
  -H "Authorization: Bearer $KYARA_INTELLIGENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "xiaomi/mimo-v2.5",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'

See the full API reference

Overview

Mei 2 is Xiaomi's native omnimodal MiMo-V2.5, built for rich perception, strong reasoning, and cost-efficient long-form RP. Its massive 1M token context keeps complete character histories, lore documents, and extended conversations in view, helping scenes stay coherent across deep emotional turns, complex plots, and long-running narratives. Compared with earlier MiMo versions, it brings sharper multimodal understanding and more capable agentic behavior while staying affordable for everyday premium storytelling.

Specifications

Context / Memory 🌌 Extreme · 1M tokens

Cost vs baseline Below baseline

Input

0.2x

Output

0.2x

Input

1.9M

cr / M tokens

Output

cr / M tokens

Multiples are relative to the catalog median; bars are scaled to the most expensive model.

Model ID

xiaomi/mimo-v2.5

Reasoning

Available

Status

Current

Upstream moderation

All models on Kyara Intelligence are accessed through their original API providers (Mistral, Z.AI/GLM, xAI, DeepSeek, and others). Each provider's content policies and moderation apply to all requests.

Kyara routes API calls without modifying inputs or outputs, and does not log prompt or response content. Users are responsible for complying with the relevant provider's terms of service in addition to Kyara's terms.