Skip to content
CheapestInference

MiMo v2.5 API — unlimited & flat-rate access

MiMo v2.5 is Xiaomi’s fast, efficient model with a ~1M-token context window. CheapestInference serves it in the Core Pool through an OpenAI- and Anthropic-compatible API on unlimited, flat-rate time-block subscriptions — so your cost does not scale with tokens.

Quick facts

Section titled “Quick facts”
ModelMiMo v2.5
Model IDmimo-v2.5
Context window~1M tokens
Cost basis$0.14 / $0.28 per 1M tokens (in / out)
PoolCore Pool (with DeepSeek V4 Flash)
Endpoints/v1/chat/completions (OpenAI), /anthropic/v1/messages (Anthropic)
Pricing$6.99/mo per 8-hour daily time block ($5.94/mo with annual billing), up to full 24/7

Call MiMo v2.5

Section titled “Call MiMo v2.5”
from openai import OpenAI


client = OpenAI(
    base_url="https://api.cheapestinference.com/v1",
    api_key="sk-..."  # your subscriber key
)


response = client.chat.completions.create(
    model="mimo-v2.5",
    messages=[{"role": "user", "content": "Classify these support tickets..."}],
)
Terminal window
curl https://api.cheapestinference.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mimo-v2.5", "messages": [{"role": "user", "content": "Hello"}]}'

Why flat-rate MiMo v2.5

Section titled “Why flat-rate MiMo v2.5”

MiMo v2.5 is built for speed and efficiency with a ~1M-token context window, making it a strong fit for high-volume tasks — summarization, extraction, classification, long-document Q&A, and agent loops that would be expensive on per-token billing. On CheapestInference it is billed at a flat monthly rate, not per token, so bulk workloads have a fixed, predictable cost — a Core Pool time block covers unlimited MiMo v2.5 usage (plus DeepSeek V4 Flash) during your reserved hours. It works in any OpenAI-compatible client.

Common questions

Section titled “Common questions”

Is there a MiMo v2.5 API? Yes. Use model id mimo-v2.5 against https://api.cheapestinference.com/v1. The API is OpenAI- and Anthropic-SDK compatible.

How much does MiMo v2.5 cost? From $6.99/month ($5.94/mo with annual billing). You reserve one or more 8-hour daily time blocks (up to full 24/7) and use MiMo v2.5 with no token caps — billed at a flat monthly fee, not per token.

What is the MiMo v2.5 context window? Around 1M tokens, so it handles large codebases, long documents, and extended agent conversations in a single request.

Who makes MiMo v2.5? MiMo v2.5 is made by Xiaomi. CheapestInference serves it on flat-rate, unlimited time-block subscriptions in the Core Pool.

Section titled “Related”