chat Text ZDR (Zero Data Retention)

MiMo v2.5

Lightweight thinking model operated by Xiaomi

A light, fast thinking model with 1M token context. An alternative routing path at a price point similar to DeepSeek V4 Flash.

verified

Single price — no hidden costs

Parameters: 310B total · 15B active (MoE)
License: MIT (open-weight)
Training data: 48T tokens
Context: 1M tokens
Tool calling: Supported
Best for: Chat, quick coding, repetitive automation
Input: $0.14 / 1M tokens
Output: $0.28 / 1M tokens
Cache Read /M: $0.0028 / 1M tokens
30-day uptime: 99.9%
Time to first response: ~450ms
Throughput: ~85 tok/s

Measured by meshcode across our own infrastructure — redundancy means uptime holds even if one upstream has issues.

Use this model View API docs

Quality

Reasoning

Speed

Cost efficiency

Good fit for

Everyday chat Quick code edits Repetitive tool-calling automation Fast Q&A

Code example

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

FAQ

Which company built this model? expand_more

Xiaomi's MiMo team develops and operates this model directly. meshcode contracts API access and passes calls straight through.

Are there any hidden costs? expand_more

No. The input/output prices shown here are the whole story — no subscription fee, no minimum commitment. You're only charged for what you use, deducted from your wallet balance.