MiMo-V2.5 API: Pricing and Specs

MiMo-V2.5 API

MiMo-V2.5 is a large language model by Xiaomi, available on the Venice API as xiaomi-mimo-v2-5. It runs privately, with zero data retention.MiMo-V2.5 is Xiaomi’s native omnimodal model with strong agentic capabilities, supporting text, image, video, and audio understanding in a unified architecture. Built on a sparse Mixture-of-Experts backbone with 310B total and 15B active parameters, it delivers long-context reasoning up to 1M tokens, function calling, and multimodal perception.

MiMo-V2.5 API pricing

Model ID	Variant	Privacy	Price
`xiaomi-mimo-v2-5`	Standard	Private	$0.40 / $2.00 per 1M

MiMo-V2.5 specifications

Spec	Value
Provider	Xiaomi
Released	Jun 11, 2026
Privacy	Private
Status	Stable
Open weights	Yes
Context window	1M tokens
Max output	64K tokens
Reasoning effort	none, low, medium, high
Served precision	FP8

How to use the MiMo-V2.5 API

Send requests to POST https://api.venice.ai/api/v1/chat/completions with "model": "xiaomi-mimo-v2-5" and your API key.

curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "xiaomi-mimo-v2-5",
    "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
    "reasoning_effort": "high"
  }'

Related models

Qwen 3.7 Plus API: $0.50 / $2.00 per 1M
Venice Role Play Uncensored API: $0.50 / $2.00 per 1M
MiniMax M2.7 API: $0.375 / $1.50 per 1M
Gemini 3.5 Flash-Lite API: $0.375 / $3.13 per 1M

Explore

By modality

MiMo-V2.5 API