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	$0.40 input /$ 2.00 output per 1M tokens

MiMo-V2.5 specifications

Spec	Value
Provider	Xiaomi
Released	Jun 11, 2026
Privacy	Private
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"
  }'

MiMo-V2.5 API FAQ

How much does the MiMo-V2.5 API cost?

0.40 per 1M input tokens and

2.00 per 1M output tokens, with cached input at $0.08 per 1M. Prices are in USD and can be paid in DIEM at parity.

What is the MiMo-V2.5 model ID?

Use xiaomi-mimo-v2-5 as the model parameter.

Is the MiMo-V2.5 API private?

MiMo-V2.5 is private: requests run on infrastructure Venice controls with zero data retention, and prompts and outputs are never stored or used for training.

What is the context window of MiMo-V2.5?

1M tokens of context, with up to 64K output tokens per response.

What does MiMo-V2.5 support?

MiMo-V2.5 supports function calling, structured outputs, reasoning, image input, web search and prompt caching. Reasoning effort is adjustable with reasoning_effort: none, low, medium and high (default high).

Which endpoint does the MiMo-V2.5 API use?

Call POST /chat/completions. /responses (Alpha) is also supported.

Related models

Qwen 3.7 Plus API: $0.50 input /$ 2.00 output per 1M tokens
Venice Role Play Uncensored API: $0.50 input /$ 2.00 output per 1M tokens
MiniMax M2.7 API: $0.38 input /$ 1.50 output per 1M tokens
Gemini 3.5 Flash-Lite API: $0.38 input /$ 3.13 output per 1M tokens

Explore

By modality