Question 1

What is MiMo V2.5?

Accepted Answer

MiMo V2.5 is a model from Xiaomi, released on Apr 23, 2026. MiMo-V2.5 is a native omnimodal model with strong agentic capabilities, supporting text, image, video, and audio understanding within a unified architecture. Built upon the MiMo-V2-Flash backbone and extended with dedicated vision and audio encoders, it delivers robust performance across multimodal perception, long-context reasoning, and agentic workflows. Key features include:.

Question 2

How much does MiMo V2.5 cost?

Accepted Answer

On the Respan gateway, input starts at $0.14 per 1M tokens on OpenRouter, and output starts at $0.28 per 1M tokens on OpenRouter, after gateway discounts. Averaged across 3 providers, it costs $0.33 per 1M input tokens and $0.66 per 1M output tokens.

Question 3

Which providers serve MiMo V2.5 on Respan?

Accepted Answer

3 providers serve MiMo V2.5: OpenRouter, Novita, and EmpirioLabs.

Question 4

What is MiMo V2.5's context window?

Accepted Answer

MiMo V2.5 accepts up to 1.1M tokens of context on its largest provider route.

Question 5

How do I use MiMo V2.5 with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "mimo-v2.5". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is MiMo V2.5?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was Novita at 20 tokens per second, and the lowest response latency was 3.1 seconds on Novita. Speed varies with request size and provider.

Question 7

Where does MiMo V2.5 rank on the Respan Index?

Accepted Answer

MiMo V2.5 scores 28.8 out of 100 on the Respan Index v1.1, ranking #68 of 138 models. By category: Coding 11.3 (estimated), Agents 40.8, Reasoning 21.7, Knowledge & language 27.4 (estimated), and Human preference 50.9. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

Question 8

How does MiMo V2.5 score on benchmarks?

Accepted Answer

MiMo V2.5 has 11 published benchmark scores, including Toolathlon-Verified 49.1%, ScienceQA Visual 97.5%, and LMArena WebDev 1438. Each score links to where it was published; the data is collected by llmmetric.com.

Provider	Context	Input	Output
OpenRouter`openrouter/xiaomi/mimo-v2.5`	1.1M	$0.14/M	$0.28/M
NovitaSave 10%`novita/xiaomimimo/mimo-v2.5`	1.0M	$0.15/M	$0.30/M
EmpirioLabs`empiriolabs/mimo-v2-5`	1M	$0.70/M	$1.40/M

MiMo V2.5

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Benchmarks

Respan Indexv1.1

Agents1

Multimodal6

Apps

MiMo V2.5 FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.

Arena3

Other1