MiMo-V2.5

xiaomi/mimo-v2.5

MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...

InputAudioImageTextVideo
OutputText
Input / Outputclub$0.1484 / $0.2968per 1M tokens · USD
Context window1.1Mtoken
Maximum output131.1Ktoken

Pricing

Current model usage rates. Choose your plan to see its published prices.

Pricing
UsagePricing
InputUS$0.1484/ 1M token
Cache readUS$0.002968/ 1M token
OutputUS$0.2968/ 1M token

Membership and model usage are billed separately. Compare plans

Capabilities

Input
AudioImageTextVideo
Output
Text
Context window
1,050,000 token
Maximum output
131,072 token

Providers

Model supply available through Vecbase.

Via OpenRouter

Access is subject to your account’s permissions and model availability.

Frequently asked questions

What is MiMo-V2.5, and who develops it?

MiMo-V2.5 is a model from xiaomi. Its model ID on Vecbase is xiaomi/mimo-v2.5. MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...

How much does MiMo-V2.5 cost on Vecbase?

For MiMo-V2.5, the Club plan lists USD 0.1484 per 1 million input tokens and USD 0.2968 per 1 million output tokens, as of 10/22/2026, 9:25:16 PM UTC. See the pricing table for cache rates, input-length tiers and other usage types. Membership fees are separate.

How many tokens fit in MiMo-V2.5’s context window?

MiMo-V2.5 has a context window of 1,050,000 tokens. Input and output must fit within the limits of the API you use.

What is the maximum output length for MiMo-V2.5?

MiMo-V2.5 can generate up to 131,072 tokens per response. Your API or request settings may set a lower limit.

Can MiMo-V2.5 call tools in an agent workflow?

Yes. MiMo-V2.5 supports tool calling. Your application provides the tool definitions and runs the tools the model requests.

Does MiMo-V2.5 support structured outputs?

Yes. MiMo-V2.5 supports structured output. Set the required format in your API request and check the returned data before using it.

Which input and output formats does MiMo-V2.5 support?

MiMo-V2.5 accepts Audio, Image, Text, and Video and produces Text.

Which providers make MiMo-V2.5 available through Vecbase?

Vecbase offers MiMo-V2.5 through OpenRouter. Availability may vary by provider.

Which model ID should an agent use to request MiMo-V2.5?

Use xiaomi/mimo-v2.5 as the model identifier for MiMo-V2.5. See Vecbase’s API documentation for authentication, required inputs and supported request formats.

What does an agent need to access MiMo-V2.5 through Vecbase?

To use MiMo-V2.5, you need an authenticated account with the required permissions, sufficient balance and the relevant capability enabled. See the documentation for setup.

Is a release date available for MiMo-V2.5?

We do not yet have a confirmed release date for MiMo-V2.5.

Which models can I compare with MiMo-V2.5 on Vecbase?

You can compare MiMo-V2.5 with MiMo-V2.5-Pro (xiaomi/mimo-v2.5-pro), MiMo-V2.6-Flash (xiaomi/mimo-v2.6-flash), and Vecbase Flash (vecbase-1.0-lite). Check their capabilities and prices to find the best fit for your task.