MiMo V2.5

MiMo V2.5 is Xiaomi's native omnimodal model, perceiving images, video, audio, and text with native agent execution for tasks such as browsing.

start building →

compare models

                               .  ...... ..... ...
                      .......::--++++*+*++++++---::......
                   .:::-**===%%%%%@@@@@@@@@@%%@%%%===**+-:::...
              ..:-+=%%@@@@@@##@#####@@@#@@####@@@@@@@@@@%%==*+::..
            ..-*=@@#@####@#@#@@@@#@##@##@@@#@@@@@@@@@@@@@@@@@%%=+:...
          ..-=%@#@#@#@#########@##@#@@@@#@@@@@#@@@@@##@@@@@@@@@@%=*-:.
         :-=%##@#@@@###@####@@@@@##@##@@#@@@@@@@@@@@@@@@@@@@@@@@@@@=*-.
       .:*%@##@#@##@@@@###@#@#####@@@@##@@@##@##@#@@@@@@@@@@@@@@@@%@@=+:
     ..:*@@###########@###@@@####@@#@@@@@@#@@@@@@@@@@@@@@@@@@@@@@@@@@%%*:..
     .:*@###@########@######@@@@##@@##@@@@#@#@@@@@@@@@@@@@@@@@@%@@%@@%@%*:
    .:*@@@#########@#@########@#@@@#@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@%%@%%+..
    :+%@#####@####@####@@@@##@@@@@##@@@##@@@@@@@@@@@@@@@@@%@%@@@@@%%%@%%%=-.
   .-=@#####@##@@#@#@@##@@@#@@##@#@@#@@@@@@@@@@@@@@@@@@@@@@@%%@%@@%@%%%%%%*:
   .+%#@##@@#####@##@###@#@@@#@#@@@@@@@@@@@@@@@@@@@@@@@@@@%@@@%%%%@@%%%%%%*-.
  .:*@###@#@#@#####@@#@####@@#@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@%@@%@%@%%%@%%=+:.
  .-=@#@@@####@@##@@###@##@#@@@@#@@@@@@@@@@@@@@@@@@@@@@@@%@%%%%@@@@@@%%@%%%*:..
 ..+%#@#@##@######@@#@##@@@##@@@@@@@@@@@@@@@@@@@@@@@@%%@@%@@@%%%%%@%%@%%%%=*-.
 .:*%#@###@#@@@@@@##@@#@#@##@@@@@@@@@@@@@@@@@@@@@@@@@@@@@%@%@%@@%%@%%%%%%%==+:
 .:*@###@#####@@@#@@#@#@@@@@@@@@@@@@@@@@@@@@@@@%%@@@%%%@@@%%@%@%%%%%%%%%%%%=+:
 .-=@@@##@@###@##@@@##@@@#@@@@@@@@@@@@@@@@@@@@@@@@%%%%%@@@%%@%%%%%%%%%%%%%%=+-.
 .-=@@##@###@@##@##@@@##@###@@@@@@@@@@@@@@@@@@@@@@@@%%%%@%%%%%%%%%%%%%%%=%==*-.
 .+%@@###@####@@##@@@@@@@@@@@@@@@@@@@@@@@@@@%@%@@@@%@@@%%%%@%%%%%%%%%%%%%%%=*+.
.:+%@#@####@###@#@@#@@@@#@@@@@@@@@@@@@@@@@@@@%%@%%@@%@%@%%%%%%%%%%%%%%%%%%%=*-.
 .+%@##@@@@##@@@@#@@@@@@@@@@@@@@@@@@@@@@@@%%%%@@%@@@%%@@@%%%%%%%%%%%%%%%%=%=*-.
 .+%@@@#@#@@@@@@#@@@@@@@@@@@@@@@@@@@@@@%@@%%%@@%@%%%%%%%%%%%%%%%%%%%%%%%==%=*-.
 :+%@@@@@#@@@@##@@@@@@@@@@@@@@@@@@@@@@@@@%@%@@@@%@%%%%%%%%%%%%%%%%%%======%=*-.
 .+%@@#@#@@#@@@@@@@@@@@@@@@@@@@@@@@@@@%%%@@%%@%@%@@%%%%%%%%%%%%%%=%%%=%=====*-.
 .-=@@#@@@@@@@@@@@@@@@@@@@@@@@@@@@@@%%%%%%@%@%%%%%%%%%%%%%%%%%%%%%%=%===%===*-.
 .-=@@@#@#@@@@@@@@@@@@@@@@@@@@%@%@%%@@@@%@%%@%%%%%%%%%%%%%%%=%%%=%%%=======*+:.
 .:*@@@@@#@@@@@@@@@@@@@@@@@@@%@@@@@@@%@%@%%@%%%%@%%%%%%%%%%%%=%=%===%======*+:
  :*%@@@#@@@@@@@@@@@@@@@@@@@@@@@%%@%%%%@@%%%%@%%%%%%%%%%%%=%%%%=====%======*-.
  .+%@@#@@@@@@@@@@@@@@@@@@@@%@%%@%%@%%@@%%%%%%%%%%%%%%%%%%%%%%=%%=%========*-.
 ..-=@@@@@@@@@@@@@@@@@@@@@@%@%%@@@%%%%%@%%@%%%%%%%%%%%====%%=%===%========*+:.
   :*%@@@@@@@@@@@@@@@@@@@@@%@@%%@%@@@%%@%%%%%%%%%%%%%%%%==%==%============*-:
   .+%@@@@@@@@@@@@@@@@@@@@@@@%%@%%%%%%%@%%%%%%%%%%%%%%%%=%%%%%%===========*:.
   .:*%@@@@@@@@@@@@@@@@%@%%@@@%%%%%%@@%%%%%%%%%%%=%==%=%%%%============*=*-:
    .+=@@@@@@@@@@@@@@@@@%@@%%%%@%%%%%%%%%%%%%%%%%%%=%%=%================**-..
    .:+%@@@@@@@@@@@@%@@@@%@%%@%%@%%%%%%%%%%%%%%%=%=%%=%%%============*=**-..
     .-*%%@@@@@@@@%@%@%%@%@@%@%%%%%%%%%%%%%=%=%%=%%=%==%==============**+:
      .:*%%%@@@%%%@%%%@%@%%%%%%%%%%%%%%%%%%%%%=%%=%%=================**-:
       .:*=%@@@%%%@@%%%@%%%%%%%%%%%%%%%%%%%=%%%==%%===%==========*==*+-:
         .-*%%%%@@%@%%%@%%%%%%%%%%%%%%%%%%%%%%=%================*=**+:..
         ..:-=%%%@@@@%%%%@%%%%%%%%%%%%=%%%%%%=%=%%%============**++:.
            .:-+*%%%%%%%%%%%%%%%%%%%%%%=%%==%==============*=*++-:.
               .::-*====%%%%%=%%=%%%=%%==%==============***++::..
                   .:::-+*+****===============*=****++---:......
                      . .....:::---------------:::.....
                               ..  . .  .    .

input · usd / 1m tok

$0.14

output · usd / 1m tok

$0.28

context window

1.02mtokens

modalities · in → out

pricing

base api ratesusd per 1m tokens

input: $0.14
output: $0.28
cache read: $0.003

providers

AtlasCloud hosts MiMo V2.5. Impossibl routes your request intelligently and handles failover automatically when a provider is down.

AtlasCloud

specifications

takes text and image in, gives text outxiaomi/mimo-v2.5

creatorXiaomi
model typeText generation
context window1,024,000 tokens
maximum outputnot published
input
takes text and image in, gives text out
outputtext
tool callingnot verified
releasedapr 23, 2026
endpoint/v1/chat/completions

unknown means the public catalog does not establish that fact. a model's documented capabilities can differ from what a particular api supports. see the model documentation for integration details.

try it · your prompt, this model, live

# responses API
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["IMPOSSIBL_API_KEY"],
    base_url="https://api.impossibl.com/v1",
)

resp = client.responses.create(
    model="xiaomi/mimo-v2.5",
    input="▌",
)
print(resp.output_text)

edit the prompt, then run

# responses API
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["IMPOSSIBL_API_KEY"],
    base_url="https://api.impossibl.com/v1",
)

resp = client.responses.create(
    model="xiaomi/mimo-v2.5",
    input="▌",
)
print(resp.output_text)

edit the prompt, then run

benchmarks

intelligence index

21.8#77 of 113 models on the gateway

coding index56.8#37 of 66
agentic index15.8#43 of 54
omniscience-9.8#54 of 90
gpqa84.9%#44 of 82
humanity’s last exam27.2%#58 of 93

Tau290.6%
GPQA84.9%
MMMU-Pro75.4%
AA-LCR73.0%
IFBench67.1%
SciCode43.9%
Terminal-Bench Hard41.7%
Humanity’s Last Exam27.2%
AutomationBench Partial18.4%
Tau Banking8.7%
GDP.pdf All-pass4.0%
CritPt3.7%

Intelligence Index21.82
Omniscience Index-9.83
GDPval Elo997.19
legal index (API)24.4
coding index (API)56.8
agentic index (API)15.8
economics index (API)33.9
engineering index (API)24.6
intelligence index (API)21.8
strategy and ops index (API)18.9
finance and accounting index (API)22.2

view source ↗all source data and breakdowns (json) ↗

each configuration is listed separately; these evaluations describe the tested model configuration, and performance and costs can differ on impossibl. unmeasured scores are omitted and api values keep their source units. last checked 2026-10-21.

compare MiMo V2.5 with other models

frontier labs and open weights, best-ranked firstusd / 1m tok · in / out

anthropic/claude-opus-5-5$4.00 / $20.00compare →
moonshotai/kimi-k3.1-pro$2.00 / $10.00compare →
openai/gpt-6-astra$10.00 / $50.00compare →
meta/muse-wonder$4.00 / $20.00compare →

impossibl models --all →

frequently asked questions

What is MiMo V2.5?

MiMo V2.5 is Xiaomi's native omnimodal model, perceiving images, video, audio, and text with native agent execution for tasks such as browsing. It sits on Xiaomi's performance-efficiency frontier, matching MiMo V2.5 Pro on daily tasks while surpassing MiMo V2 Omni in multimodal perception and long-range reasoning.

How much does MiMo V2.5 cost?

MiMo V2.5 costs $0.14 per million input tokens and $0.28 per million output tokens through the Impossibl API. Cache reads cost $0.003 per million tokens. All rates are in USD.

view the pricing table ↑

What is the context length of MiMo V2.5?

MiMo V2.5 has a 1,024,000-token context window through the Impossibl API.

What inputs and outputs does MiMo V2.5 support?

MiMo V2.5 accepts text and image as input. MiMo V2.5 returns text.

How do I use MiMo V2.5 through an API?

MiMo V2.5 is available through the Impossibl API. Use xiaomi/mimo-v2.5 as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.

follow the api quickstart →

When was MiMo V2.5 released?

Xiaomi released MiMo V2.5 on April 23, 2026.

Creator release announcement ↗

this page describes MiMo V2.5 as listed by the impossibl public api. prices and availability come from that catalog, refreshed here every five minutes. this is an impossibl offering, not a comparison of independent hosting-provider quotes. model descriptions and release dates, where available, use the creator sources linked under the answers above.

view the source catalog ↗model as markdown ↗report a correction →