Shortcut ChatShortcut Chat
Get started

AI model comparison

DeepSeek V4 Flash 0423 vs MiMo-V2.5

Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.

deepseek logo

DeepSeek

DeepSeek V4 Flash 0423

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.

Input / 1M
$0.01
Output / 1M
$1.28
Context
1.05M
xiaomi logo

Xiaomi

MiMo-V2.5

MiMo-V2.5 is a native omnimodal model by Xiaomi.

Input / 1M
$0.14
Output / 1M
$0.28
Context
1.05M

At a glance

Quick verdict

How the two models stack up on the things people ask about most.

Lower price

xiaomi logo

MiMo-V2.5

1.6x cheaper for a typical chat

Higher intelligence score

xiaomi logo

MiMo-V2.5

25.2 vs 24.4 on Artificial Analysis

Larger context window

xiaomi logo

MiMo-V2.5

1.05M vs 1.05M tokens

Newer release

deepseek logo

DeepSeek V4 Flash 0423

Released April 24, 2026

Benchmarks

Benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

deepseek logoDeepSeek V4 Flash 042324.4
xiaomi logoMiMo-V2.525.2

Coding index

deepseek logoDeepSeek V4 Flash 042352
xiaomi logoMiMo-V2.556.8

Agentic index

deepseek logoDeepSeek V4 Flash 042326.3
xiaomi logoMiMo-V2.515.8

Pricing

DeepSeek V4 Flash 0423 vs MiMo-V2.5 API pricing

Per-token API rates. Cheaper option highlighted.

Metricdeepseek logoDeepSeek V4 Flash 0423xiaomi logoMiMo-V2.5
Input tokensPer 1M tokens$0.01$0.14
Output tokensPer 1M tokens$1.28$0.28
Cached input (read)Per 1M tokens$0.01$0.00
Cache writePer 1M tokensNot availableNot available

What it costs in practice

Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.

Chat message

2K in, 500 out

deepseek logoDeepSeek V4 Flash 0423$0.66
xiaomi logoMiMo-V2.5$0.42

Coding task

30K in, 4K out

deepseek logoDeepSeek V4 Flash 0423$5.42$5.42 cached
xiaomi logoMiMo-V2.5$5.32$1.20 cached

Long document summary

150K in, 2K out

deepseek logoDeepSeek V4 Flash 0423$4.05$4.05 cached
xiaomi logoMiMo-V2.5$21.56$0.98 cached

Specs

Context window and capabilities

How much each model can read, how much it can write, and what it accepts as input.

Metricdeepseek logoDeepSeek V4 Flash 0423xiaomi logoMiMo-V2.5
Context window1.05M tokens1.05M tokens
Max output944K tokens131K tokens
Input typesTextAudio, Image, Text, Video
Output typesTextText
Reasoning effort levelsExtra high, HighNot available
Default reasoning effortHighNot available
Release dateApril 24, 2026April 22, 2026

Features

Supported features

API features available for each model.

Metricdeepseek logoDeepSeek V4 Flash 0423xiaomi logoMiMo-V2.5
Tool callingSupportedSupported
Structured outputsSupportedSupported
JSON modeSupportedSupported
ReasoningSupportedSupported
TemperatureSupportedSupported
Stop sequencesSupportedSupported
Deterministic seedSupportedSupported
Verbosity controlNot supportedNot supported

Our take

MiMo-V2.5 is 1.6x cheaper for a typical chat. MiMo-V2.5 scores higher on the Artificial Analysis Intelligence Index (25.2 vs 24.4). MiMo-V2.5 has the larger context window (1.05M vs 1.05M tokens). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.

FAQ

Frequently asked questions

Is DeepSeek V4 Flash 0423 or MiMo-V2.5 cheaper?

MiMo-V2.5 is cheaper for a typical chat (2K input tokens and 500 output tokens). MiMo-V2.5 costs $0.14 per 1M input tokens and $0.28 per 1M output tokens, while DeepSeek V4 Flash 0423 costs $0.01 per 1M input tokens and $1.28 per 1M output tokens.

Which has a bigger context window, DeepSeek V4 Flash 0423 or MiMo-V2.5?

MiMo-V2.5 supports up to 1.05M tokens of context, compared with 1.05M for DeepSeek V4 Flash 0423.

Is DeepSeek V4 Flash 0423 smarter than MiMo-V2.5?

On the Artificial Analysis Intelligence Index, DeepSeek V4 Flash 0423 scores 24.4 and MiMo-V2.5 scores 25.2, putting MiMo-V2.5 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.

Can I use DeepSeek V4 Flash 0423 and MiMo-V2.5 at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see DeepSeek V4 Flash 0423 and MiMo-V2.5 answer side by side and keep the better response.

deepseek logoxiaomi logo

Why choose? Ask both.

Send one prompt to DeepSeek V4 Flash 0423 and MiMo-V2.5 at the same time. Compare the answers side by side and keep the best one.

Get startedSee a preview