AI model comparison

MiMo-V2.5 vs GPT-5.1-Codex-Mini

Side by side comparison of MiMo-V2.5 and GPT-5.1-Codex-Mini on pricing, benchmark scores, context window, and more.

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

Input / 1M
$0.40
Output / 1M
$2
Context
1M

GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex

Input / 1M
$0.25
Output / 1M
$2
Context
400K

Comparing image generators? Compare image models

At a glance

Quick verdict

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

Lower price

openai logo

GPT-5.1-Codex-Mini

1.2x cheaper for a typical chat

Higher intelligence score

xiaomi logo

MiMo-V2.5

21.8 vs 20.4 on Artificial Analysis

Larger context window

xiaomi logo

MiMo-V2.5

1M vs 400K tokens

Newer release

xiaomi logo

MiMo-V2.5

Released April 22, 2026

Benchmarks

Benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

xiaomi logoMiMo-V2.521.8
openai logoGPT-5.1-Codex-Mini20.4

Coding index

xiaomi logoMiMo-V2.556.8
openai logoGPT-5.1-Codex-MiniNot available

Agentic index

xiaomi logoMiMo-V2.515.8
openai logoGPT-5.1-Codex-MiniNot available

Pricing

MiMo-V2.5 vs GPT-5.1-Codex-Mini API pricing

Per-token API rates. Cheaper option highlighted.

Metricxiaomi logoMiMo-V2.5openai logoGPT-5.1-Codex-Mini
Input tokensPer 1M tokens$0.40$0.25
Output tokensPer 1M tokens$2$2
Cached input (read)Per 1M tokens$0.08$0.03
Cache writePer 1M tokensNot availableNot available
Web searchPer requestNot available$0.01

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

xiaomi logoMiMo-V2.5$1.80
openai logoGPT-5.1-Codex-Mini$1.50

Coding task

30K in, 4K out

xiaomi logoMiMo-V2.5$20$10.40 cached
openai logoGPT-5.1-Codex-Mini$15.50$8.90 cached

Long document summary

150K in, 2K out

xiaomi logoMiMo-V2.5$64$16 cached
openai logoGPT-5.1-Codex-Mini$41.50$8.50 cached

Specs

Context window and capabilities

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

Metricxiaomi logoMiMo-V2.5openai logoGPT-5.1-Codex-Mini
Context window1M tokens400K tokens
Max output66K tokens128K tokens
Input typesAudio, Image, Text, VideoImage, Text
Output typesTextText
Reasoning effort levelsNot availableHigh, Medium, Low
Default reasoning effortNot availableMedium
Release dateApril 22, 2026November 13, 2025

Features

Supported features

API features available for each model.

Metricxiaomi logoMiMo-V2.5openai logoGPT-5.1-Codex-Mini
Tool callingSupportedSupported
Structured outputsSupportedSupported
JSON modeSupportedSupported
ReasoningSupportedSupported
TemperatureSupportedNot supported
Stop sequencesSupportedNot supported
Deterministic seedNot supportedSupported
Verbosity controlNot supportedSupported

Our take

GPT-5.1-Codex-Mini is 1.2x cheaper for a typical chat. MiMo-V2.5 scores higher on the Artificial Analysis Intelligence Index (21.8 vs 20.4). MiMo-V2.5 has the larger context window (1M vs 400K 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 MiMo-V2.5 or GPT-5.1-Codex-Mini cheaper?

GPT-5.1-Codex-Mini is cheaper for a typical chat (2K input tokens and 500 output tokens). GPT-5.1-Codex-Mini costs $0.25 per 1M input tokens and $2 per 1M output tokens, while MiMo-V2.5 costs $0.40 per 1M input tokens and $2 per 1M output tokens.

Which has a bigger context window, MiMo-V2.5 or GPT-5.1-Codex-Mini?

MiMo-V2.5 supports up to 1M tokens of context, compared with 400K for GPT-5.1-Codex-Mini.

Is MiMo-V2.5 smarter than GPT-5.1-Codex-Mini?

On the Artificial Analysis Intelligence Index, MiMo-V2.5 scores 21.8 and GPT-5.1-Codex-Mini scores 20.4, putting MiMo-V2.5 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.

Can I use MiMo-V2.5 and GPT-5.1-Codex-Mini at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see MiMo-V2.5 and GPT-5.1-Codex-Mini answer side by side and keep the better response.

xiaomi logoopenai logo

Why choose? Ask both.

Send one prompt to MiMo-V2.5 and GPT-5.1-Codex-Mini at the same time. Compare the answers side by side and keep the best one.