AI model comparison

Kimi K3 vs Gemini 2.5 Pro

Side by side comparison of Kimi K3 and Gemini 2.5 Pro on pricing, benchmark scores, context window, and more.

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.

Input / 1M
$0.19
Output / 1M
$16
Context
1.05M

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks.

Input / 1M
$1.25
Output / 1M
$10
Context
1.05M

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

google logo

Gemini 2.5 Pro

1.1x cheaper for a typical chat

Higher intelligence score

moonshotai logo

Kimi K3

17.4 vs 16.1 on Artificial Analysis

Larger context window

Tie

1.05M vs 1.05M tokens

Newer release

moonshotai logo

Kimi K3

Released July 16, 2026

Benchmarks

Benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

moonshotai logoKimi K317.4
google logoGemini 2.5 Pro16.1

Coding index

moonshotai logoKimi K372
google logoGemini 2.5 Pro33.3

Agentic index

moonshotai logoKimi K329.3
google logoGemini 2.5 Pro1.6

Pricing

Kimi K3 vs Gemini 2.5 Pro API pricing

Per-token API rates. Cheaper option highlighted.

Metricmoonshotai logoKimi K3google logoGemini 2.5 Pro
Input tokensPer 1M tokens$0.19$1.25
Output tokensPer 1M tokens$16$10
Cached input (read)Per 1M tokens$0.18$0.13
Cache writePer 1M tokensNot available$0.38
Long-context pricingPer 1M tokens, for very long promptsSame rate at any length$2.50 in / $15 out above 200K
Web searchPer requestNot available$0.014

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

moonshotai logoKimi K3$8.38
google logoGemini 2.5 Pro$7.50

Coding task

30K in, 4K out

moonshotai logoKimi K3$69.76$69.46 cached
google logoGemini 2.5 Pro$77.50$43.75 cached

Long document summary

150K in, 2K out

moonshotai logoKimi K3$60.80$59.30 cached
google logoGemini 2.5 Pro$207.50$38.75 cached

Specs

Context window and capabilities

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

Metricmoonshotai logoKimi K3google logoGemini 2.5 Pro
Context window1.05M tokens1.05M tokens
Max output944K tokens66K tokens
Input typesImage, Text, VideoAudio, File, Image, Text, Video
Output typesTextText
Reasoning effort levelsMax, High, Low, NoneNot available
Default reasoning effortMaxNot available
Release dateJuly 16, 2026June 17, 2025

Features

Supported features

API features available for each model.

Metricmoonshotai logoKimi K3google logoGemini 2.5 Pro
Tool callingSupportedSupported
Structured outputsSupportedSupported
JSON modeSupportedSupported
ReasoningSupportedSupported
TemperatureSupportedSupported
Stop sequencesSupportedNot supported
Deterministic seedSupportedSupported
Verbosity controlNot supportedNot supported

Our take

Gemini 2.5 Pro is 1.1x cheaper for a typical chat. Kimi K3 scores higher on the Artificial Analysis Intelligence Index (17.4 vs 16.1). 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 Kimi K3 or Gemini 2.5 Pro cheaper?

Gemini 2.5 Pro is cheaper for a typical chat (2K input tokens and 500 output tokens). Gemini 2.5 Pro costs $1.25 per 1M input tokens and $10 per 1M output tokens, while Kimi K3 costs $0.19 per 1M input tokens and $16 per 1M output tokens.

Which has a bigger context window, Kimi K3 or Gemini 2.5 Pro?

Kimi K3 supports up to 1.05M tokens of context, compared with 1.05M for Gemini 2.5 Pro.

Is Kimi K3 smarter than Gemini 2.5 Pro?

On the Artificial Analysis Intelligence Index, Kimi K3 scores 17.4 and Gemini 2.5 Pro scores 16.1, putting Kimi K3 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.

Can I use Kimi K3 and Gemini 2.5 Pro at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Kimi K3 and Gemini 2.5 Pro answer side by side and keep the better response.

moonshotai logogoogle logo

Why choose? Ask both.

Send one prompt to Kimi K3 and Gemini 2.5 Pro at the same time. Compare the answers side by side and keep the best one.