AI model comparison

DeepSeek V4 Pro 0423 vs Kimi K2 Thinking

Side by side comparison of DeepSeek V4 Pro 0423 and Kimi K2 Thinking on pricing, benchmark scores, context window, and more.

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window.

Input / 1M
$0.90
Output / 1M
$1.50
Context
1.05M

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning.

Input / 1M
$0.60
Output / 1M
$2.50
Context
262K

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

moonshotai logo

Kimi K2 Thinking

1.0x cheaper for a typical chat

Higher intelligence score

moonshotai logo

Kimi K2 Thinking

22 vs 20.8 on Artificial Analysis

Larger context window

deepseek logo

DeepSeek V4 Pro 0423

1.05M vs 262K tokens

Newer release

deepseek logo

DeepSeek V4 Pro 0423

Released April 24, 2026

Benchmarks

Benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

deepseek logoDeepSeek V4 Pro 042320.8
moonshotai logoKimi K2 Thinking22

Coding index

deepseek logoDeepSeek V4 Pro 042359.4
moonshotai logoKimi K2 Thinking21

Agentic index

deepseek logoDeepSeek V4 Pro 042326.3
moonshotai logoKimi K2 ThinkingNot available

Pricing

DeepSeek V4 Pro 0423 vs Kimi K2 Thinking API pricing

Per-token API rates. Cheaper option highlighted.

Metricdeepseek logoDeepSeek V4 Pro 0423moonshotai logoKimi K2 Thinking
Input tokensPer 1M tokens$0.90$0.60
Output tokensPer 1M tokens$1.50$2.50
Cached input (read)Per 1M tokens$0.20$0.15
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 Pro 0423$2.55
moonshotai logoKimi K2 Thinking$2.45

Coding task

30K in, 4K out

deepseek logoDeepSeek V4 Pro 0423$33$12 cached
moonshotai logoKimi K2 Thinking$28$14.50 cached

Long document summary

150K in, 2K out

deepseek logoDeepSeek V4 Pro 0423$138$33 cached
moonshotai logoKimi K2 Thinking$95$27.50 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 Pro 0423moonshotai logoKimi K2 Thinking
Context window1.05M tokens262K tokens
Max output393K tokens98K tokens
Input typesTextText
Output typesTextText
Reasoning effort levelsExtra high, High, NoneNot available
Default reasoning effortHighNot available
Release dateApril 24, 2026November 6, 2025

Features

Supported features

API features available for each model.

Metricdeepseek logoDeepSeek V4 Pro 0423moonshotai logoKimi K2 Thinking
Tool callingSupportedSupported
Structured outputsSupportedSupported
JSON modeSupportedSupported
ReasoningSupportedSupported
TemperatureSupportedSupported
Stop sequencesSupportedSupported
Deterministic seedSupportedSupported
Verbosity controlNot supportedNot supported

Our take

Kimi K2 Thinking is 1.0x cheaper for a typical chat. Kimi K2 Thinking scores higher on the Artificial Analysis Intelligence Index (22 vs 20.8). DeepSeek V4 Pro 0423 has the larger context window (1.05M vs 262K 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 Pro 0423 or Kimi K2 Thinking cheaper?

Kimi K2 Thinking is cheaper for a typical chat (2K input tokens and 500 output tokens). Kimi K2 Thinking costs $0.60 per 1M input tokens and $2.50 per 1M output tokens, while DeepSeek V4 Pro 0423 costs $0.90 per 1M input tokens and $1.50 per 1M output tokens.

Which has a bigger context window, DeepSeek V4 Pro 0423 or Kimi K2 Thinking?

DeepSeek V4 Pro 0423 supports up to 1.05M tokens of context, compared with 262K for Kimi K2 Thinking.

Is DeepSeek V4 Pro 0423 smarter than Kimi K2 Thinking?

On the Artificial Analysis Intelligence Index, DeepSeek V4 Pro 0423 scores 20.8 and Kimi K2 Thinking scores 22, putting Kimi K2 Thinking ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.

Can I use DeepSeek V4 Pro 0423 and Kimi K2 Thinking at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see DeepSeek V4 Pro 0423 and Kimi K2 Thinking answer side by side and keep the better response.

deepseek logomoonshotai logo

Why choose? Ask both.

Send one prompt to DeepSeek V4 Pro 0423 and Kimi K2 Thinking at the same time. Compare the answers side by side and keep the best one.