Shortcut ChatShortcut Chat
Get started

AI model comparison

Inkling vs DeepSeek V4 Flash 0423

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

thinkingmachines logo

Thinking Machines

Inkling

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total.

Input / 1M
$1
Output / 1M
$4.05
Context
524K
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

At a glance

Quick verdict

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

Lower price

deepseek logo

DeepSeek V4 Flash 0423

6.1x cheaper for a typical chat

Higher intelligence score

thinkingmachines logo

Inkling

25 vs 24.4 on Artificial Analysis

Larger context window

deepseek logo

DeepSeek V4 Flash 0423

1.05M vs 524K tokens

Newer release

thinkingmachines logo

Inkling

Released July 17, 2026

Benchmarks

Benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

thinkingmachines logoInkling25
deepseek logoDeepSeek V4 Flash 042324.4

Coding index

thinkingmachines logoInkling52.1
deepseek logoDeepSeek V4 Flash 042352

Agentic index

thinkingmachines logoInkling22.5
deepseek logoDeepSeek V4 Flash 042326.3

Pricing

Inkling vs DeepSeek V4 Flash 0423 API pricing

Per-token API rates. Cheaper option highlighted.

Metricthinkingmachines logoInklingdeepseek logoDeepSeek V4 Flash 0423
Input tokensPer 1M tokens$1$0.01
Output tokensPer 1M tokens$4.05$1.28
Cached input (read)Per 1M tokens$0.17$0.01
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

thinkingmachines logoInkling$4.03
deepseek logoDeepSeek V4 Flash 0423$0.66

Coding task

30K in, 4K out

thinkingmachines logoInkling$46.20$21.30 cached
deepseek logoDeepSeek V4 Flash 0423$5.42$5.42 cached

Long document summary

150K in, 2K out

thinkingmachines logoInkling$158.10$33.60 cached
deepseek logoDeepSeek V4 Flash 0423$4.05$4.05 cached

Specs

Context window and capabilities

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

Metricthinkingmachines logoInklingdeepseek logoDeepSeek V4 Flash 0423
Context window524K tokens1.05M tokens
Max output472K tokens944K tokens
Input typesAudio, Image, TextText
Output typesTextText
Reasoning effort levelsMax, High, Medium, Low, Minimal, NoneExtra high, High
Default reasoning effortHighHigh
Release dateJuly 17, 2026April 24, 2026

Features

Supported features

API features available for each model.

Metricthinkingmachines logoInklingdeepseek logoDeepSeek V4 Flash 0423
Tool callingSupportedSupported
Structured outputsNot supportedSupported
JSON modeNot supportedSupported
ReasoningSupportedSupported
TemperatureSupportedSupported
Stop sequencesSupportedSupported
Deterministic seedSupportedSupported
Verbosity controlNot supportedNot supported

Our take

DeepSeek V4 Flash 0423 is 6.1x cheaper for a typical chat. Inkling scores higher on the Artificial Analysis Intelligence Index (25 vs 24.4). DeepSeek V4 Flash 0423 has the larger context window (1.05M vs 524K 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 Inkling or DeepSeek V4 Flash 0423 cheaper?

DeepSeek V4 Flash 0423 is cheaper for a typical chat (2K input tokens and 500 output tokens). DeepSeek V4 Flash 0423 costs $0.01 per 1M input tokens and $1.28 per 1M output tokens, while Inkling costs $1 per 1M input tokens and $4.05 per 1M output tokens.

Which has a bigger context window, Inkling or DeepSeek V4 Flash 0423?

DeepSeek V4 Flash 0423 supports up to 1.05M tokens of context, compared with 524K for Inkling.

Is Inkling smarter than DeepSeek V4 Flash 0423?

On the Artificial Analysis Intelligence Index, Inkling scores 25 and DeepSeek V4 Flash 0423 scores 24.4, putting Inkling ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.

Can I use Inkling and DeepSeek V4 Flash 0423 at the same time?

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

thinkingmachines logodeepseek logo

Why choose? Ask both.

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

Get startedSee a preview