AI model comparison

Inkling Small vs DeepSeek V3.1

Side by side comparison of Inkling Small and DeepSeek V3.1 on pricing, benchmark scores, context window, and more.

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total.

Input / 1M
$0.45
Output / 1M
$1.20
Context
524K

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates.

Input / 1M
$0.25
Output / 1M
$0.95
Context
164K

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

deepseek logo

DeepSeek V3.1

1.5x cheaper for a typical chat

Higher intelligence score

deepseek logo

DeepSeek V3.1

13.7 vs 12.9 on Artificial Analysis

Larger context window

thinkingmachines logo

Inkling Small

524K vs 164K tokens

Newer release

thinkingmachines logo

Inkling Small

Released July 30, 2026

Benchmarks

Benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

thinkingmachines logoInkling Small12.9
deepseek logoDeepSeek V3.113.7

Coding index

thinkingmachines logoInkling Small52.9
deepseek logoDeepSeek V3.1Not available

Agentic index

thinkingmachines logoInkling Small23.5
deepseek logoDeepSeek V3.1Not available

Pricing

Inkling Small vs DeepSeek V3.1 API pricing

Per-token API rates. Cheaper option highlighted.

Metricthinkingmachines logoInkling Smalldeepseek logoDeepSeek V3.1
Input tokensPer 1M tokens$0.45$0.25
Output tokensPer 1M tokens$1.20$0.95
Cached input (read)Per 1M tokens$0.10$0.13
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 Small$1.50
deepseek logoDeepSeek V3.1$0.98

Coding task

30K in, 4K out

thinkingmachines logoInkling Small$18.30$7.80 cached
deepseek logoDeepSeek V3.1$11.30$7.70 cached

Long document summary

150K in, 2K out

thinkingmachines logoInkling Small$69.90$17.40 cached
deepseek logoDeepSeek V3.1$39.40$21.40 cached

Specs

Context window and capabilities

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

Metricthinkingmachines logoInkling Smalldeepseek logoDeepSeek V3.1
Context window524K tokens164K tokens
Max output262K tokens147K tokens
Input typesAudio, Image, TextText
Output typesTextText
Reasoning effort levelsMax, High, Medium, Low, Minimal, NoneNot available
Default reasoning effortHighNot available
Release dateJuly 30, 2026August 21, 2025

Features

Supported features

API features available for each model.

Metricthinkingmachines logoInkling Smalldeepseek logoDeepSeek V3.1
Tool callingSupportedSupported
Structured outputsNot supportedSupported
JSON modeNot supportedSupported
ReasoningSupportedSupported
TemperatureSupportedSupported
Stop sequencesSupportedSupported
Deterministic seedSupportedSupported
Verbosity controlNot supportedNot supported

Our take

DeepSeek V3.1 is 1.5x cheaper for a typical chat. DeepSeek V3.1 scores higher on the Artificial Analysis Intelligence Index (13.7 vs 12.9). Inkling Small has the larger context window (524K vs 164K 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 Small or DeepSeek V3.1 cheaper?

DeepSeek V3.1 is cheaper for a typical chat (2K input tokens and 500 output tokens). DeepSeek V3.1 costs $0.25 per 1M input tokens and $0.95 per 1M output tokens, while Inkling Small costs $0.45 per 1M input tokens and $1.20 per 1M output tokens.

Which has a bigger context window, Inkling Small or DeepSeek V3.1?

Inkling Small supports up to 524K tokens of context, compared with 164K for DeepSeek V3.1.

Is Inkling Small smarter than DeepSeek V3.1?

On the Artificial Analysis Intelligence Index, Inkling Small scores 12.9 and DeepSeek V3.1 scores 13.7, putting DeepSeek V3.1 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.

Can I use Inkling Small and DeepSeek V3.1 at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Inkling Small and DeepSeek V3.1 answer side by side and keep the better response.

thinkingmachines logodeepseek logo

Why choose? Ask both.

Send one prompt to Inkling Small and DeepSeek V3.1 at the same time. Compare the answers side by side and keep the best one.