AI model comparison

Inkling Small vs Qwen3 235B A22B Instruct 2507

Side by side comparison of Inkling Small and Qwen3 235B A22B Instruct 2507 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

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass.

Input / 1M
$0.14
Output / 1M
$0.80
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

qwen logo

Qwen3 235B A22B Instruct 2507

2.2x cheaper for a typical chat

Higher intelligence score

thinkingmachines logo

Inkling Small

12.9 vs 12 on Artificial Analysis

Larger context window

thinkingmachines logo

Inkling Small

524K vs 262K 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
qwen logoQwen3 235B A22B Instruct 250712

Coding index

thinkingmachines logoInkling Small52.9
qwen logoQwen3 235B A22B Instruct 2507Not available

Agentic index

thinkingmachines logoInkling Small23.5
qwen logoQwen3 235B A22B Instruct 2507Not available

Pricing

Inkling Small vs Qwen3 235B A22B Instruct 2507 API pricing

Per-token API rates. Cheaper option highlighted.

Metricthinkingmachines logoInkling Smallqwen logoQwen3 235B A22B Instruct 2507
Input tokensPer 1M tokens$0.45$0.14
Output tokensPer 1M tokens$1.20$0.80
Cached input (read)Per 1M tokens$0.10$0.05
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
qwen logoQwen3 235B A22B Instruct 2507$0.68

Coding task

30K in, 4K out

thinkingmachines logoInkling Small$18.30$7.80 cached
qwen logoQwen3 235B A22B Instruct 2507$7.40$4.70 cached

Long document summary

150K in, 2K out

thinkingmachines logoInkling Small$69.90$17.40 cached
qwen logoQwen3 235B A22B Instruct 2507$22.60$9.10 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 Smallqwen logoQwen3 235B A22B Instruct 2507
Context window524K tokens262K tokens
Max output262K tokens118K tokens
Input typesAudio, Image, TextText
Output typesTextText
Reasoning effort levelsMax, High, Medium, Low, Minimal, NoneNot available
Default reasoning effortHighNot available
Release dateJuly 30, 2026July 21, 2025

Features

Supported features

API features available for each model.

Metricthinkingmachines logoInkling Smallqwen logoQwen3 235B A22B Instruct 2507
Tool callingSupportedSupported
Structured outputsNot supportedSupported
JSON modeNot supportedSupported
ReasoningSupportedNot supported
TemperatureSupportedSupported
Stop sequencesSupportedSupported
Deterministic seedSupportedSupported
Verbosity controlNot supportedNot supported

Our take

Qwen3 235B A22B Instruct 2507 is 2.2x cheaper for a typical chat. Inkling Small scores higher on the Artificial Analysis Intelligence Index (12.9 vs 12). Inkling Small has the larger context window (524K 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 Inkling Small or Qwen3 235B A22B Instruct 2507 cheaper?

Qwen3 235B A22B Instruct 2507 is cheaper for a typical chat (2K input tokens and 500 output tokens). Qwen3 235B A22B Instruct 2507 costs $0.14 per 1M input tokens and $0.80 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 Qwen3 235B A22B Instruct 2507?

Inkling Small supports up to 524K tokens of context, compared with 262K for Qwen3 235B A22B Instruct 2507.

Is Inkling Small smarter than Qwen3 235B A22B Instruct 2507?

On the Artificial Analysis Intelligence Index, Inkling Small scores 12.9 and Qwen3 235B A22B Instruct 2507 scores 12, putting Inkling Small ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.

Can I use Inkling Small and Qwen3 235B A22B Instruct 2507 at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Inkling Small and Qwen3 235B A22B Instruct 2507 answer side by side and keep the better response.

thinkingmachines logoqwen logo

Why choose? Ask both.

Send one prompt to Inkling Small and Qwen3 235B A22B Instruct 2507 at the same time. Compare the answers side by side and keep the best one.