thinkingmachines logo

Thinking Machines

Inkling Small

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

At a glance

Input / 1M
$0.45
Output / 1M
$1.20
Context
524K
Max output
262K
Intelligence
25.7
Released
Jul 2026
Text inputImage inputAudio inputReasoningTool callingFree tier

Pricing

Inkling Small API pricing

Per-token rates, plus what common tasks actually cost.

Input tokensPer 1M tokens$0.45
Output tokensPer 1M tokens$1.20
Cached input (read)Per 1M tokens$0.10
Cache writePer 1M tokensNot available

Chat message

2K in, 500 out

$1.50

per 1,000 requests

Coding task

30K in, 4K out

$18.30

per 1,000 requests

Long document summary

150K in, 2K out

$69.90

per 1,000 requests

Benchmarks

Inkling Small benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

25.7

Coding index

52.9

Agentic index

23.5

Specs

Context window and capabilities

What it can read, what it can write, and which API features it supports.

Context window
524K tokens
Max output
262K tokens
Input types
Audio, Image, Text
Output types
Text
Reasoning effort
Max, High, Medium, Low, Minimal, None
Release date
July 30, 2026
  • Tool calling
  • Structured outputs
  • JSON mode
  • Reasoning
  • Temperature
  • Stop sequences
  • Deterministic seed
  • Verbosity control

FAQ

Frequently asked questions

How much does Inkling Small cost?

Inkling Small costs $0.45 per 1M input tokens and $1.20 per 1M output tokens through the API. A typical chat message costs about $1.50 per 1,000 messages.

What is the context window of Inkling Small?

Inkling Small accepts up to 524K tokens of input and can write up to 262K tokens in a single response.

What is the best alternative to Inkling Small?

MiniMax M3 from MiniMax is a strong alternative. It offers: higher intelligence score, larger 1.05m context, accepts video.

Can I use Inkling Small alongside other models?

Yes. Shortcut Chat sends one prompt to Inkling Small and any other models you pick at the same time, so you can compare answers side by side.

thinkingmachines logo

Try Inkling Small next to every other model.

Use Inkling Small alongside all the other models. Use one at a time, or multiple together. Get the best answer from every AI.