modelgrep
T

Thinking Machines: Inkling

thinkingmachines/inkling

27th smartest of 154ReasoningToolsVisionAudio
Use via OpenRouter ↗
Intelligence
40.7
27th of 154
Design Elo
Speed
tokens/sec
Latency
first token
Input price
$1.00
199th cheapest
Context
1.0M

How it compares

Smarter than82%
of all ranked models
Cheaper than35%
of all ranked models

Overview

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...

Benchmarks

independent · Artificial Analysis & Design Arena
Artificial Analysis92th percentile
Intelligence Index
40.7
Coding Index
52.1
GPQA Diamond
87%
Humanity's Last Exam
30%
SciCode
46%

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Together$1.00$4.0599.4%

Specifications

Context window1.0M
Max output
Knowledge cutoff
Input modalitiestext, image, audio
Output modalitiestext
Prompt caching
Cache read price$0.170/M
ModeratedNo

Inkling FAQ

How much does Inkling cost?

Inkling costs $1.00 per million input tokens and $4.05 per million output tokens via OpenRouter, making it 199th cheapest of 306 paid models.

How smart is Inkling?

Inkling scores 40.7 on the Artificial Analysis Intelligence Index, ranking 27th of 154 benchmarked models, with a GPQA Diamond score of 87%.

What is Inkling's context window?

Inkling supports a 1.0M-token context window. It accepts text, image, audio input.

Compare head-to-head