modelgrep
T

Thinking Machines: Inkling Small

thinkingmachines/inkling-small

42nd smartest of 184ReasoningVisionAudio
Use via OpenRouter ↗
Intelligence
40.2
42nd of 184
Design Elo
Speed
tokens/sec
Latency
first token
Input price
$0.580
181st cheapest
Context
524K
262K max out

How it compares

Smarter than77%
of all ranked models
Cheaper than45%
of all ranked models

Overview

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

Benchmarks

independent · Artificial Analysis & Design Arena
Artificial Analysis90th percentile
Intelligence Index
40.2
Coding Index
52.9
GPQA Diamond
90%
Humanity's Last Exam
32%
SciCode
49%

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
DeepInfrafp8$0.580$1.44100%

Specifications

Context window524K
Max output262K
Knowledge cutoff
Input modalitiestext, image, audio
Output modalitiestext
Prompt caching
Cache read price$0.116/M
ModeratedNo

Inkling Small FAQ

How much does Inkling Small cost?

Inkling Small costs $0.580 per million input tokens and $1.44 per million output tokens via OpenRouter, making it 181st cheapest of 332 paid models.

How smart is Inkling Small?

Inkling Small scores 40.2 on the Artificial Analysis Intelligence Index, ranking 42nd of 184 benchmarked models, with a GPQA Diamond score of 90%.

What is Inkling Small's context window?

Inkling Small supports a 524K-token context window and can output up to 262K tokens. It accepts text, image, audio input.

Compare head-to-head