Back to Explore
Inkling Small
Thinking Machines·Released 2026-07-30
Public weightsTrending266B524K ctxApache 2.0Multimodal
Comparable data available93% coverage21/21 fields directly observedUpdated Jul 31, 2026, 6:15 PM
About
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...
Related Models
Pricing
Input
$0.58
per 1M tokens
Output
$1.44
per 1M tokens
Blended
$0.80
per 1M tokens
Cheaper than 52% of models. Median price is $0.85/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.80
Monthly
$23.85
vs. Similar Models
GLM-5.1 (Reasoning)Q:0.0
$2.13+169%
DeepSeek V4 Flash (Reasoning, Max Effort)Q:+0.1
$0.17-78%
GPT-5.2 Codex (xhigh)Q:-0.1
$4.81+505%
GPT-5.4 mini (xhigh)Q:-0.2
$1.69+112%
Performance
95
tokens/sec
Faster than 49% of models
1.71
seconds
Faster than 36% of models
22.87
seconds
Faster than 23% of models
Market Median
101 tok/s
7% slower
Median TTFT
1.26s
36% slower
Throughput/Dollar
119
tok/s per $/1M
Speed Comparison
Reka Flash 3
93 tok/s-2%
Magistral Small 1.2
93 tok/s-2%
Ministral 3 8B
91 tok/s-3%
Context Window
524K
tokens
Larger than 74% of models
Max Output
262K
tokens
50% of context
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
89.5%
HLE
31.6%
LiveCodeBenchNot evaluated
SciCode
48.7%
TerminalBench HardNot evaluated
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBenchNot evaluated
Long Context Recall
63.0%
Tau2Not evaluated
Market AverageTop Score