Back to Explore
Inkling
Thinking Machines·Released 2026-07-15
Comparison data ready73% coverage12/12 fields directly observedUpdated Jul 16, 2026, 6:00 AM
Pricing
Input
$1.87
per 1M tokens
Output
$4.68
per 1M tokens
Blended
$2.57
per 1M tokens
Cheaper than 26% of models. Median price is $0.68/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$2.57
Monthly
$77.16
vs. Similar Models
Claude Opus 4.5 (Reasoning)Q:+0.1
$10.00+289%
DeepSeek V4 Pro (Reasoning, High Effort)Q:+0.1
$0.54-79%
GPT-5.6 Terra (low)Q:-0.2
$5.63+119%
Nex AGI: Nex-N2-ProQ:+0.3
$0.44-83%
Performance
83
tokens/sec
Faster than 45% of models
1.63
seconds
Faster than 32% of models
25.72
seconds
Faster than 22% of models
Market Median
93 tok/s
11% slower
Median TTFT
1.10s
48% slower
Throughput/Dollar
32
tok/s per $/1M
Speed Comparison
Grok 4.1 Fast (Non-reasoning)
83 tok/s-0%
Magistral Small 1.2
83 tok/s-0%
Mistral: Mistral Medium 3.1
84 tok/s+1%
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
87.2%
HLE
29.7%
LiveCodeBenchNot evaluated
SciCode
46.1%
TerminalBench HardNot evaluated
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBenchNot evaluated
Long Context Recall
63.3%
Tau2Not evaluated
Market AverageTop Score