Effort: xhigh · Xhigh
thinkingmachinesReleased Jul 15, 2026
Thinking Machines: Inkling
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,...
Context window1M
Max output471.9K
Provider endpoints6
Benchmark results11
Measured performance
All leaderboards ↗Benchmark results
Effort: xhigh · Xhigh
GDPval-AA ↗2.1
1,076.19Effort: xhigh · Xhigh
AutomationBench-AA ↗AA Index 4.3.2 collection
4.98%Effort: xhigh · Xhigh
Effort: xhigh · Xhigh · Harness unreported
SciCode ↗AA Index 4.3.2 collection
46.99%AA · Under reviewEffort: xhigh · Xhigh
Humanity’s Last Exam ↗AA Index 4.3.2 collection
31.88%Effort: xhigh · Xhigh
GDP.pdf ↗AA Index 4.3.2 collection
12.8%Effort: xhigh · Xhigh
CritPt ↗AA Index 4.3.2 collection
5.43%AA · Under reviewEffort: xhigh · Xhigh
AA-Omniscience ↗AA Index 4.3.2 collection
2Effort: xhigh · Xhigh
AA-LCR ↗1.1
77.33%Effort: xhigh · Xhigh
Provider measurements
1 configurationSpeed
≈10K input tokens1 requestmedian / 72h
Artificial Analysis · first-party providers · serving endpoint not reported
Thinking Machines
Inkling (Xhigh)
Reasoning xhigh
- Output rate
- 197.032 tok/s
- Time to first chunk
- 1.80238 s
Last checked Source ↗
Methodology 2.2.0 & measurement details
First chunk includes request processing and network time, and may include reasoning.
- Prompt
- long · ≈10,000 input tokens
- Parallel requests
- 1
- Minimum answer
- 1,500 tokens
- Aggregation
- median over 72 hours
- Token counting
- o200k_base
- Benchmark client
- Google Cloud us-central1-a
- Serving endpoint
- Not reported
- Serving region
- Not reported
- Sample size
- Not reported
- Window end
- Not reported
Access & cost
6 quotesPrices across providers
Your token mix
USD · listed token ratesOpenRouter
Catalog quote- Input
- $1.00
- Output
- $4.05
- Cached input
- $0.17
together
via Hugging Face- Input
- $1.00
- Output
- $4.05
fireworks-ai
via Hugging Face- Input
- —
- Output
- —
deepinfra
via Hugging Face- Input
- $0.95
- Output
- $4.05
- Input
- $0.95
- Output
- $4.05
- Cached input
- $0.16
- Input
- $1.00
- Output
- $4.05
- Cached input
- $0.17
Model specifications
- Developer
- thinkingmachines
- Modality
- Language
- Context
- 1,048,576 tokens
- Maximum output
- 471,859 tokens
- Weights
- Open weights
- Released
- Jul 15, 2026
- Provider listed
- Jul 14, 2026
- First discovered
- Oct 16, 2026
Exact identities
- openrouter
thinkingmachines/inkling - huggingface
thinkingmachines/Inkling - artificial-analysis
0de09623-2b1a-4c8d-86ef-7f5245d4e24b
Sources
Updated Oct 17, 2026
More from thinkingmachines
View all ↗thinkingmachinesListed Jul 30
Thinking Machines: Inkling Small (free)
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...
1M contextImage inputAudio inputNo reported score
No reported score
$0.00in$0.00out/ 1M tokens · USDThinking Machines · via OpenRouter · 2 endpointsthinkingmachines/nvfp4 · quantization=nvfp4
thinkingmachinesListed Jul 27
Inkling-Small
Inkling-Small is a Mixture-of-Experts transformer with 276B total parameters, 12B active, trained on NVIDIA GB300 NVL72 systems. Like Inkling, it features native reasoning over audio and images, variable…
524.3K contextImage inputAudio inputNo reported score
No reported score
thinkingmachinesListed Jul 17
Thinking Machines: Inkling (free)
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…
1M contextImage inputAudio inputNo reported score
No reported score
$0.00in$0.00out/ 1M tokens · USDThinking Machines · via OpenRouter · 2 endpointsthinkingmachines/nvfp4 · quantization=nvfp4