token.app › Thinkingmachines › Inkling Small
Inkling Small pricing & benchmarks
Inkling Small is available from Thinkingmachines at $0.450 per million input tokens and $1.20 per million output tokens ($0.637 blended at 3:1). It accepts up to 524,288 tokens of context. 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...
Pricing
Per million tokens · OpenRouter
Input$0.450
Output$1.20
Blended (3:1)$0.637
Specification
thinkingmachines/inkling-small
Context window524K
Max output262K
ReleasedJul 2026
LicenceOpen weights
Modalitiesin:text, in:image, in:audio, out:text
Benchmarks
Independently run — not vendor self-reports. Every score links its source.
| Benchmark | Score | Config | Run | Source |
|---|---|---|---|---|
| GPQA Diamond | 88.5% ±1.9 | xhigh effort | 2026-08-14 | Independently run · Epoch AI |
| FrontierMath T1–3 | 46.3% ±3.0 | xhigh effort | 2026-08-14 | Independently run · Epoch AI |
| FrontierMath T4 | 17.1% ±5.9 | xhigh effort | 2026-08-14 | Independently run · Epoch AI |
| OTIS Mock AIME | 90.0% ±4.0 | xhigh effort | 2026-08-14 | Independently run · Epoch AI |
Scores published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0.
Cheaper models that score at least as well on GPQA Diamond
Strictly lower blended price AND an equal-or-higher GPQA Diamond score. One benchmark is one dimension — a model that wins here may still be weaker at your specific task.
| Model | Provider | Blended $/1M | GPQA Diamond | |
|---|---|---|---|---|
| GPT-5.6 Luna | OpenAI | $0.450 (−29%) | 91.6% | Compare → |
| MiniMax M3 | MiniMax | $0.525 (−18%) | 90.9% | Compare → |
Compare Inkling Small
FAQ
How much does Inkling Small cost?
Inkling Small costs $0.450 per million input tokens and $1.20 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.637 per million tokens.
What is Inkling Small's context window?
Inkling Small accepts up to 524,288 tokens of context, and can generate up to 262,144 output tokens.
How good is Inkling Small on benchmarks?
Inkling Small scores 88.5% on GPQA Diamond, independently run and published by Epoch AI. 4 benchmark results are listed on this page, each with its run date and source.
Is there a cheaper model as good as Inkling Small?
Yes — 2 models in our catalogue cost less per token than Inkling Small and score at least as high on the same benchmark. The cheapest is GPT-5.6 Luna at $0.450 per million tokens blended.