thinkingmachines/inkling-smallInkling-Small is Thinking Machines’s open-weights AI model, released Jul 15, 2026. It costs $0.50/M input and $1.20/M output tokens, and handles a 1M-token context window.
Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total.
Scores on standardized evaluations. Higher is better — and rank shows where Inkling-Small lands among all models tracked on Model Beat.
Abstract visual reasoning
Harder abstract reasoning
Graduate-level scientific reasoning
Frontier of human expert knowledge
Factual accuracy & hallucination
Scientific research coding
Human-rated web development
Olympiad-qualifier math
Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total.
Inkling-Small is an AI model developed by Thinking Machines, released Jul 15, 2026.
Inkling-Small is served from $0.50 per million input tokens and $1.20 per million output tokens (cheapest credible provider on OpenRouter: BaseTen).
Inkling-Small supports a context window of up to 1M tokens.
On standardized evaluations tracked by Epoch AI, Inkling-Small scores 49.7% on SciCode, 88.5% on GPQA Diamond, 33.3% on Humanity's Last Exam.
Inkling-Small is released with open weights (Open weights (unrestricted)), so the model can be downloaded and self-hosted.
Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Sep 16, 2026.