Inkling (Thinking Machines) and Inkling 2 Small (Thinking Machines) compared on the ModelCap Index, API price, context window, provider availability, weight access and every public benchmark board they share. Figures are the same ones shown on the live rankings; nothing here is a hidden score.
Snapshot as of 19 November 2026
As of 19 November 2026, Inkling holds the stronger ModelCap Index position (#62 vs #98); Inkling 2 Small is 4.1× cheaper per output token ($1.00/1M vs $4.05/1M); and Inkling 2 Small offers the longer context window (1M vs 524K tokens).
Evidence: 4 public benchmark observations across 4 boards · 5 public benchmark observations across 5 boards. Prices are the lowest listed API offer per million tokens observed on the OpenRouter catalogue.
Benchmark scores: Inkling vs Inkling 2 Small
Public benchmark boards where Inkling or Inkling 2 Small has a published result
Inkling ranks higher on the ModelCap Index as of 19 November 2026: #62 against #98. That is a capability ranking built from public benchmark evidence with published uncertainty; whether it is "better" for you also depends on price, context and where you can run it. Their published uncertainty intervals overlap, so the rank difference alone does not establish a reliable capability advantage for your workload.
Is Inkling cheaper than Inkling 2 Small?
Inkling 2 Small is cheaper on output tokens: $1.00/1M against $4.05/1M. Input tokens are $1.00/1M for Inkling and $0.30/1M for Inkling 2 Small. Prices are the lowest listed API offer ModelCap observed, in USD per million tokens. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $4.03 for Inkling versus $1.10 for Inkling 2 Small. Inkling 2 Small costs 72.7% less in this scenario. This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the selected endpoint before budgeting.
Which has the bigger context window, Inkling or Inkling 2 Small?
Inkling 2 Small has the larger context window: 1M tokens against 524K. OpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified.
Which is better for coding, Inkling or Inkling 2 Small?
Are Inkling and Inkling 2 Small open-weight models?
Inkling: Open weights. Inkling 2 Small: Open weights. Open weights mean the checkpoint can be downloaded and self-hosted under its licence. A missing weight link does not identify every API or chat product that offers a model.
Where can I run Inkling and Inkling 2 Small?
ModelCap currently lists 1 API provider for Inkling and 6 for Inkling 2 Small, from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.
How current is this Inkling vs Inkling 2 Small comparison?
Every figure and ModelCap Index position comes from the same published snapshot dated 19 November 2026. Publication and page updates happen separately; use the snapshot date shown on the page.