Skip to content
ModelCap

Model decision surface

Compare AI models

Start with Inkling and Inkling Small, or choose any two current ranked language models. Compare capability evidence, price, context, provider availability, and weight access without pretending one field decides every use case.

Current public data

Inkling vs Inkling Small

Live dataset updated 11/7/2026, 2:00:08 PM UTC

Open 1200×630 evidence receipt
Factual comparison of Inkling and Inkling Small
Field
Inkling

Thinking Machines

Inkling Small

Thinking Machines

ModelCap position#57#107
Index score67.153.7
EvidenceMeasured4 public benchmark observations across 4 boardsMeasured4 public benchmark observations across 4 boards
Input / 1M$1.00$0.45
Output / 1M$4.05$1.20
Pricing statusfreshfresh
Context524K524K
Providers11
Weight accessOpen weightsOpen weights

Decision facts

  • Inkling is #57; Inkling Small is #107 on the same current language board.
  • Index scores are 67.1 for Inkling and 53.7 for Inkling Small. Their published uncertainty intervals do not overlap, but the aggregate Index does not predict performance on every task; compare the relevant benchmark configurations before choosing.
  • Both positions use Measured evidence.
  • Listed output price per 1M tokens is $4.05 for Inkling and $1.20 for Inkling Small. 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 $1.50 for Inkling Small. Inkling Small costs 62.7% less in this scenario. This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the selected endpoint before budgeting.
  • Published context is 524,288 tokens for Inkling and 524,288 for Inkling Small.

These are separate published fields, not a synthetic winner. ModelCap does not collapse price, access, context, and capability evidence into a hidden recommendation score.

Each comparison page is a permanent, shareable URL with the same live figures as this tool: ModelCap Index position, API pricing, context window, provider count, weight access and every shared benchmark board.