OpenRating is an independent, open-source AI rating platform. Join the community

OOpenRating
All models

Inkling · Released Jan 25, 2026

Inkling

Compact AI model specializing in knowledge base indexing, semantic question answering, and customer support automations.

Proprietary

OpenRating Index

42.5

0–100 composite

Reasoning Index

58.9

0–100 composite

Cost / Task

$0.34

benchmark run

Output speed

81 tok/s

blended tok/s

Time to first token

0.6s

median latency

Input price

$0.15

per 1M tokens

Output price

$0.6

per 1M tokens

Context window

128K

tokens

Strengths

  • Strong domain knowledge alignment for support workflows

  • Effective prompt caching utilization

  • Clean integration into RAG knowledge graphs

How we rate Inkling

OpenRating scores every model on the same axes. The OpenRating Index is a weighted composite of reasoning, knowledge, and agentic benchmarks, normalised to a 0–100 scale. Speed is blended output measured in tokens per second under standardised load, with time-to-first-token reported separately. Prices are list input and output prices per million tokens, and Task Cost measures end-to-end workload spending.

OpenRating Index

42.5

Reasoning Index

58.9

Token Pricing

Input per 1M tokens

$0.15

Output per 1M tokens

$0.6

Cost of 1M input + 1M output

$0.75

Task Cost Economics

Empirical cost breakdown for a standard OpenRating Index benchmark task ($0.34 total).

Reasoning (Chain of Thought)
$0.080
Answer generation
$0.025
Cache write overhead
$0.053
Cache hit queries
$0.17
Input payload
$0.006