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

OOpenRating
All models

Motif · Released Mar 1, 2026

Motif 3

Specialized foundation model tailored for document layout extraction, structured entity mapping, and business intelligence.

Proprietary

OpenRating Index

47.6

0–100 composite

Reasoning Index

64.6

0–100 composite

Cost / Task

$0.32

benchmark run

Output speed

111 tok/s

blended tok/s

Time to first token

0.6s

median latency

Input price

$0.18

per 1M tokens

Output price

$0.72

per 1M tokens

Context window

128K

tokens

Strengths

  • High accuracy on tabular data and complex layouts

  • Sub-$0.32 task cost for document processing

  • Deterministic structured output guarantees

How we rate Motif 3

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

47.6

Reasoning Index

64.6

Token Pricing

Input per 1M tokens

$0.18

Output per 1M tokens

$0.72

Cost of 1M input + 1M output

$0.9

Task Cost Economics

Empirical cost breakdown for a standard OpenRating Index benchmark task ($0.32 total).

Reasoning (Chain of Thought)
$0.083
Answer generation
$0.028
Cache write overhead
$0.062
Cache hit queries
$0.14
Input payload
$0.006