modelgrep
I

inclusionAI: Ring-2.6-1T

inclusionai/ring-2.6-1t

49th smartest of 180Cheaper than 89% of paidReasoningToolsJSON
Use via OpenRouter ↗
Intelligence
38.5
49th of 180
Design Elo
Speed
74
117th fastest
Latency
2.7s
first token
Input price
$0.075
32nd cheapest
Context
262K
66K max out

How it compares

Smarter than73%
of all ranked models
Faster than62%
of all ranked models
Cheaper than89%
of all ranked models

Overview

Ring-2.6-1T is a 1T-parameter-scale thinking model with 63B active parameters, built for real-world agent workflows that require both strong capability and operational efficiency. It is optimized for coding agents, tool...

Benchmarks

independent · via OpenRouter
Artificial Analysis69th percentile
Intelligence Index
38.5
Coding Index
33.3
Agentic Index
51.5
GPQA Diamond
86%
Humanity's Last Exam
18%
SciCode
42%
Tau²-Bench (agentic)
92%

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Novita$0.075$0.625100%

Specifications

Context window262K
Max output66K
Knowledge cutoff
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price$0.015/M
ModeratedNo

Ring-2.6-1T FAQ

How much does Ring-2.6-1T cost?

Ring-2.6-1T costs $0.075 per million input tokens and $0.625 per million output tokens via OpenRouter, making it 32nd cheapest of 298 paid models.

How smart is Ring-2.6-1T?

Ring-2.6-1T scores 38.5 on the Artificial Analysis Intelligence Index, ranking 49th of 180 benchmarked models, with a GPQA Diamond score of 86%.

How fast is Ring-2.6-1T?

Ring-2.6-1T generates around 74 tokens per second with 2.7s time-to-first-token (p50), the 117th fastest tracked model.

What is Ring-2.6-1T's context window?

Ring-2.6-1T supports a 262K-token context window and can output up to 66K tokens. It accepts text input.

Compare head-to-head