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.
Prices update automatically — checked hourly against provider list prices.
Independent benchmark scores for Ring-2.6-1T, measured by Artificial Analysis. Higher is better.
Ring-2.6-1T is a commercial AI model by InclusionAI. The specifications below are tracked automatically: pricing is refreshed hourly from public list prices, so the numbers on this page reflect the current cost of using the model through its API.
Ring-2.6-1T is an AI language model from InclusionAI. It is a proprietary model, available through an API. It scores 30.6 on the Artificial Analysis intelligence index.
Ring-2.6-1T is not free: it costs $0.08 per million input tokens and $0.63 per million output tokens. Open-weight alternatives can be self-hosted at no per-token cost.
Independent benchmarks from Artificial Analysis give it GPQA 85.7%, Humanity's Last Exam 18.3%, Long Context Reasoning 64.3%, SciCode 42.4%, IFBench 44.6%, τ²-Bench 92.4%, τ-Bench Banking 14.2%, Terminal-Bench 43.1%, Terminal-Bench Hard 28.8%. It is particularly used for code generation.
It generates about 130.6 tokens per second, with a median 1.82s delay before the first token. Measured independently by Artificial Analysis.