Kimi logo

K2.6 (Non-reasoning) – Benchmarks, Pricing & Intelligence Analysis

Not available on LLMBase

K2.6 (Non-reasoning) is not currently available in LLMBase Chat or the LLMBase Inference API. Benchmarks, pricing, and model details remain available for research and comparison.

Input Price$0.95/1M tokens
Output Price$4.00/1M tokens
Intelligence34.6
CodingN/A

Specifications

Technical details and pricing.

ProviderKimi
Context WindowN/A
Release DateApr 20, 2026
ModalitiesText
AvailabilityNot available

Benchmarks

7 benchmark scores from Artificial Analysis.

GPQA78.8%
HLE18.2%
SciCode39.5%
LCR57.7%
IFBench44.3%
Tau293.9%
TerminalBench Hard37.9%

Composite Indices

Higher is better; speed and price are normalized

Standard Benchmarks

Only benchmarks with data are shown

Frequently Asked Questions

What is K2.6 (Non-reasoning) good for?

K2.6 (Non-reasoning) currently has benchmark and pricing data on this page. Runtime metadata will appear later when the model catalog entry becomes available.

How much does K2.6 (Non-reasoning) cost?

Pricing is based on usage. Current rates are $0.95/1M tokens for input and $4.00/1M tokens for output.

Is K2.6 (Non-reasoning) available in LLMBase Chat yet?

Not yet on this page. We will add chat and inference actions automatically once an exact catalog entry exists for K2.6 (Non-reasoning).

Does K2.6 (Non-reasoning) support images or audio?

K2.6 (Non-reasoning) focuses on text-based tasks.

Benchmarks and pricing use Artificial Analysis where available. Catalog specs are used as a fallback.