kimi/kimi-k2.6

Updated at:

Kimi K2.6 is the latest and most advanced model in the Kimi series, featuring comprehensive enhancements in general-purpose agent capabilities, coding, and visual understanding. It achieves industry-leading results across multiple benchmarks, including the PhD-level full version of Humanity's Last Exam, SWE-Bench Pro for real-world software engineering, and DeepSearchQA for agent deep retrieval. The model supports text, image, and video inputs, offers both thinking and non-thinking modes, and handles conversational and agent tasks.

Inference Service Provider

The inference service provider for kimi/kimi-k2.6 is Moonshot AI.

Model Capabilities

CapabilitySupportCapabilitySupport

Input Modality

Text Image Video

Output Modality

Text

Model Experience

Unsupported

Function Calling

Supported

Structured Outputs

Supported

Web Search

Unsupported

Prefix Completion

Supported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Context Limits

ParameterValueParameterValue

Max Input Length

262144

Max Output Length

262144

Context Window

262144

Max Input Length (Thinking Mode)

262144

Max Output Length (Thinking Mode)

262144

Max Chain-of-Thought Length

262144

Pricing

This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.

China (Beijing)

Billing ItemPrice (CNY)Unit

Input

6.5

Per 1M tokens

Output

27

Per 1M tokens

Input(Implicit Cache)

1.1

Per 1M tokens

Rate Limits

China (Beijing)

ParameterValue

RPM (Requests Per Minute)

500

TPM (Tokens Per Minute)

3,000,000