Kimi K2.6
Moonshot
moonshot/kimi-k2.6
K2.6 multimodal reasoning
Context Window
262K
262,144 tokens
Max Output
98K
98,304 tokens
About this model
Kimi K2.6 is the latest Kimi multimodal reasoning model available through Bailian, with 262K context, image-text input, and stronger coding and agent-task performance.
Use it for long-document analysis, complex coding, image understanding, and production workflows that need reliable tool use.
Highlights
262K context
Multimodal input
Strong coding
Tool use
Best For
Long-doc analysisComplex codingImage understandingAgent workflows
2026-04-24MoE TransformerProprietary
Capabilities
ChatVisionReasoningCodetoolscache
Pricing (per 1M tokens)
| Pricing (per 1M tokens) | / 1M tokens |
|---|---|
| Input / 1M | $0.948 |
| Output / 1M | $3.94 |
| Cache Read | $0.190 |
| Cache Write | $1.18 |
Final prices shown
Quick Start
main.py
from openai import OpenAI client = OpenAI( base_url="https://api.chuizi.ai/v1", api_key="ck-your-key-here", ) response = client.chat.completions.create( model="moonshot/kimi-k2.6", messages=[{"role": "user", "content": "Hello!"}], ) print(response.choices[0].message.content)