Kimi K2.5
Moonshot
moonshot/kimi-k2.5
Reasoning model, 262K context
Context Window
262K
262,144 tokens
Max Output
16K
16,384 tokens
About this model
Kimi K2.5, multimodal flagship with 262K context
This model supports up to 262K tokens of context. It includes native vision understanding for analyzing images and documents. It excels at complex reasoning, mathematical problems, and multi-step tasks. It provides strong code generation and debugging capabilities.
Access it through Chuizi.AI with a single ck- API key β no separate Moonshot account needed.
Highlights
262K context window
16K max output
Advanced reasoning
Native vision support
Strong code generation
Best For
Complex coding tasksAlgorithm designCode reviewTechnical architecture
2026-01-01
Capabilities
ChatVisionReasoningCodetools
Aliases
kimi-k2.5Pricing (per 1M tokens)
| Pricing (per 1M tokens) | / 1M tokens |
|---|---|
| Input / 1M | $0.59 |
| Output / 1M | $3.05 |
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-k2.5", messages=[{"role": "user", "content": "Hello!"}], ) print(response.choices[0].message.content)