China
Kimi
Kimi is an AI chatbot and assistant platform developed by Moonshot AI (月之暗面), a Chinese AI startup based in Beijing. The platform features Kimi K2.6 model with capabilities including long-context processing, deep research, code generation (Kimi Code), and agent-based workflows (Agent Swarm). Kimi gained significant popularity in China for its strong long-context understanding abilities, initially supporting 200K+ token contexts. The platform also offers productivity tools including document creation, slide presentations, spreadsheets, and website building.
Region
China
Updated
May 14, 2026
CODPL speed
Provider speed highlights
Product coverage
Products from this provider
Model coverage
Models from this provider
Kimi K2
Kimi K2
Kimi K2 is a large language model developed by Moonshot AI (Kimi). It is part of the Kimi series, likely representing a significant iteration in the model family.
Input / 1M tokens
$0.585
Output tokens/s
33.17
First-token seconds
1.3s
Artificial Analysis Intelligence Index
26.3
Kimi K2
Kimi K2 0905
Kimi K2 0905 is a large language model developed by Moonshot AI (Kimi). It is part of the Kimi series, likely featuring strong long-context understanding and reasoning capabilities.
Input / 1M tokens
$0.60
Output tokens/s
16.5
First-token seconds
1.85s
Artificial Analysis Intelligence Index
30.9
Kimi K2
Kimi K2 Thinking
Kimi K2 Thinking is a reasoning-focused model from Moonshot AI, designed to excel in complex problem-solving and chain-of-thought tasks. It is optimized for deep analysis and logical inference.
Input / 1M tokens
$0.60
Output tokens/s
118.72
First-token seconds
0.96s
Artificial Analysis Intelligence Index
40.9
Kimi K2.5
Kimi K2.5 (Non-reasoning)
Kimi K2.5 (Non-reasoning) is a fast-response variant of the Kimi K2.5 series, optimized for low-latency interactions. It excels in rapid content generation, chat, and multimodal understanding tasks where immediate answers are prioritized over deep, step-by-step reasoning.
Input / 1M tokens
$0.60
Output tokens/s
56.41
First-token seconds
1.19s
Artificial Analysis Intelligence Index
37.3
Kimi K2.5
Kimi K2.5 (Reasoning)
Kimi K2.5 (Reasoning) is a large language model from Moonshot AI, specifically optimized for complex reasoning tasks. It excels in multi-step logical deduction, mathematical problem-solving, and code analysis, often employing a chain-of-thought approach to enhance accuracy. The model is designed to handle intricate queries that require deep analytical thinking.
Input / 1M tokens
$0.54
Output tokens/s
47.81
First-token seconds
1.16s
Artificial Analysis Intelligence Index
46.8
Kimi K2.6
Kimi K2.6
Kimi K2.6 is a large language model developed by Moonshot AI, optimized for long-context understanding and complex reasoning tasks. It builds upon the Kimi K2 series, offering enhanced performance in processing extensive information and generating coherent, logical responses.
Input / 1M tokens
$0.95
Output tokens/s
40.66
First-token seconds
1.26s
Artificial Analysis Intelligence Index
53.9
Kimi K2.6
Kimi K2.6 (Non-reasoning)
A non-reasoning variant of the Kimi K2.6 model, optimized for fast response times and cost-efficiency. It is suitable for applications requiring quick, economical replies while maintaining the long-context capabilities of the Kimi K2 series.
Input / 1M tokens
$0.95
Output tokens/s
36.78
First-token seconds
1.26s
Artificial Analysis Intelligence Index
42.9
Kimi
Kimi Linear 48B A3B Instruct
Kimi Linear 48B A3B Instruct is a large language model optimized for efficiency, likely utilizing a Mixture-of-Experts (MoE) architecture with 48 billion total parameters and 3 billion active parameters. The 'Linear' designation suggests it may employ linear attention mechanisms for enhanced performance on long sequences. As an instruction-tuned model, it is designed for strong instruction following and conversational capabilities.
Input / 1M tokens
$0.00
Artificial Analysis Intelligence Index
14.4
Discussion
Thinking... Make sure you are connected to GitHub server