Kimi K2 0711 (free) Check detailed information and pricing for AI models
Context Length 32,768 tokens, moonshotai from provided
32,768
Context Tokens
Free
Prompt Price
Free
Output Price
10/16
Feature Support
Model Overview
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. Kimi K2 excels across a broad range of benchmarks, particularly in coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) tasks. It supports long-context inference up to 128K tokens and is designed with a novel training stack that includes the MuonClip optimizer for stable large-scale MoE training.
Basic Information
Developer
moonshotai
Model Series
Other
Release Date
2025-07-11
Context Length
32,768 tokens
Variant
free
Pricing Information
This model is free to use
Data Policy
Terms of Service
학습 정책
1
Supported Features
Supported (10)
Top K
Seed
Frequency Penalty
Presence Penalty
Repetition Penalty
Min P
Logit Bias
Tool Usage
Logprobs
Top Logprobs
Unsupported (6)
Image Input
Response Format
Structured Outputs
Reasoning
Web Search Options
Top A
Other Variants
Actual Usage Statistics
#44
Out of 353 total models
47.0B
Total Tokens Last 30 Days
1.6B
Daily Average Usage
13%
Weekly Usage Change