MoonshotAI: Kimi K2 0711
moonshotai/kimi-k2
Description
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.
How this model compares
Overall covers the full catalog. By plan covers only models available on that tier (same rules as available models in your list). Position on min–average–max. Prices use the higher of prompt or completion per token, shown per 1M tokens.
Price (per 1M tokens)
Min
Max
This model
336 models in this groupPrice (per 1M tokens)
- Min
- $0.04
- Avg
- $12.385977
- Max
- $750.00
This model: $2.30 / 1M tokens
Context length (tokens)
Min
Max
This model
336 models in this groupContext length (tokens)
- Min
- 4,095 tokens
- Avg
- 382,115.467 tokens
- Max
- 10,000,000 tokens
This model: 131,072 tokens
Capabilities
Text → TextContext: 131,072 tokens
Input:
Text
Output:
Text