kimi-k2
by moonshotaiKimi 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.
Pricing
Pay-as-you-go rates for this model. More details can be found here.
Input Tokens (1M)
$0.29
Output Tokens (1M)
$1.15
Capabilities
Input Modalities
Output Modalities
Rate Limits
Requests per minute (RPM) and per day (RPD) by tier. More about tiers here
| Tier | RPM | RPD |
|---|---|---|
| Free | — | — |
| Tier 1 | 10 | — |
| Tier 2 | 15 | — |
| Tier 3 | 25 | — |
| Tier 4 | 50 | — |
Usage Analytics
Token usage across the last 30 active days