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.
Back to Models
-$0.56/ M tokens$2.23/ M tokensRead:0.2/ M tokensWrite:0.003/ M tokens128K--
Providers
Route requests across multiple providers. Copy a provider slug to set your preference.
ProviderCache Hit RateContext
VolcengineSunset
volcengine
Uptime
24hoursDirect request success rate on AI Gateway and per-provider.
May 25, 16:54
Volcengine100.00%
Throughput
24hoursP50 throughput on live AI Gateway traffic, in tokens per second (TPS).
No data
Latency
24hoursP50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds.
No latency samples available for this period.
Activity
Token volume and request traffic to this model over time.
Token Consumption
May 25
Tbox-
Volcengine55.9K
Token volume broken down by the provider that served each request. Larger segments indicate providers handling more of this model's traffic.
Benchmarks
Scores on standardized evaluations. Higher percentages are better — and rank percentile shows
Metrics sourced fromArtificial Analysis
Artificial AnalysisNo benchmark data is available for this model.
Apps
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for. View All
Token Ranking
No app usage is available for this period.
Related Models
More models from MoonshotAI