kimi-k2-instruct by fireworksai - AI Model Details, Pricing, and Performance Metrics
kimi-k2-instruct
completionskimi-k2-instruct
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.
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.
Access kimi-k2-instruct through LangDB AI Gateway
Integrate with moonshotai's kimi-k2-instruct and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.
Free tier available • No credit card required
Statistics
Category Scores
Benchmark Tests
| Metric | GPQA | HumanEval | MMLU | MMLU-Pro |
|---|---|---|---|---|
| Score | 75.1 | 93.3 | 89.5 | 81.1 |
Compare with Similar Models
Code Examples
Integration samples and API usage
Related Models
Similar models from fireworksai
