Author's Description
Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It 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 supports long-context inference up to 256k tokens, extended from the previous 128k. This update improves agentic coding with higher accuracy and better generalization across scaffolds, and enhances frontend coding with more aesthetic and functional outputs for web, 3D, and related tasks. Kimi K2 is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. It excels across coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) benchmarks. The model is trained with a novel stack incorporating the MuonClip optimizer for stable large-scale MoE training.
Key Specifications
Supported Parameters
This model supports the following parameters:
Features
This model supports the following features:
Performance Summary
MoonshotAI's Kimi K2 0905 demonstrates a robust performance profile, particularly excelling in reliability with a 100% success rate across all benchmarks, indicating exceptional stability and minimal technical failures. Its speed performance is moderate, ranking in the 26th percentile, while its pricing is also moderate, falling into the 36th percentile. The model showcases significant strengths in specific areas. It achieves perfect accuracy in Hallucinations (Baseline), demonstrating an impressive ability to acknowledge uncertainty, and performs exceptionally well in Email Classification (99.0% accuracy) and Instruction Following (72.0% accuracy), both ranking in the 84th percentile. Its agentic capabilities are further supported by strong performance in Reasoning (78.0% accuracy, 67th percentile) and Coding (87.0% accuracy, 64th percentile), aligning with its description as optimized for advanced tool use and code synthesis. However, Kimi K2 0905 exhibits notable weaknesses in General Knowledge (77.0% accuracy, 23rd percentile), Ethics (80.0% accuracy, 20th percentile), and Mathematics (53.0% accuracy, 25th percentile), where its accuracy falls into the lower percentiles. While its long-context inference and MoE architecture are advanced, these areas suggest potential for improvement in broader factual recall, ethical discernment, and complex mathematical problem-solving.
Model Pricing
Current Pricing
Feature | Price (per 1M tokens) |
---|---|
Prompt | $0.6 |
Completion | $2.5 |
Input Cache Read | $0.15 |
Price History
Available Endpoints
Provider | Endpoint Name | Context Length | Pricing (Input) | Pricing (Output) |
---|---|---|---|---|
Moonshot AI
|
Moonshot AI | moonshotai/kimi-k2-0905 | 262K | $0.6 / 1M tokens | $2.5 / 1M tokens |
Moonshot AI
|
Moonshot AI | moonshotai/kimi-k2-0905 | 262K | $2.4 / 1M tokens | $10 / 1M tokens |
Together
|
Together | moonshotai/kimi-k2-0905 | 262K | $1 / 1M tokens | $3 / 1M tokens |
Fireworks
|
Fireworks | moonshotai/kimi-k2-0905 | 262K | $0.6 / 1M tokens | $2.5 / 1M tokens |
Groq
|
Groq | moonshotai/kimi-k2-0905 | 262K | $1 / 1M tokens | $3 / 1M tokens |
Novita
|
Novita | moonshotai/kimi-k2-0905 | 262K | $0.6 / 1M tokens | $2.5 / 1M tokens |
Chutes
|
Chutes | moonshotai/kimi-k2-0905 | 262K | $0.39 / 1M tokens | $1.9 / 1M tokens |
Parasail
|
Parasail | moonshotai/kimi-k2-0905 | 262K | $0.55 / 1M tokens | $2.99 / 1M tokens |
BaseTen
|
BaseTen | moonshotai/kimi-k2-0905 | 262K | $0.6 / 1M tokens | $2.5 / 1M tokens |
AtlasCloud
|
AtlasCloud | moonshotai/kimi-k2-0905 | 65K | $0.6 / 1M tokens | $2.5 / 1M tokens |
SiliconFlow
|
SiliconFlow | moonshotai/kimi-k2-0905 | 262K | $0.4 / 1M tokens | $2 / 1M tokens |
DeepInfra
|
DeepInfra | moonshotai/kimi-k2-0905 | 262K | $0.5 / 1M tokens | $2 / 1M tokens |
GMICloud
|
GMICloud | moonshotai/kimi-k2-0905 | 262K | $0.39 / 1M tokens | $1.9 / 1M tokens |
WandB
|
WandB | moonshotai/kimi-k2-0905 | 128K | $0.39 / 1M tokens | $1.9 / 1M tokens |
Benchmark Results
Benchmark | Category | Reasoning | Strategy | Free | Executions | Accuracy | Cost | Duration |
---|
Other Models by moonshotai
|
Released | Params | Context |
|
Speed | Ability | Cost |
---|---|---|---|---|---|---|---|
MoonshotAI: Kimi K2 0711 | Jul 11, 2025 | ~1T | 131K |
Text input
Text output
|
★★★★ | ★★★★★ | $$ |
MoonshotAI: Kimi Dev 72B | Jun 16, 2025 | 72B | 131K |
Text input
Text output
|
★ | ★★ | $$$$ |
MoonshotAI: Kimi VL A3B Thinking Unavailable | Apr 10, 2025 | 3B | 131K |
Image input
Text input
Text output
|
★ | ★ | $$$ |