Context
128K
Input
text
Output
text
Tool calling
Supported
About this model
Kimi-K2-Instruct is Moonshot AI's flagship 100-billion-parameter instruction-tuned model featuring a hybrid dense-MoE architecture with 200K context handling. Optimized for complex reasoning, multilingual dialogue, and long-form document understanding. Specializes in Chinese and English technical domains with enhanced safety alignment.
Input modalities
text
Accepted as model input
Providers
Available routing options for this model through OneInfer.
Available
Input tokens
$0.570 / 1M tokens
Output tokens
$2.300 / 1M tokens
Routing
OneInfer optimized
Pricing
Current OneInfer pricing for this model.
| Usage | Price |
|---|---|
| Input tokens | $0.570 / 1M tokens |
| Output tokens | $2.300 / 1M tokens |
Performance
Published evaluation results associated with this model.
Long-Context Understanding
Needle-in-Haystack (200K)98.2
Book Summarization (F1)92.7
Legal Document QA89.4
Reasoning Capabilities
MMLU (5-shot)83.5
CMMLU (Chinese MMLU)85.1
GSM8K (8-shot)91.3
HumanEval (0-shot)73.8
Multilingual Performance
Chinese (CEval)86.4
English (MMLU)83.5
Japanese (JGLUE)78.9
Korean (Ko-LLM-Leaderboard)76.2
Safety Alignment
Harmful Query Rejection95.6
Bias Detection Score93.2
API example
curl https://api.oneinfer.ai/v1/ula/chat/completions \
-H "Authorization: Bearer $ONEINFER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "moonshotai/Kimi-K2-Instruct",
"messages": [
{ "role": "user", "content": "Hello!" }
]
}'