Moonshot · Open weights
Kimi K2 0905
Kimi K2 0905. Kimi-k2 is a Mixture-of-Experts (MoE) foundation model with exceptional coding and agent capabilities, featuring 1 trillion total parameters and 32 billion activated parameters. In benchmark evaluations covering general knowledge reasoning, programming, mathematics, and agent-related tasks, the K2 model outperforms other leading open-source models. Quantized at FP8.
- Tools
- Structured output
- Input
- Text
- Output
- Text
- Discovery tier
- Open weights
Pricing
USD per 1M tokens- Input
- $0.40
- Output
- $1.80
Reference prices as published by the model provider. API example
Specifications
- Context window
- 262.1K
- Max output
- 100.4K
- Average output (7 days)
- 677 tokens
- Longer than 60% of 473 models
Side by side
Compare models
Put Kimi K2 0905 next to up to three other models. The comparison stays in the link, so you can share it.
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
Intelligence Index
15.3
Better than 39% of 326 scored models
Indexes
Math Index
57.3Composite of the math evaluations
Better than 54% of 118 scored models
Document reasoning
AA-LCRv1.1
53.0%Reasoning across long documents
Better than 32% of 309 scored models
Reasoning and knowledge
Humanity’s Last Exam
6.4%Expert-level questions across academic fields
Better than 22% of 323 scored models
GPQA Diamond
76.7%Graduate-level science questions
Better than 40% of 291 scored models
MMLU-Pro
81.9%Multi-subject knowledge and reasoning
Better than 62% of 132 scored models
IFBench
41.7%Following precise output instructions
Better than 33% of 215 scored models
Coding
LiveCodeBench
61.0%Recent competitive programming problems
Better than 60% of 129 scored models
Math
AIME 2025
57.3%Competition mathematics, 2025 problems
Better than 54% of 118 scored models
Legacy evaluations
Terminal-Bench Hard
23.5%Earlier terminal task suite
Better than 44% of 212 scored models
τ²-Bench Telecom
73.4%Tool use in a customer-support simulation
Better than 55% of 214 scored models
AA-LCR (unversioned)
53.0%Long-context reasoning, earlier grading
Better than 32% of 309 scored models
Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis
Live routing data
Performance and reliability
Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.
- Throughput
- 55.9 tok/s
- Faster than 41% of 256 models
- Time to first token
- 5.1 s
- Quicker than 28% of 256 models
- Prompt cache hits
- 30.3%
- Request success (24h)
- 100.0%
- Reliable
Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.
- Healthy (98% or more)
- Degraded (90–98%)
- Down (under 90%)
- No requests
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "moonshotai/Kimi-K2-Instruct-0905",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="moonshotai/Kimi-K2-Instruct-0905",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)Moonshot
Related models
Other Moonshot models, starting with the same family.