Moonshot · Open weights
Kimi K2 Thinking
Moonshot AI's distinct Kimi K2 Thinking checkpoint is a mandatory-reasoning model for long-horizon agentic workflows and multi-step tool use.
- Reasoning
- Tools
- Structured output
- Input
- Text
- Output
- Text
- Discovery tier
- Open weights
Pricing
USD per 1M tokens- Input
- $0.60
- Output
- $2.50
- Cache read
- $0.15
Reference prices as published by the model provider. API example
Specifications
- Context window
- 262.1K
- Max output
- 98.3K
- Average output (7 days)
- 1.9K tokens
- Longer than 91% of 473 models
Side by side
Compare models
Put Kimi K2 Thinking 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
22.0
Better than 53% of 326 scored models
Indexes
Math Index
94.7Composite of the math evaluations
Better than 95% of 118 scored models
Document reasoning
AA-LCRv1.1
72.0%Reasoning across long documents
Better than 53% of 309 scored models
Reasoning and knowledge
Humanity’s Last Exam
23.8%Expert-level questions across academic fields
Better than 55% of 323 scored models
GPQA Diamond
83.8%Graduate-level science questions
Better than 55% of 291 scored models
MMLU-Pro
84.8%Multi-subject knowledge and reasoning
Better than 84% of 132 scored models
IFBench
68.1%Following precise output instructions
Better than 68% of 215 scored models
Coding
LiveCodeBench
85.3%Recent competitive programming problems
Better than 93% of 129 scored models
Math
AIME 2025
94.7%Competition mathematics, 2025 problems
Better than 95% of 118 scored models
Legacy evaluations
Terminal-Bench Hard
31.1%Earlier terminal task suite
Better than 57% of 212 scored models
τ²-Bench Telecom
93.0%Tool use in a customer-support simulation
Better than 80% of 214 scored models
AA-LCR (unversioned)
72.0%Long-context reasoning, earlier grading
Better than 53% 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
- 81.2 tok/s
- Faster than 53% of 256 models
- Time to first token
- 4.9 s
- Quicker than 29% of 256 models
- Prompt cache hits
- 3.6%
- About $0.58 per 1M input tokens with caching
- Request success (24h)
- 99.6%
- 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-thinking",
"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-thinking",
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.