Kimi K3
moonshotai/kimi-k3
Kimi K3 is Kimi’s most capable model to date, with 2.8 trillion parameters. Built on Kimi Delta Attention, a hybrid linear attention mechanism, and Attention Residuals, it offers native visual understanding and a 1M-token context window for frontier intelligence scenarios such as software engineering, knowledge work, and deep reasoning.
Price
| Input | $3 per million tokens |
| Cached reads | $0.3 per million tokens |
| Output | $15/百万 tokens |
Use the following code example to integrate our API:
1from openai import OpenAI
2
3client = OpenAI(
4 api_key="<Your API Key>",
5 base_url="https://api.highwayapi.ai/openai"
6)
7
8response = client.chat.completions.create(
9 model="moonshotai/kimi-k3",
10 messages=[
11 {"role": "system", "content": "You are a helpful assistant."},
12 {"role": "user", "content": "Hello, how are you?"}
13 ],
14 max_tokens=1000,
15 temperature=0.7
16)
17
18print(response.choices[0].message.content)Information
Provider
Quantification
-
Supported Features
Context length
1048576
Maximum output
-
serverless
Support
Function call
Support
Structured output
Support
Reasoning
Support
Input Capabilities
text, image, video
Output Capabilities
text