Kimi K3
ChatNot available
Moonshot AI's 2.8T parameter open-weight multimodal reasoning model, optimized for complex coding, knowledge work, and agentic workflows.
- Context
- 1Mtokens
- Max output
- 128Ktokens
- Latency
- ~16ms
- Released
- 2026-07
Pricing
$ / 1M tokensInput
$3.00/M
Output
$15.00/M
Cache Read
$0.30/M
Cache Write
$3.00/M
Capabilities
5 listed- Chat
- Tool Use
- Reasoning
- Coding
- Analysis
Code examples
POST /v1/chat/completionspython
from openai import OpenAI
client = OpenAI(
api_key="your_api_key",
base_url="https://api.modelstack.cc/v1",
)
response = client.chat.completions.create(
model="kimi-k3",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)Related models
Frequently asked questions
How is Kimi K3 billed on ModelStack?expand_more
ModelStack bills based on actual request usage. Input, output, cache, and any other applicable rates follow the live pricing table on this page. Final request costs are available in the console.
What are the context window and maximum output for Kimi K3?expand_more
Kimi K3 has a 1M context window and supports up to 128K of output.
How can I call Kimi K3 through ModelStack?expand_more
Use the model ID `kimi-k3` with any OpenAI-compatible SDK pointed at the ModelStack API — see the code examples above for Python, Node.js, and cURL.
Which capabilities does Kimi K3 support?expand_more
Kimi K3 supports: Chat, Tool Use, Reasoning, Coding, Analysis.