Don't show again
KAT-Coder-Pro V1
20% OFF
kat-coder
KAT-Coder-Pro V1 is KwaiKAT's most advanced agentic coding model in the KwaiKAT series. Designed specifically for agentic coding tasks, it excels in real-world software engineering scenarios, achieving a remarkable 73.4% solve rate on the SWE-Bench Verified benchmark. KAT-Coder-Pro V1 delivers top-tier coding performance and has been rigorously tested by thousands of in-house engineers.
The model has been optimized for tool-use capability, multi-turn interaction, instruction following, generalization and comprehensive capabilities through a multi-stage training process, including mid-training, supervised fine-tuning (SFT), reinforcement fine-tuning (RFT), and scalable agentic RL.
Features
Serverless API
Docs
kat-coder is available via Novita's serverless API, where you pay per token. There are several ways to call the API, including OpenAI-compatible endpoints with exceptional reasoning performance.
Available Serverless
Run queries immediately, pay only for usage
Input$0 / M Tokens$0.98 / M Tokens
Output$0 / M Tokens$3.8 / M Tokens
Tiered pricing
| Input length | Input price (M tokens) | Output Price (M tokens) |
|---|---|---|
| 0 < tokens <= 32,768 | $0 | $0 |
| 32,768 < tokens <= 131,072 | $0 | $0 |
| 131,072 < tokens <= 262,144 | $0 | $0 |
Use the following code examples to integrate with our API:
1from openai import OpenAI
2
3client = OpenAI(
4 api_key="<Your API Key>",
5 base_url="https://api.novita.ai/openai"
6)
7
8response = client.chat.completions.create(
9 model="kat-coder",
10 messages=[
11 {"role": "system", "content": "You are a helpful assistant."},
12 {"role": "user", "content": "Hello, how are you?"}
13 ],
14 max_tokens=32000,
15 temperature=0.7
16)
17
18print(response.choices[0].message.content)Info
Provider
KwaiKAT
Quantization
fp16
Supported Functionality
Context Length
256000
Max Output
32000
Serverless
Supported
Structured Output
Supported
Function Calling
Supported
Input Capabilities
text
Output Capabilities
text