Kimi K3.1 Pro for bug bounty
Kimi K3.1 Pro is our first pick for bug bounty work, because it reads text, images and video and writes up to 943,718 tokens. It costs $3.50 per 1M input tokens and $8.00 per 1M output tokens at Silk Compute.
Specs
- Maker
- Moonshot AI
- Parameters
- 2,780B
- Model id
kimi-k3.1-pro-uncensored- Context
- 1,048,576 tokens
- Max output
- 943,718 tokens
- Reads
- text, images, video
- Price per 1M
- $3.50 in, $0.35 cached, $8.00 out
Source: Silk Compute model page. Read November 18, 2026.
Jobs it fits
| Job | Why |
|---|---|
| Steps from a PoC screen recording | Reads video |
| Describing evidence screenshots | Reads images |
| Policy, notes and draft in one request | 1,048,576-token context |
| Long reports and write-ups | 943,718-token output |
It is the most expensive of the four. For bulk notes, DeepSeek V4.1 Flash 1017 costs $0.24 in.
Call it
import osfrom openai import OpenAI client = OpenAI(base_url="https://api.silkcompute.com", api_key=os.environ["SILK_API_KEY"])reply = client.chat.completions.create( model="kimi-k3.1-pro-uncensored", messages=[{"role": "user", "content": "Draft a HackerOne report from these notes: ..."}],)print(reply.choices[0].message.content)