Kimi K3.1 Pro or Hy4?
The two newest models on the line, Moonshot AI's Kimi K3.1 Pro and Tencent's Hy4, both uncensored, both reading images and a million tokens of context, both calling tools. Kimi is the stronger and dearer of the two.
| Kimi K3.1 Pro Outlaw | Hy4 Outlaw | |
|---|---|---|
| Model id | kimi-k3.1-pro-outlaw | hy4-outlaw |
| Intelligence Index (base model) | 55 | - |
| Context | 1,048,576 tokens | 1,048,576 tokens |
| Longest reply | 943,718 tokens | 65,536 tokens |
| Tool calling | Yes | Yes |
| Images | Yes | Yes |
| Reasoning | On by default, adjustable | On by default, adjustable |
| Input, per 1M tokens | $7.50 | $3.20 |
| Cached input, per 1M tokens | $0.80 | $0.60 |
| Output, per 1M tokens | $37.50 | $6.40 |
| A 25-turn agent session | $2.29 | $0.90 |
Intelligence Index is the Artificial Analysis Intelligence Index v4.3.2 for each base model; uncensored builds are not benchmarked separately. The agent session is about 750,000 input tokens re-read across 25 turns, 85% of them cache hits, and 25,000 tokens written. Prices are what Wild West charges, checked 18 October 2026; the model pages always carry the current figures.
Use Kimi K3.1 Pro Outlaw when
- The task is the hardest you have. Kimi K3.1 Pro Outlaw is the strongest model on the line, at 55 on the Intelligence Index for its base model.
- The reply is very long. It writes up to 943,718 tokens in one reply against 65,536.
Use Hy4 Outlaw when
- Cost matters: $3.20 in, $0.60 cached and $6.40 out per million tokens against $7.50, $0.80 and $37.50.
- Replies fit in 65,536 tokens, which covers almost every chat and agent step.
Trying both
Both answer on https://wildwestapi.com/v1 and the Anthropic-compatible endpoint with the same key, so the quickest comparison is your own prompt sent to each. The request is identical apart from the model id; the DeepSeek V4.1 Flash quickstart has it in curl, Python and JavaScript.
FAQ
Which is newer, Kimi K3.1 Pro Outlaw or Hy4 Outlaw?
Both went on the line on the same day, 2026-11-06. Both are uncensored builds with image input and tool calling.
Which one should an agent use?
Kimi K3.1 Pro Outlaw for the hardest steps, Hy4 Outlaw where cost adds up. Both take the same key and endpoint, so an agent can use both.
Can I switch between them?
Yes. Same endpoint, same key: change the model id from kimi-k3.1-pro-outlaw to hy4-outlaw or back.