Claude as uncensored AI
Wild West API does not sell an uncensored or abliterated Claude (checked 2 October 2026). The uncensored model to use instead is GLM 5.3 Xploded, which scores 45 on the Intelligence Index to Claude Opus 5.5's 58.
Claude, uncensored and abliterated, so far
Anthropic has never released the weights of any Claude model. Claude runs only on Anthropic's own API and the clouds that resell it, so there is no abliterated or uncensored Claude anywhere, and "uncensored Claude" online means jailbreak prompts, which stop working as they get patched. What does carry over is the client: Wild West API answers the Anthropic Messages format at /v1/messages, so Claude Code and other Anthropic clients run unchanged on an uncensored model instead.
Claude releases and the uncensored line
| Model | Intelligence | Uncensored on Wild West API | Context | Price per 1M (in / out) |
|---|---|---|---|---|
| Claude Opus 5.5 | 58 | No | - | - |
| Claude Sonnet 5.5 | 56 | No | - | - |
| Claude Fable 5.1 | 53 | No | - | - |
| Outlaw 1 Xploded | - | Yes | 1M | $0.30 / $1.00 |
| GLM 5.3 Xploded | 45 | Yes | 1M | $2.50 / $4.50 |
| GLM 5.3 Flash Xploded | 42 | Yes | 1M | $0.40 / $1.60 |
| MiMo V2.6 Flash Xploded | 38 | Yes | 1M | $1.00 / $3.00 |
| Qwen3.8 27B Xploded | 34 | Yes | 524K | $0.30 / $2.40 |
Intelligence is the Artificial Analysis Intelligence Index v4.3.2 for each base model, checked 2 October 2026. Uncensored builds are not benchmarked separately.
Calling GLM 5.3 Xploded
Any OpenAI client works with the base URL https://wildwestapi.com/v1; see OpenAI-compatible API for the full set of examples.
curl https://wildwestapi.com/v1/chat/completions \ -H "Authorization: Bearer sk-ww-..." \ -H "Content-Type: application/json" \ -d '{ "model": "glm-5.3-xploded", "messages": [{"role": "user", "content": "Hello"}] }'
FAQ
Is there an uncensored Claude API?
Not on Wild West API as of 2 October 2026. GLM 5.3 Xploded is the uncensored model to use instead.
Can it drive Claude Code or another coding agent?
GLM 5.3 Xploded calls tools, so yes. Every model on the line supports tool calling and answers both the OpenAI and Anthropic formats; setups are in the guides.