GLM as uncensored AI
Yes. Wild West API sells three uncensored GLM models: GLM 5.3 Xploded (glm-5.3-xploded) and GLM 5.3 Flash Xploded (glm-5.3-flash-xploded) and Outlaw 1 Xploded (outlaw-1-xploded).
GLM, uncensored and abliterated, so far
GLM is Z.ai's open-weight line, and GLM 5.3 is one of the strongest open models on the Artificial Analysis index. The best-known abliterated GLM is abliteration.ai's Abliterated Model Large V2, an abliterated and retuned GLM-5.3 sold through its own API; its previous Large was built on GLM-5.2. Wild West API sells uncensored builds of both GLM 5.3 and GLM 5.3 Flash, which are the two that call tools and carry a million tokens of context.
GLM releases and the uncensored line
| Model | Intelligence | Uncensored on Wild West API | Context | Price per 1M (in / out) |
|---|---|---|---|---|
| GLM 5.3 | 45 | Yes, as GLM 5.3 Xploded | 1M | $2.50 / $4.50 |
| GLM 5.3 Flash | 42 | Yes, as GLM 5.3 Flash Xploded | 1M | $0.40 / $1.60 |
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 GLM API?
Yes: GLM 5.3 Xploded (glm-5.3-xploded) and GLM 5.3 Flash Xploded (glm-5.3-flash-xploded) and Outlaw 1 Xploded (outlaw-1-xploded) on Wild West API, through an OpenAI- or Anthropic-compatible endpoint.
Is the GLM on Wild West API abliterated or uncensored?
GLM 5.3 Xploded is uncensored: the refusal training was taken off, not edited out along the refusal direction. GLM 5.3 Flash Xploded is uncensored: the refusal training was taken off, not edited out along the refusal direction. Outlaw 1 Xploded is abliterated: the refusal direction was removed from the weights.
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.