Wild West API

GLM 5.3 Apex Outlaw

glm-5.3-apex-outlaw

GLM is the open-weight model family from Z.ai, the company formerly known as Zhipu AI. Served through Wild West API on one OpenAI-compatible endpoint.

Modalities
Price per 1M
$0.30 / $1.00
input / output, $0.20 cached input
Context
1.05M
1,048,576 tokens

The abliterated GLM 5.3 Apex API

Wild West API serves an abliterated build of GLM 5.3 Apex under the model id glm-5.3-apex-outlaw. It has 1.05M tokens of context, costs $0.30 per million input tokens and $1.00 per million output tokens, with cached input at $0.20, and supports tool calling, so it can drive an agent. One key works on the OpenAI-compatible endpoint (https://wildwestapi.com/v1) and on the Anthropic-compatible one Claude Code uses, so the same GLM 5.3 Apex model plugs into Claude Code, Cline, opencode, SillyTavern, the OpenAI SDK and anything else that takes a custom base URL.

GLM 5.3 Apex abliterated against the rest of the line

ModelContextInputOutputIntelligenceToolsImages
High Noon1.05M$1.00$2.0038YesYes
GLM 5.3 Apex Outlaw1.05M$0.30$1.00-YesYes
DeepSeek V4.1 Flash Outlaw1.05M$0.30$1.5039YesNo
Qwen3.8 27B Fast Outlaw524k$1.50$5.0034YesYes
Sidewinder1.05M$1.50$5.0034YesYes
Hipshooter1.05M$0.30$1.0042YesYes
Slingshooter1.05M$2.00$5.0045YesNo

Prices are per million tokens. Intelligence is the Artificial Analysis Intelligence Index of the base model.

What the abliterated tag actually means

glm-5.3-apex-outlaw is tagged abliterated, meaning the refusal direction was identified and removed from the model's activations, so it very rarely refuses. That is not the same as being correct or safe: it can still be wrong, produce weak output, or generate content that is illegal to use. The tag describes what was done to the weights, not a promise about answers.

Call it with curl

Shell
curl https://wildwestapi.com/v1/chat/completions \
  -H "Authorization: Bearer sk-ww-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.3-apex-outlaw",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Call it with the OpenAI SDK

Python
# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://wildwestapi.com/v1",
    api_key="sk-ww-...",
)

resp = client.chat.completions.create(
    model="glm-5.3-apex-outlaw",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

In Claude Code

This model supports tool calling, so it can drive Claude Code. Set the context length to its real value of 1,048,576:

Shell
# Put these in your shell profile, then run: claude
export ANTHROPIC_BASE_URL=https://wildwestapi.com
export ANTHROPIC_AUTH_TOKEN=sk-ww-...
export ANTHROPIC_MODEL=glm-5.3-apex-outlaw
export ANTHROPIC_DEFAULT_HAIKU_MODEL=glm-5.3-outlaw
export CLAUDE_CODE_MAX_CONTEXT_TOKENS=1048576

FAQ

What does the abliterated tag mean?

Abliterated means the refusal direction was removed from the model, so it almost never refuses. It does not mean the output is correct or lawful to use.

How much does it cost?

$0.30 per million input tokens and $1.00 per million output tokens.

Is there an abliterated GLM 5.3 Apex API?

Yes. Wild West API serves GLM 5.3 Apex with the refusal training removed (abliterated) as glm-5.3-apex-outlaw, on an OpenAI-compatible endpoint at https://wildwestapi.com/v1 and an Anthropic-compatible one for Claude Code.

What is the GLM 5.3 Apex context window?

1,048,576 tokens (1.05M).

Does GLM 5.3 Apex abliterated support tool calling?

Yes. It can call tools, so it can drive coding agents such as Claude Code, Cline and opencode.

Can GLM 5.3 Apex abliterated read images?

Yes. Send images as OpenAI image_url content parts, or paste them into the chat.

Can I use GLM 5.3 Apex abliterated in SillyTavern?

Yes. Add Wild West API as an OpenAI-compatible (Chat Completion) source with the base URL https://wildwestapi.com/v1, your key, and glm-5.3-apex-outlaw as the model.

The rest of the line

Uncensored AI models on one key

OpenAI and Anthropic compatible, pay as you go. New to it? Start with uncensored AI, explained.