NotHoly Specter

Base model: GLM 5.3 Abliterated

Trace complex code paths and work through multi-step security questions with detailed technical context.

Try in chat Use the API

Base model: GLM 5.3 Abliterated

Public API ID: notholy-specter
Effective context capacity: 1,048,576 tokens
Effective maximum output: 131,072 tokens
Model access: Chat, CLI and supported API contracts

Published capabilities

Tool calling
Reasoning
Streaming

Check field and protocol support

Usage per million tokens

Token type	Retail USD	Credits
Input	$3.00	300
Cached input	$0.45	45
Output	$6.00	600

USD per 1 million tokens. Schedule retail-2026-10-31-v2. Cached tokens replace ordinary input for that subset. Billable output may include reasoning tokens.

A bounded first request.

Set your customer key as an environment variable. This example is not executed by the page.

bash

curl https://api.notholy.com/v1/chat/completions \
  -H "Authorization: Bearer $NOTHOLY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"notholy-specter","messages":[{"role":"user","content":"Review this code and identify its trust boundaries."}],"max_tokens":512}'

Explore reasoning, tools and protocol support

Know the model behind the name.

NotHoly Specter provides access to GLM 5.3 Abliterated. NotHoly supplies the interface and routing; we do not claim to have trained or own the underlying model.

Effective context and output limits are request ceilings, not throughput commitments. Token consumption depends on the context sent, generated output and eligible cache usage.

Read data handling

Compare all models