Z.ai
GLM-5.3 Flash Abliterated
GLM-5.3 Flash Abliterated is Z.ai's 320B mixture-of-experts model with its refusal direction removed, built for high-volume work.
Rank#4 / 8
#4Editors' rankingSize#4 / 8
320BTotal, 18B activePrice#2 / 5
$0.43Blended per 1M, lowest hostContext
1MTokens per requestOur pick for high-volume work at the lowest input price.
Input
Price in / out$0.24 / $1.00
Context1M tokens
Max output131,072
Model id
glm-5.3-flash-uncensoredIts input price matches DeepSeek V4.1 Flash, and its output costs $1.00 per 1M tokens against $0.90.
Where to run GLM-5.3 Flash by API
| Provider | Model id | Input | Cached | Output | Context | Prompts |
|---|---|---|---|---|---|---|
| Silk Compute | glm-5.3-flash-uncensored | $0.24 | $0.06 | $1.00 | 1M | Never stored |
Per 1M tokens, read from pricing pages on November 18, 2026.
Try GLM-5.3 Flash in two lines
Set the base URL and your key in the OpenAI or Anthropic SDK.
from openai import OpenAI client = OpenAI( base_url="https://api.silkcompute.com", api_key="YOUR_API_KEY", ) reply = client.chat.completions.create( model="glm-5.3-flash-uncensored", messages=[{"role": "user", "content": "..."}], )
In Claude Code:
export ANTHROPIC_BASE_URL=https://api.silkcompute.com export ANTHROPIC_AUTH_TOKEN=YOUR_API_KEY export ANTHROPIC_MODEL=glm-5.3-flash-uncensored claudeGLM-5.3 Flash on Silk Compute