GLM-5.3 Flash uncensored providers
by Z.ai320B total, 18B active parametersUpdated
Silk Compute is the only provider in this directory that serves GLM-5.3 Flash uncensored, at $0.24 in and $1.00 out per 1M tokens. It is a 320B model with 18B active parameters that takes text and images.
InputsText inputImage input
Lowest in / out price$0.24 / $1.00per 1M
Context1.05M
Providers1 of 7
Providers
Sorted by input price, read November 18, 2026.
| Provider | Sold as | Input /M | Output /M | Context | Access |
|---|---|---|---|---|---|
| Silk Compute | GLM-5.3 Flash | $0.24 | $1.00 | 1.05M | Verified email |
| Not served by | |||||
| Abliteration | Not listed | ||||
| Morph | Not listed | ||||
| Unfil.AI | Not listed | ||||
| Featherless | Not listed | ||||
| Awan LLM | Not listed | ||||
| ModelsLab | Not listed | ||||
Data policy and payment
| Provider | Data policy | Payment | API formats |
|---|---|---|---|
| Silk Compute | Zero data retention | Card, Crypto | Chat, Messages, Responses |
Setup
Silk Compute takes OpenAI SDK requests at its base URL; GLM-5.3 Flash on Silk Compute lists the limits.
Python
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.silkcompute.com",
api_key=os.environ["SILK_API_KEY"],
)
reply = client.chat.completions.create(
model="glm-5.3-flash-uncensored",
messages=[{"role": "user", "content": "Hello"}],
)