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.

ProviderSold asInput /MOutput /MContextAccess
Silk ComputeGLM-5.3 Flash$0.24$1.001.05MVerified email
Not served by
AbliterationNot listed
MorphNot listed
Unfil.AINot listed
FeatherlessNot listed
Awan LLMNot listed
ModelsLabNot listed

Data policy and payment

ProviderData policyPaymentAPI formats
Silk ComputeZero data retentionCard, CryptoChat, 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"}],
)