Z.ai · Open weights

Apex Flash 1 Abliterated

Added Oct 5, 2026Open weights

Apex Flash 1 Abliterated is an experimental derivative of Cantina Security and Yeta's Apex Flash 1 with modified refusal behavior.

Reasoning
Tools
Vision

Input: Text, Images
Output: Text
Reasoning effort: low · high · max
Discovery tier: Open weights

Pricing

USD per 1M tokens

Input: $0.15
Output: $0.50
Cache read: $0.075

Reference prices as published by the model provider. API example

Specifications

Context window: 1M
Max output: 32.8K
Average output (7 days): 629 tokens; Longer than 57% of 465 models

Side by side

Apex Flash 1 Abliterated compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Limits
	Apex Flash 1 AbliteratedZ.aiThis model	GLM 5.3 UncensoredZ.aiRemove
Provider	Z.ai	Z.ai
Discovery tier	Open weights	Open weights
Added	Oct 5, 2026	Sep 26, 2026
Context window	1.05M	1.05M
Max output	32.77K	131.07KBest
Average output	629 tokens	1.1K tokens
Pricing, USD per 1M tokens
Input	$0.15Best	$1.25
Output	$0.50Best	$2.25
Cache read	$0.075Best	$0.30
Performance
Throughput	13.2 tok/s	37.0 tok/sBest
Time to first token	5.2 sBest	7.6 s
Request success (24h)	92.8%	98.8%Best
Capabilities
Reasoning	Yes	Yes
Tools	Yes	Yes
Vision	Yes	No
Reasoning effort	low, high, max	low, high, max

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

Apex Flash 1 Abliterated
GLM 5.3 Uncensored

Leaderboard	Apex Flash 1 Abliterated	GLM 5.3 Uncensored
Usage Share	Not in top 20	#8 · 4.8%

Ranks among Noumen catalog models on Usage leaderboards. Only top-20 placements are listed.

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Throughput: 13.2 tok/s; Faster than 2% of 250 models
Time to first token: 5.2 s; Quicker than 32% of 250 models
Prompt cache hits: 91.2%; About $0.0816 per 1M input tokens with caching
Request success (24h): 92.8%; Unstable

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 46.3%

Healthy (98% or more)
Degraded (90–98%)
Down (under 90%)
No requests

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart

curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/glm-5.3-flash-apex-abliterated",
    "reasoning_effort": "low",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'

import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="z-ai/glm-5.3-flash-apex-abliterated",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Z.ai

Other Z.ai models, starting with the same family.