NOUMENOpen app
NOUMEN

Z.ai · Open weights

Apex Flash 1

Added Oct 5, 2026Open weights

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

Apex Flash 1 is Cantina Security and Yeta's cybersecurity-focused post-train of GLM 5.3 Flash for code investigation and tool use.

  • 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)
672 tokens
Longer than 59% of 465 models

Side by side

Apex Flash 1 compared

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

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Apex Flash 1Z.aiThis modelGLM 5.3 Flash TEEZ.aiRemove
ProviderZ.aiZ.ai
Discovery tierOpen weightsOpen weights
AddedOct 5, 2026Aug 28, 2026
Limits
Context window1.05M1.05M
Max output32.77K131.07KBest
Average output672 tokens845 tokens
Pricing, USD per 1M tokens
Input$0.15$0.15
Output$0.50$0.50
Cache read$0.075$0.03Best
Performance
Throughput14.5 tok/s75.4 tok/sBest
Time to first token4.1 s3.8 sBest
Request success (24h)94.6%99.9%Best
Benchmark indexes
Intelligence Index—41.8
Coding Index—71.5
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesYes
Structured outputNoYes
Parallel toolsNoYes
Reasoning effortlow, high, maxlow, high, max

Public evaluations

Benchmarks

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

  • Apex Flash 1
  • GLM 5.3 Flash TEE

Intelligence Index

  • Apex Flash 1—
  • GLM 5.3 Flash TEE41.8
3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Apex Flash 1: —
    • GLM 5.3 Flash TEE: 71.5

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Apex Flash 1: —
    • GLM 5.3 Flash TEE: 60.4%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Apex Flash 1: —
    • GLM 5.3 Flash TEE: 25.4%

  • Harvey LAB-AAv1.1

    Legal tasks passed in full, with no material hallucination

    • Apex Flash 1: —
    • GLM 5.3 Flash TEE: 0.8%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Apex Flash 1: —
    • GLM 5.3 Flash TEE: 1,452 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Apex Flash 1: —
    • GLM 5.3 Flash TEE: 1,642 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Apex Flash 1: —
    • GLM 5.3 Flash TEE: 15.4%

  • AA-LCRv1.1

    Reasoning across long documents

    • Apex Flash 1: —
    • GLM 5.3 Flash TEE: 80.0%

  • MLCR-AA

    Long-context reasoning over medical records

    • Apex Flash 1: —
    • GLM 5.3 Flash TEE: 11.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Apex Flash 1: —
    • GLM 5.3 Flash TEE: 39.9%

  • GPQA Diamond

    Graduate-level science questions

    • Apex Flash 1: —
    • GLM 5.3 Flash TEE: 91.2%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Apex Flash 1: —
    • GLM 5.3 Flash TEE: 32.8%

  • SciCode

    Scientific computing in Python

    • Apex Flash 1: —
    • GLM 5.3 Flash TEE: 51.6%

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Apex Flash 1: —
    • GLM 5.3 Flash TEE: 80.0%

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

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
14.5 tok/s
Faster than 5% of 251 models
Time to first token
4.1 s
Quicker than 41% of 251 models
Prompt cache hits
94.4%
About $0.0792 per 1M input tokens with caching
Request success (24h)
94.6%
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 66.6%
  • 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",
    "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",
    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.