NOUMENOpen app
NOUMEN

Z.ai · Open weights

GLM 5.3 Flash

Added Aug 26, 2026Open weights

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

Use in the app

ox-alpha out of stealth! GLM-5.3 Flash is Z.ai's first natively multimodal GLM-5 model, with 320B total parameters and just 18B active parameters for efficient coding, agentic work, and precise 1M-token context. Its hybrid sparse-and-linear attention architecture helps it outperform GLM-5.2 at one-tenth the price while approaching Claude Opus 4.8 on coding and agentic benchmarks.

  • Reasoning
  • Tools
  • Vision
  • Structured output
  • Video input
Input
Text, Images, Video
Output
Text
Reasoning effort
low · high · max
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.10
Output
$0.30
Cache read
$0.025

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
131.1K
Average output (7 days)
1.3K tokens
Longer than 80% of 465 models

Side by side

Compare models

Put GLM 5.3 Flash next to up to three other models. The comparison stays in the link, so you can share it.

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

TryClaude Opus 4.8GPT 5.6 TerraLing 3.1 FlashAll 3

Public evaluations

Benchmarks

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

Intelligence Index

41.8

Better than 86% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    71.5

    Composite of the coding evaluations

    Better than 80% of 168 scored models

Agentic work

  • AutomationBench-AA

    60.4%

    Workflow automation, penalized for guardrail violations

    Better than 83% of 173 scored models

  • AutomationBench-AA tasks completed

    25.4%

    Workflows finished end to end without a guardrail violation

    Better than 73% of 173 scored models

  • Harvey LAB-AAv1.1

    0.8%

    Legal tasks passed in full, with no material hallucination

    Better than 68% of 29 scored models

  • AA-Briefcasev1.1

    1,452 Elo

    Agentic knowledge work, rated head to head

    Better than 77% of 166 scored models

  • GDPval-AAv2.1

    1,642 Elo

    Economically valuable occupational tasks, rated head to head

    Better than 89% of 187 scored models

Document reasoning

  • GDP.pdf

    15.4%

    Professional reasoning over PDF documents, all-pass rate

    Better than 64% of 171 scored models

  • AA-LCRv1.1

    80.0%

    Reasoning across long documents

    Better than 80% of 309 scored models

  • MLCR-AA

    11.7%

    Long-context reasoning over medical records

    Better than 44% of 121 scored models

Reasoning and knowledge

  • Humanity’s Last Exam

    39.9%

    Expert-level questions across academic fields

    Better than 76% of 323 scored models

  • GPQA Diamond

    91.2%

    Graduate-level science questions

    Better than 84% of 291 scored models

Coding

  • Terminal-Benchv4.0

    32.8%

    Practical software engineering in a terminal

    Better than 78% of 171 scored models

  • SciCode

    51.6%

    Scientific computing in Python

    Better than 60% of 174 scored models

Legacy evaluations

  • AA-LCR (unversioned)

    80.0%

    Long-context reasoning, earlier grading

    Better than 80% of 309 scored models

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
138.4 tok/s
Faster than 71% of 247 models
Time to first token
3.5 s
Quicker than 48% of 247 models
Prompt cache hits
82.8%
About $0.0379 per 1M input tokens with caching
Request success (24h)
99.6%
Reliable

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 98.2%
  • 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",
    "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",
    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.