NOUMENOpen app
NOUMEN

Z.ai · Efficient

GLM 4.1V Thinking Flash

Added Jul 9, 2025

Compare models

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

Loading models…

Use in the app

Vision-Language Model with thinking paradigm and reinforcement learning. Achieves state-of-the-art performance among 10B-parameter VLMs. Supports 64k context length, handles arbitrary aspect ratios and up to 4K image resolution. Bilingual Chinese/English.

  • Vision
Input
Text, Images
Output
Text
Discovery tier
Efficient

Pricing

USD per 1M tokens
Input
$0.30
Output
$0.30

Reference prices as published by the model provider. API example

Specifications

Context window
64K
Max output
8.2K

Side by side

GLM 4.1V Thinking Flash 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…

GLM 4.1V Thinking FlashZ.aiThis modelGemini 3.5 Flash LiteGoogleRemove
ProviderZ.aiGoogle
Discovery tierEfficientEfficient
AddedJul 9, 2025Jul 21, 2026
Limits
Context window64K1.05MBest
Max output8.19K65.54KBest
Average output—178 tokens
Pricing, USD per 1M tokens
Input$0.30$0.30
Output$0.30Best$2.50
Cache read—$0.03
Cache write—$0.0833
Performance
Throughput—181.3 tok/s
Time to first token—0.7 s
Request success (24h)—99.8%
Benchmark indexes
Intelligence Index—22.2
Coding Index—49.3
Capabilities
ReasoningNoYes
ToolsNoYes
VisionYesYes
Structured outputNoYes
PDF inputNoYes
Audio inputNoYes
Video inputNoYes
Reasoning effort—minimal, low, medium, high

Public evaluations

Benchmarks

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

  • GLM 4.1V Thinking Flash
  • Gemini 3.5 Flash Lite

Intelligence Index

  • GLM 4.1V Thinking Flash—
  • Gemini 3.5 Flash Lite22.2
3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • GLM 4.1V Thinking Flash: —
    • Gemini 3.5 Flash Lite: 49.3

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • GLM 4.1V Thinking Flash: —
    • Gemini 3.5 Flash Lite: 25.0%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • GLM 4.1V Thinking Flash: —
    • Gemini 3.5 Flash Lite: 3.3%

  • Harvey LAB-AAv1.1

    Legal tasks passed in full, with no material hallucination

    • GLM 4.1V Thinking Flash: —
    • Gemini 3.5 Flash Lite: 0.0%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • GLM 4.1V Thinking Flash: —
    • Gemini 3.5 Flash Lite: 650 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • GLM 4.1V Thinking Flash: —
    • Gemini 3.5 Flash Lite: 985 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • GLM 4.1V Thinking Flash: —
    • Gemini 3.5 Flash Lite: 13.6%

  • AA-LCRv1.1

    Reasoning across long documents

    • GLM 4.1V Thinking Flash: —
    • Gemini 3.5 Flash Lite: 76.0%

  • MLCR-AA

    Long-context reasoning over medical records

    • GLM 4.1V Thinking Flash: —
    • Gemini 3.5 Flash Lite: 10.6%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GLM 4.1V Thinking Flash: —
    • Gemini 3.5 Flash Lite: 18.8%

  • GPQA Diamond

    Graduate-level science questions

    • GLM 4.1V Thinking Flash: —
    • Gemini 3.5 Flash Lite: 83.8%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • GLM 4.1V Thinking Flash: —
    • Gemini 3.5 Flash Lite: 1.0%

  • SciCode

    Scientific computing in Python

    • GLM 4.1V Thinking Flash: —
    • Gemini 3.5 Flash Lite: 41.3%

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GLM 4.1V Thinking Flash: —
    • Gemini 3.5 Flash Lite: 76.0%

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

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": "glm-4.1v-thinking-flash",
    "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="glm-4.1v-thinking-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.