NOUMENOpen app
NOUMEN

Z.ai · Open weights

GLM 5V Turbo Thinking

Added Apr 2, 2026Open weights

Compare models

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

Loading models…

Use in the app

Thinking-enabled GLM 5V Turbo for image, video, and text inputs. Uses the same multimodal foundation model with more deliberate vision-grounded analysis, planning, and tool use.

  • Reasoning
  • Tools
  • Vision
  • Structured output
  • Video input
Input
Text, Images, Video
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$1.20
Output
$4.00
Cache read
$0.24

Reference prices as published by the model provider. API example

Specifications

Context window
202.8K
Max output
131.1K
Average output (7 days)
942 tokens
Longer than 69% of 468 models

Side by side

GLM 5V Turbo Thinking 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 5V Turbo ThinkingZ.aiThis modelSolar Mini 4upstageRemove
ProviderZ.aiupstage
Discovery tierOpen weightsEfficient
AddedApr 2, 2026Sep 23, 2026
Limits
Context window202.8K524.29KBest
Max output131.07K131.07K
Average output942 tokens561 tokens
Pricing, USD per 1M tokens
Input$1.20$0.05Best
Output$4.00$0.20Best
Cache read$0.24$0.005Best
Performance
Throughput41.0 tok/s90.6 tok/sBest
Time to first token6.5 s2.2 sBest
Request success (24h)97.6%Best89.1%
Benchmark indexes
Intelligence Index23.524.1Best
Capabilities
ReasoningYesNo
ToolsYesYes
VisionYesNo
Structured outputYesYes
Video inputYesNo
Reasoning effort——

Public evaluations

Benchmarks

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

  • GLM 5V Turbo Thinking
  • Solar Mini 4

Intelligence Index

  • GLM 5V Turbo Thinking23.5
  • Solar Mini 424.1

GLM 5V Turbo Thinking: Better than 57% of 326 scored models

3.8Catalog models by score55.1

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • GLM 5V Turbo Thinking: —
    • Solar Mini 4: 22.3%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • GLM 5V Turbo Thinking: —
    • Solar Mini 4: 2.4%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • GLM 5V Turbo Thinking: —
    • Solar Mini 4: 867 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • GLM 5V Turbo Thinking: —
    • Solar Mini 4: 1,085 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • GLM 5V Turbo Thinking: —
    • Solar Mini 4: 5.0%

  • AA-LCRv1.1

    Reasoning across long documents

    • GLM 5V Turbo Thinking: 70.3%
    • Solar Mini 4: 83.3%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • GLM 5V Turbo Thinking: —
    • Solar Mini 4: 6.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GLM 5V Turbo Thinking: 17.1%
    • Solar Mini 4: 25.8%Top

  • GPQA Diamond

    Graduate-level science questions

    • GLM 5V Turbo Thinking: 80.9%
    • Solar Mini 4: —

  • IFBench

    Following precise output instructions

    • GLM 5V Turbo Thinking: 61.1%
    • Solar Mini 4: —

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • GLM 5V Turbo Thinking: —
    • Solar Mini 4: 1.0%

  • SciCode

    Scientific computing in Python

    • GLM 5V Turbo Thinking: —
    • Solar Mini 4: 47.6%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • GLM 5V Turbo Thinking: 32.6%
    • Solar Mini 4: —

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • GLM 5V Turbo Thinking: 98.5%
    • Solar Mini 4: —

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GLM 5V Turbo Thinking: 70.3%
    • Solar Mini 4: 83.3%Top

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
41.0 tok/s
Faster than 30% of 254 models
Time to first token
6.5 s
Quicker than 26% of 254 models
Prompt cache hits
60.3%
About $0.62 per 1M input tokens with caching
Request success (24h)
97.6%
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 80.0%
  • 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-5v-turbo:thinking",
    "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-5v-turbo:thinking",
    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.