Buy me a coffee
Chat with GLM 4.6V for free on AIFreeForever

GLM 4.6V Free AI Chatbot

GLM 4.6V is Z.ai's open vision model for long PDFs, slide decks and videos. It reads about 150 pages or an hour of video in one request and can turn a screenshot into a working web page. GLM 4.6V is available for free on AIFreeForever.

Create anything with GLM 4.6V using our @skills feature

About GLM 4.6V AI model

GLM 4.6V is Z.ai's open vision model that reads images, video, documents and text, with a 128K-token context window. It can pass images straight into tools and turn screenshots into code. Chat with GLM 4.6V free on AIFreeForever.

GLM 4.6VMade by Z.ai Try GLM 4.6V on AIFreeForever→
Made byZ.ai
Model IDglm-4.6v
ReleasedDecember 2025
Size106B parameters
LicenceMIT
API price per 1M tokens$0.30 in / $0.90 out
Price of GLM 4.6V on AIFreeForeverFree

AIFreeForever is not affiliated with or endorsed by the model providers. All trademarks and logos belong to their owners.

What GLM 4.6V is best at

Long documents

Reads about 150 document pages in one request.

Video

Watches about 1 hour of video in one request.

Slides

Reads about 200 slides in one request.

Computer use

Turns a screenshot into HTML, CSS and JavaScript.

How to use GLM 4.6V for free on AIFreeForever

  1. 1

    Open the chat

    and choose GLM 4.6V.

  2. 2

    Add an image, PDF, slides or video

  3. 3

    Type your question

    about it.

  4. 4

    Read the answer

    and ask follow-up questions.

Tip: Ask GLM 4.6V to name the page or time where it found each answer, so you can check it's accurate.
Try it for free

Why choose AIFreeForever's free GLM 4.6V?

No upgrade required

Our chatbot gives you GLM 4.6V free, without a Z.ai account.

Document reading

Our chatbot answers questions about long PDFs with tables and charts.

Video reading

When you upload a video up to about an hour long, our chatbot can see what happens.

Screenshot to code

Our chatbot turns a page screenshot into HTML, CSS and JavaScript.

Multi-image reading

Our chatbot pulls the same fields from several screenshots at once.

Open model

MIT licence allows free business use.

GLM 4.6V benchmark results

GLM 4.6V answers at about 33 tokens a second and starts answering after about 9.4 seconds.

MeasureWhat it showsGLM 4.6V
Output speedTokens written per second33
Time to first answer tokenWait before the answer starts9.39 s
Context windowText it can take in128K tokens

This benchmark was extracted from Artificial Analysis.

Z.ai tested GLM 4.6V on more than 20 image tests, including MMBench, MathVista and OCRBench, and publishes the scores as a chart on its GLM-4.6V model card.

GLM 4.6V vs other top models

GLM 4.6V is the open model below with MIT-licensed weights that reads images and video.

ModelContextImage inputStrength
GLM 4.6V128KYes, plus videoScreenshots and documents
Qwen3.7 Plus1MYes, plus videoImage and video tasks
Qwen3.5-9B262KYes, plus videoSmall open model
GLM 5.31MNoCoding and cybersecurity
Tip: Pick GLM 4.6V for slide decks, scans and screenshots. Pick Qwen3.7 Plus for files longer than 128K tokens.

Chat with GLM 4.6V on AIFreeForever

AIFreeForever's free chatbot is fully integrated with GLM 4.6V via the official API providers. To get started, type your question or add a supporting document, and GLM 4.6V answers in the same chat. Use it to summarise slide decks, read scanned reports, rebuild pages from screenshots and more.

This model is subject to availability, based on our budget. For long-term use, we advise you to pay for an upgrade with the model provider.
Tip: GLM 4.6V is best suited for everyday tasks.

What you can create with GLM 4.6V

A turtle with a shell made of clear glass panels in violet and green@Website

Screenshot to HTML

A page that matches the picture.“@Website Rebuild this screenshot as a page in HTML, CSS and JavaScript.” Try the prompt→ A tall stack of paper files held together by a large brass clipPlain chat

Report summaries

Key points from a long PDF.“Summarise this 100-page PDF in 10 bullets with page numbers.” Try the prompt→ A row of small glass picture frames standing in a line, each glowing a different colour@Word

Slide summaries

A deck in one page.“@Word Summarise these slides as a one-page brief.” Try the prompt→ A vintage pocket watch with a glowing violet face and an open lidPlain chat

Video summaries

Scenes with times.“Summarise this video in 6 bullets with the time each part starts.” Try the prompt→ A wooden card catalogue drawer filled with neat index cards@Excel

Data from screenshots

Fields from several images in one table.“@Excel Put the order number, date and total from these 5 screenshots into a sheet.” Try the prompt→ A brass telescope on a tripod pointing slightly upwardsPlain chat

Chart reading

Every value in a table.“Read this chart and give me every value as a table.” Try the prompt→

Best GLM 4.6V prompts

Free GLM 4.6V PDF Summary Prompt

“Summarise this PDF in 10 bullets. Put the page number after each bullet and list any tables separately.” Try the prompt→
Download the free GLM 4.6V prompt guide (PDF) →

How GLM 4.6V works

GLM 4.6V's image encoder is trained with the same 128K-token window as its text model, so it reads long, image-heavy documents in one pass. It can pass images and screenshots straight into tools and read the images that tools send back, as explained in Z.ai's GLM-4.6V guide.

How much does GLM 4.6V cost?

GLM 4.6V costs $0.30 per million input tokens and $0.90 per million output tokens on Z.ai's API. It's free on AIFreeForever.

WherePriceCached inputContext
Z.ai API$0.30 in / $0.90 out per 1M tokens$0.05128K
OpenRouter$0.30 in / $0.90 out per 1M tokens—131K
Hugging Face weightsFree (MIT)—128K
AIFreeForever's Free AIFree——

Can you use GLM 4.6V for free?

Yes. You can use GLM 4.6V free in two ways:

  • On AIFreeForever: pick it in the chat and start typing.
  • On your own servers: download it from Hugging Face under the MIT licence.

Z.ai also offers GLM-4.6V-Flash, a smaller 9B version, free on its API.

Chat with GLM 4.6V

Limitations of GLM 4.6V on AIFreeForever

GLM 4.6V has three limits on AIFreeForever, which connects to it through its API and adds our skills and file editors:

  • Its 128K-token window limits very long files; split them or use Qwen3.7 Plus.
  • Z.ai's chat app and visual search tools aren't part of AIFreeForever.
  • You can't run Python, start agents that work on their own, or run regression analysis here.
Tip: Test GLM 4.6V free here first. For the best experience, use Z.ai's own platform.

Best ways to test GLM 4.6V free

TestHow to use it on AIFreeForever
Screenshot to codeUpload a page screenshot; open the HTML it writes.
Long PDFUpload a long PDF; ask about a table near the end.
VideoUpload a clip; check the times it gives.
Compare modelsSend the same image to Qwen3.7 Plus.

These limitations only cover what you can do with GLM 4.6V on AIFreeForever, not the limits of the model on Z.ai’s own platform. All trademarks belong to their owners, and the model’s full features are only available when you use it officially through Z.ai.

Frequently asked questions

Is GLM 4.6V free?

Yes. It's free on AIFreeForever and free to download under the MIT licence.

Who made GLM 4.6V?

Z.ai made GLM 4.6V.

Can GLM 4.6V read video?

Yes. Z.ai says it can take about one hour of video in one request.

How large is the GLM 4.6V context window?

GLM 4.6V takes up to 128K tokens, which Z.ai puts at about 150 document pages or 200 slides.

Is GLM 4.6V open source?

Yes. Z.ai releases the weights under the MIT licence.

What is GLM 4.6V Flash?

GLM-4.6V-Flash is a smaller 9B version for local use, and it's free on Z.ai's API.

Are GLM 4.6V answers 100% correct?

No. It can misread images and make mistakes, so check important details.

Chat with GLM 4.6V for free

Ask GLM 4.6V a question, paste your code or add a file and get instant answers. Not satisfied? Compare your answers to other models for free.

Chat with GLM 4.6V

Explore other free AI chat models

Open AI models

Alibaba Cloud models

Anthropic models