Zhipu AI: GLM-5V-Turbo

Fast GLM vision model for screenshots, documents, and multimodal agent tasks

glm-5v-turbo

AvailableZhipu AIChat

Input / Output: $1.20 / $4.00
Context: 205K
Max output: 128K
Modalities: VisionChat
Capabilities: Tool usePrompt Cache

About GLM-5V-Turbo

GLM-5V-Turbo is Z.ai's first multimodal coding foundation model, built for vision-based coding and agent workflows. It processes images, video, text, and files together and answers in text. It is strong at turning design mock-ups into front-end code and at operating graphical interfaces, while keeping text coding performance solid.

Where it works well

Design-to-code is a headline use: it recreates front ends from mock-ups and screenshots.
Z.ai reports solid results on AndroidWorld and WebVoyager, which test operating real GUI environments.
Images, video, text, and files are processed together, so one request can combine a recording and a log.
Pure text coding stays competitive, so it does not require a separate model for the code written afterward.

When to choose another model

Output is text only; it writes code and descriptions but cannot generate images.
It was released before the GLM-5.3 line, whose Flash models add a longer context at lower cost.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

Text to textMessages API

POST/v1/messages

API format:

curl https://api.tokenlab.sh/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk-xxx" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "glm-5v-turbo",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Default spec

per 1M tokens

Official price: Input $1.20 / Output $4.00 / Cache read $0.24
Verified price: —
Discount: —

Prompt cache pricing

Cache read

Official price: $0.24
Verified price: —
Discount: —

	Official priceper 1M tokens	Verified priceper 1M tokens	Discount
Default spec	Input $1.20 / Output $4.00 / Cache read $0.24	—	—
Prompt cache pricing
Cache read	$0.24	—	—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Nov 1, 2026, 8:13 AM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open GLM-5V-Turbo in Console with a prompt ready to edit or send.

Help me try glm-5v-turbo with a short message at /v1/messages. Show the reply, latency, and cost.

Use cases

Best for

Vision

Mock-up to web page
Give it a screenshot or design file and get front-end code that matches the layout.
Website exploration agents
Drive a browser agent that looks at pages, decides what to click, and gathers the data requested.
Bug reports from screenshots
Read a user's screenshot of an error, locate the likely cause in code, and propose a patch.

Prompt examples

Turn this dashboard mock-up into a responsive HTML page with the same spacing and colors.

Open the pricing page screenshots in order and list the plan names and limits you can see.

This screenshot shows a cut-off button on mobile. Find the CSS that causes it and fix it.

This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.

FAQ

What exactly is GLM-5V-Turbo?

It is Z.ai's multimodal coding model, designed to see as well as code. It accepts images, video, text, and files, and its documentation highlights design-to-code and GUI automation, with function calling and thinking mode available.

Is GLM-5V-Turbo only for images?

No. It also handles plain text coding tasks, and Z.ai says text coding performance remains strong. The vision input adds mock-ups, screenshots, and video to what you can send.

How does it differ from GLM-5.3-Flash?

Both read images, video, and files. GLM-5V-Turbo is the earlier vision coding model built around design-to-code and GUI agents; GLM-5.3-Flash is newer with a much longer context and lower cost.

Can it return structured JSON?

Yes, JSON-formatted output is supported, which helps when extracting fields from screenshots, forms, or documents into a fixed schema that your own code can validate and use.

How much does GLM-5V-Turbo cost?

On TokenLab, GLM-5V-Turbo costs Input $1.20 / Output $4.00 per 1M tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

What are the context window and output limit of GLM-5V-Turbo?

GLM-5V-Turbo accepts up to 204,800 tokens of context and returns up to 131,072 tokens in one response.

Which endpoint should GLM-5V-Turbo use?

Use https://api.tokenlab.sh/v1/messages for GLM-5V-Turbo. The request example below shows the matching code shape.

Which operations does GLM-5V-Turbo support?

GLM-5V-Turbo supports Text to text. Select an operation above to see its endpoint and request example.