GLM 4.6 Vision

Q: What is the context length of GLM 4.6 Vision?

GLM 4.6 Vision has a 128,000 token context window. It supports up to 128,000 output tokens.

Q: How much does GLM 4.6 Vision cost?

On AIHubMix, GLM 4.6 Vision costs $0.137 per million input tokens and $0.411 per million output tokens. Cached input reads are billed at $0.0274 per million tokens.

Q: What modalities does GLM 4.6 Vision support?

GLM 4.6 Vision accepts text, image and video input. It returns text output.

Q: How do I call GLM 4.6 Vision via API?

GLM 4.6 Vision is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to glm-4.6v — no other code changes needed.

Q: Who created GLM 4.6 Vision?

GLM 4.6 Vision is developed by Z.AI. AIHubMix aggregates it alongside models from other providers behind one API and one bill.

glm-4.6vllms.txt

Z.AI

Zhipu's latest visual reasoning model achieves state-of-the-art visual understanding accuracy at the same scale upon release. It natively supports tool invocation, can automatically complete tasks, supports ultra-long 128K context length, and allows flexible toggling of reasoning.

Pricing

Tier	Pricing	Cache Read
Tier	Pricing	Cache Read
Input<=32K	$0.137$0.411	$0.0274/M tokens
32K<Input<=128K	$0.274$0.822	$0.0548/M tokens

Input Modalities

Text
Vision
Video

Output Modalities

Text

Providers

Z.AI zai-glm-4.6v

Pricing$0.137$0.411

Cache Read$0.0274/M tokens

Pricing$0.274$0.822

Cache Read$0.0548/M tokens

Context128K

Max output128K

Latency1.7S

Throughput18.2TPS

Uptime

97.67% uptime 2 days ago

98.18% uptime yesterday

100.00% uptime today

Performance for glm-4.6v

Uptime is the percentage of requests that succeeded over the past 72 hours. AIHubMix continuously monitors every provider and automatically retries with the next-best provider when one returns an error or responds too slowly; Latency is total round-trip time (lower is better); Throughput is how fast the model writes (tokens per second, higher is better).

Uptime

Latency

Throughput

Try this model

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AIHUBMIX_API_KEY"],
    base_url="https://aihubmix.com/v1",
)

response = client.chat.completions.create(
    model="glm-4.6v",
    messages=[
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    max_tokens=1024,
    stream=False,
)

print(response.choices[0].message.content)

Frequently asked questions

What is GLM 4.6 Vision?

What is the context length of GLM 4.6 Vision?

How much does GLM 4.6 Vision cost?

What modalities does GLM 4.6 Vision support?

How do I call GLM 4.6 Vision via API?

Who created GLM 4.6 Vision?

Compare GLM 4.6 Vision

GLM 4.6 VisionvsQwen3.8 Max Preview GLM 4.6 VisionvsKimi K3 GLM 4.6 VisionvsGLM 5.2 GLM 4.6 VisionvsGrok 4.5

GLM 4.6 Vision

Pricing

Input Modalities

Output Modalities

Providers

Performance for glm-4.6v

Try this model

Frequently asked questions

What is GLM 4.6 Vision?

What is the context length of GLM 4.6 Vision?

How much does GLM 4.6 Vision cost?

What modalities does GLM 4.6 Vision support?

How do I call GLM 4.6 Vision via API?

Who created GLM 4.6 Vision?

Compare GLM 4.6 Vision

Product

Company

Developer

Connect

GLM 4.6 Vision

Pricing

Input Modalities

Output Modalities

Providers

Performance for glm-4.6v

Try this model

Frequently asked questions

What is GLM 4.6 Vision?

What is the context length of GLM 4.6 Vision?

How much does GLM 4.6 Vision cost?

What modalities does GLM 4.6 Vision support?

How do I call GLM 4.6 Vision via API?

Who created GLM 4.6 Vision?

Compare GLM 4.6 Vision

More models from Z.AI

Product

Company

Developer

Connect