How much does the GLM 4.6V API cost?

On FastMetal, GLM 4.6V is billed per token: $0.33 per 1M input tokens and $0.99 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.

Can I call GLM 4.6V with the OpenAI SDK?

Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "glm-4.6v" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.

What is the context window of GLM 4.6V?

131,072 tokens, shared between the prompt and the response.

What do I need to try GLM 4.6V?

Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.

Back to Models

Z.ai

glm-4.6v

GLM 4.6V

GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts and charts directly as visual inputs, and integrates native multimodal function calling to connect perception with downstream tool execution. The model also enables interleaved image-text generation and UI reconstruction workflows, including screenshot-to-HTML synthesis and iterative visual editing.

12/8/2025

131,072 tokens

Input: $0.33/M

Output: $0.99/M

Try in Chat Get API Key

Specifications

Modalities

Input

image

text

video

Output

text

Supported Parameters

frequency_penalty

include_reasoning

max_tokens

min_p

presence_penalty

reasoning

repetition_penalty

response_format

seed

stop

structured_outputs

temperature

tool_choice

tools

top_k

top_p

Max Output Tokens

131,072

Data policy

Prompt retention: Not retained — every host this model runs on is configured not to retain prompts
Training: Not used for training

Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.

Measured performance

Time to first response (p50)915ms

Routed across 2 independent backends

Measured through FastMetal's own gateway over the last 30 days (660 first-response samples).

Time to first response is measured to the first streamed chunk; throughput counts all output tokens, including reasoning tokens. These are observations, not a performance guarantee.

Code Examples

curl https://api.fastmetal.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "glm-4.6v",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How GLM 4.6V actually answers

Real responses to our standard prompts, recorded on FastMetal.

Count the number of 'r's in 'strawberry'

Count the number of 'r's in 'strawberry'. Explain your reasoning step by step.

To count the number of **'r'** letters in the word **"strawberry"**, follow these steps: 1. **Write out the word** and list each character one by one: `s, t, r, a, w, b, e, r, r, y` 2. **Identify each occurrence of 'r'**: - The 3rd character is `r`. - The 8th character is `r`. - The 9th character is `r`. 3. **Count the identified 'r's**: There are three instances of the letter 'r'. Therefore, the number of 'r's in "strawberry" is **3**.

16.0s response466 output tokens

Debug This Error

I'm getting the following error in my Node.js application: TypeError: Cannot read properties of undefined (reading 'map') at UserList (/app/components/UserList.js:12:25) at renderWithHooks (/app/node_modules/rea…

Of course! This is a very common error in React applications. Let's break down what's happening and how to fix it. ### The Cause of the Error The error message `TypeError: Cannot read properties of undefined (reading 'map')` tells you exactly what's wrong: 1. **`TypeError`**: You are trying to perform an operation (in this case, calling the `.map()` method) on a value that is not of the expected type. 2. **`Cannot read properties of undefined`**: The value you are trying to call `.map()` on is `undefined`. 3. **`(reading 'map')`**: You are specifically trying to access the `map` method. In your `UserList` component, the line causing the error is: ```javascript {users.map(user => <li…

96.3s response2681 output tokens

Code Review

Please review the following Python function and suggest improvements for readability, performance, and best practices: def get_data(url, retries=3): import requests import time for i in range(retries):…

Of course! This is a great function to review. It's functional, but there are several opportunities to improve its readability, performance, and adherence to Python best practices. Here is the original function: ```python def get_data(url, retries=3): import requests import time for i in range(retries): try: r = requests.get(url, timeout=10) if r.status_code == 200: data = r.json() result = [] for item in data: if item["active"] == True: result.append({"name": item["name"], "id": item["id"]}) return result else:…

106.4s response3729 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the GLM 4.6V API cost?: On FastMetal, GLM 4.6V is billed per token: $0.33 per 1M input tokens and $0.99 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
Can I call GLM 4.6V with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "glm-4.6v" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of GLM 4.6V?: 131,072 tokens, shared between the prompt and the response.
What do I need to try GLM 4.6V?: Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.