How much does the GLM 5.2 API cost?

On FastMetal, GLM 5.2 is billed per token in yen: ¥250.18 per 1M input tokens and ¥786.28 per 1M output tokens, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.

Can I call GLM 5.2 with the OpenAI SDK?

Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "glm-5.2" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.

What is the context window of GLM 5.2?

1,048,576 tokens, shared between the prompt and the response.

What do I need to try GLM 5.2?

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-5-2

GLM 5.2

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...

6/16/2026

1,048,576 tokens

Input: ¥250.18/M

Output: ¥786.28/M

Try in Chat Get API Key

Specifications

Modalities

Input

text

Output

text

Supported Parameters

frequency_penalty

include_reasoning

logit_bias

logprobs

max_tokens

min_p

parallel_tool_calls

presence_penalty

reasoning

reasoning_effort

repetition_penalty

response_format

seed

stop

structured_outputs

temperature

tool_choice

tools

top_k

top_logprobs

top_p

Max Output Tokens

131,072

Reasoning Configuration

Default: Thinking on (effort: high)
Selectable effort levels: xhigh
high
Turning thinking off: Possible (reasoning.enabled: false)

How to control thinking, and what it costs

Code Examples

curl https://api.fastmetal.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "glm-5.2",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How GLM 5.2 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's in the word 'strawberry', let's look at the word letter by letter: 1. **s** - no 'r' 2. **t** - no 'r' 3. **r** - this is the 1st 'r' 4. **a** - no 'r' 5. **w** - no 'r' 6. **b** - no 'r' 7. **e** - no 'r' 8. **r** - this is the 2nd 'r' 9. **r** - this is the 3rd 'r' 10. **y** - no 'r' Total count: 3 There are **3** 'r's in the word 'strawberry'.

2.6s response439 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…

The error `TypeError: Cannot read properties of undefined (reading 'map')` happens because the `users` prop being passed to your `UserList` component is currently `undefined`. When JavaScript tries to call `.map()` on `undefined`, it throws this error. Here are the best ways to fix this: ### Fix 1: Provide a default value (Recommended) You can provide a default empty array `[]` when destructuring the props. This ensures that even if `users` is not passed down, the `.map()` function will still have an array to iterate over (resulting in an empty list rather than a crash). ```jsx function UserList({ users = [] }) { return ( <ul> {users.map(user => <li key={user.id}>{user.name}</…

8.3s response1006 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):…

Here is a review of your Python function, broken down by readability, performance, and best practices, followed by a refactored version of the code. ### 1. Best Practices * **Move imports to the top:** Importing modules inside a function is generally discouraged. While Python caches imports, putting `import requests` and `import time` at the top of your file is the standard convention and improves readability. * **Avoid bare `except:` blocks:** Using a bare `except:` catches everything, including `KeyboardInterrupt` and `SystemExit`. This makes it hard to interrupt your program if it gets stuck in a loop. You should catch specific exceptions, such as `requests.exceptions.RequestException` (…

10.9s response2061 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the GLM 5.2 API cost?: On FastMetal, GLM 5.2 is billed per token in yen: ¥250.18 per 1M input tokens and ¥786.28 per 1M output tokens, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
Can I call GLM 5.2 with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "glm-5.2" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of GLM 5.2?: 1,048,576 tokens, shared between the prompt and the response.
What do I need to try GLM 5.2?: 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.