GLM-5.3 / GLM-5.2 API — Access via an AI API Gateway
Call Zhipu (Z.ai) GLM-5.3 and GLM-5.2 through byesu — an AI API gateway with pay-as-you-go billing and no subscription. It uses the OpenAI-compatible API, so existing OpenAI SDK code only needs a new base URL and token. Note: GLM needs a separate token in the Glm group — see below.
Model specs below are quoted from Z.ai’s official documentation, checked on 2026-10-22.
What It Is
GLM-5.3 is Zhipu’s current flagship model, aimed at complex software engineering and agent tasks. It shares its base model with GLM-5.2, and its gains come from post-training; Z.ai reports a 50% coding improvement over GLM-5.2 on Z.ai Code Bench. GLM-5.2 is the previous flagship foundation model (GLM-5.2 official page).
| Item | Value |
|---|---|
| Model ID on byesu | glm-5.3 · glm-5.2 |
| Context window | 1M tokens |
| Max output | 128K tokens |
| Input → output | Text → text |
Thinking (glm-5.3) | Always on; reasoning_effort accepts low / high / max, default max |
| Tool calling / structured output / context caching | Supported |
Models available on byesu
| Model ID | Notes |
|---|---|
glm-5.3 | Current flagship; thinking always on; list price $1.4 / $4.4 |
glm-5.2 | Previous flagship, same base model; thinking can be turned off; list price $1.4 / $4.4 |
How Pricing Works
byesu bills per token with no monthly fee. The actual price of every model is shown live in the model list after you sign in, and the console records the charge for each request.
For reference, Z.ai’s official list price (same for both) is $1.4 input, $0.26 cached input and $4.4 output per million tokens (official pricing page).
Create a token in the Glm group
glm-5.3 and glm-5.2 are served by the Glm group, which is not part of the auto group: a default auto-group token returns “no available channel”. Go to Console → Tokens, create a new token, set its group to Glm, and call the model with that token. See Choosing a Group.
How to Call It
The base URL depends on the API format:
- OpenAI-compatible (
/v1/chat/completions) →https://byesu.com/v1
Authenticate with Authorization: Bearer sk-YOUR_TOKEN.
Option 1: curl
curl https://byesu.com/v1/chat/completions \
-H "Authorization: Bearer sk-YOUR_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-5.3",
"messages": [
{"role": "user", "content": "Explain what an API gateway is in one sentence"}
]
}'Option 2: Python (OpenAI SDK)
from openai import OpenAI
client = OpenAI(api_key="sk-YOUR_TOKEN", base_url="https://byesu.com/v1")
resp = client.chat.completions.create(
model="glm-5.3",
messages=[{"role": "user", "content": "Explain what an API gateway is in one sentence"}],
)
print(resp.choices[0].message.content)According to Z.ai’s documentation, glm-5.3 no longer supports disabling thinking: when migrating from glm-5.2, if your code sends thinking: {"type": "disabled"}, change it to enabled and set reasoning_effort to low, otherwise requests fail. To use glm-5.2, change only the model field.
FAQ
Should I use glm-5.3 or glm-5.2?
Both share the same base model, context window and list price. glm-5.3 has further post-training and Z.ai reports clearly better coding results, but thinking is always on; older code that needs thinking disabled can stay on glm-5.2.
How much does the GLM-5.3 API cost on byesu?
byesu bills per token with no subscription; the live price is shown in the model list after you sign in. For reference, Z.ai’s official list price is $1.4 input, $0.26 cached input and $4.4 output per million tokens.
How long is the GLM-5.3 context window?
According to Z.ai’s documentation, glm-5.3 and glm-5.2 both have a 1M-token context window with up to 128K output tokens.
Why does my default token return “no available channel” for glm-5.3?
GLM is not part of the auto group. Create a new token in the Glm group in the console, call glm-5.3 or glm-5.2 with it, and check that the model ID matches the console exactly.
Can I call GLM-5.3 with the OpenAI SDK?
Yes. Set the SDK base_url to https://byesu.com/v1, use a Glm-group token as the api_key, and set model to glm-5.3.