Switch to FriendliAI and get up to 50K inference credit! — Apply now
zai-org
Run this model inference with a simple API call.
API Example
Model provider
zai-org
Model tree
Base
this model
Modalities
Input
Text
Output
Text
Pricing
Serverless Endpoints
Input
$1 / 1M tokens
Output
$3.2 / 1M tokens
Dedicated Endpoints
View detailsSupported Functionality
Serverless Endpoints
Dedicated Endpoints
Container
More information
from openai import OpenAI
import os
client = OpenAI(
api_key=os.getenv("FRIENDLI_TOKEN"),
base_url="https://api.friendli.ai/serverless/v1",
)
completion = client.chat.completions.create(
model="zai-org/GLM-5",
extra_body={
"chat_template_kwargs": {
"enable_thinking": True
}
},
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Tell me a funny joke."},
],
)
print(completion.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.FRIENDLI_TOKEN,
baseURL: "https://api.friendli.ai/serverless/v1",
});
async function main() {
const completion = await client.chat.completions.create({
model: "zai-org/GLM-5",
chat_template_kwargs: {
"enable_thinking": true
},
messages: [
{ role: "system", content: "You are a helpful assistant." },
{ role: "user", content: "Tell me a funny joke." },
],
});
console.log(completion.choices[0].message.content);
}
main().catch(console.error);
curl -X POST https://api.friendli.ai/serverless/v1/chat/completions \
-H "Authorization: Bearer $FRIENDLI_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"model": "zai-org/GLM-5",
"chat_template_kwargs": {
"enable_thinking": true
},
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Tell me a funny joke."
}
]
}'