Getting Started

This guide will walk you through making your first API call to Synthetic in just a few minutes.

Tip

Check out our Guides for step-by-step tutorials on setting up various frontends and development tools with Synthetic.

Step 1: Get Your API Key

Your API Key:

Step 2: Install an OpenAI Client Library

Since Synthetic is OpenAI-compatible, you can use any OpenAI client library:

Python
Node.js

pip install openai

Other Languages

Synthetic works with OpenAI client libraries in any language including:

Go: go-openai
Rust: async-openai
Ruby: ruby-openai
PHP: openai-php
Java: openai-java

Step 3: Configure Your Client

Set up your client to point to Synthetic's API:

Python
TypeScript

import os
import openai

client = openai.OpenAI(
api_key=os.environ.get("SYNTHETIC_API_KEY"),
base_url="https://api.glhf.chat/v1/",
)

Step 4: Make Your First API Call

Chat Completions

Python
TypeScript
curl

completion = client.chat.completions.create(
model="hf:zai-org/GLM-4.6",
messages=[
  {"role": "system", "content": "You are a helpful assistant."},
  {"role": "user", "content": "Explain quantum computing in simple terms."}
]
)

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

Streaming Responses

For long responses, streaming provides a better user experience:

Python
TypeScript

completion = client.chat.completions.create(
model="hf:zai-org/GLM-4.6",
messages=[
  {"role": "system", "content": "You are a helpful assistant."},
  {"role": "user", "content": "Write a detailed explanation of machine learning."}
],
stream=True
)

for chunk in completion:
if chunk.choices[0].delta.content is not None:
  print(chunk.choices[0].delta.content, end='', flush=True)

Step 5: Choose Your Model

Explore available models using the /models endpoint:

Python
TypeScript
curl

models = client.models.list()
for model in models.data:
print(model.id)

Tip

The /models endpoint will always show all always-on models, as well as any on-demand models you've recently used.

Error Handling

python

try:
  completion = client.chat.completions.create(
    model="hf:zai-org/GLM-4.6",
    messages=[{"role": "user", "content": "Hello!"}]
  )
except openai.APIError as e:
  print(f"API error: {e}")
except openai.RateLimitError as e:
  print(f"Rate limit exceeded: {e}")

Next Steps

Explore the API Reference: Check out detailed documentation for /chat/completions and /messages.
Integration Guides: See how to integrate with tools like Octofriend, Claude Code, and more!
Monitor Usage: Track your API usage on your Billing page.

Need Help?

If you run into issues:

Check that your API key is correctly set
Verify the model name includes the hf: prefix
Ask for help on our Discord Server!

Happy coding! 🚀

completion = client.chat.completions.create( model="hf:zai-org/GLM-4.6", messages=[ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Explain quantum computing in simple terms."} ] ) print(completion.choices[0].message.content)

completion = client.chat.completions.create( model="hf:zai-org/GLM-4.6", messages=[ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Write a detailed explanation of machine learning."} ], stream=True ) for chunk in completion: if chunk.choices[0].delta.content is not None: print(chunk.choices[0].delta.content, end='', flush=True)

try: completion = client.chat.completions.create( model="hf:zai-org/GLM-4.6", messages=[{"role": "user", "content": "Hello!"}] ) except openai.APIError as e: print(f"API error: {e}") except openai.RateLimitError as e: print(f"Rate limit exceeded: {e}")