Satryx Docs
SDKs

Python SDK

The official Satryx Python library — sync and async clients with full type hints.

Installation

bash
pip install satryx

Requires Python 3.9+ and httpx ≥ 0.25.

Setup

python
from satryx import Satryx

# Reads SATRYX_API_KEY env var automatically
client = Satryx()

# Or pass explicitly
client = Satryx(api_key="satryx_live_…")
Tip:Set SATRYX_API_KEY in your environment so you never hard-code the key.

Chat completions

Non-streaming

python
response = client.chat.completions.create(
    model="llama-3.1-70b",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Summarize quantum entanglement."},
    ],
    temperature=0.7,
    max_tokens=1024,
)
print(response.choices[0].message.content)
print(f"Tokens used: {response.usage.total_tokens}")

Streaming

python
with client.chat.completions.create(
    model="llama-3.1-70b",
    messages=[{"role": "user", "content": "Write a poem about the sea."}],
    stream=True,
) as stream:
    for chunk in stream:
        delta = chunk.choices[0].delta.content
        if delta:
            print(delta, end="", flush=True)
print()  # newline when done

Image generation

python
response = client.images.generate(
    prompt="Cyberpunk cityscape at dusk, neon reflections on wet pavement",
    model="flux-dev",
    n=2,
    size="1024x1024",
)
for img in response.data:
    print(img.url)  # download before URL expires (1 hour)

Async client

python
import asyncio
from satryx import AsyncSatryx

async def main():
    async with AsyncSatryx() as client:
        response = await client.chat.completions.create(
            model="llama-3.1-70b",
            messages=[{"role": "user", "content": "Hello!"}],
        )
        print(response.choices[0].message.content)

        # Async streaming
        async with client.chat.completions.create(
            model="llama-3.1-70b",
            messages=[{"role": "user", "content": "Count to 5."}],
            stream=True,
        ) as stream:
            async for chunk in stream:
                delta = chunk.choices[0].delta.content
                if delta:
                    print(delta, end="", flush=True)

asyncio.run(main())

Error handling

python
from satryx import (
    Satryx,
    AuthenticationError,
    RateLimitError,
    APIConnectionError,
    APIStatusError,
)

client = Satryx()

try:
    response = client.chat.completions.create(
        model="llama-3.1-70b",
        messages=[{"role": "user", "content": "Hello"}],
    )
except AuthenticationError:
    print("Bad API key")
except RateLimitError as e:
    print(f"Rate limited — retry in {e.retry_after_seconds}s")
except APIConnectionError:
    print("Network error")
except APIStatusError as e:
    print(f"HTTP {e.status_code}: {e.message}")

List models

python
models = client.models.list()
for m in models.data:
    print(m.id, m.capabilities)

Configuration options

ParameterTypeDescription
api_keystrAPI key. Defaults to SATRYX_API_KEY env var.
base_urlstrAPI base URL. Default: "https://api.satryx.ai".
timeoutfloatRequest timeout in seconds. Default 60.
max_retriesintAutomatic retries on 429/5xx. Default 3.