Together AI provides an OpenAI-compatible API for open-source model inference and fine-tuning. Base URL: https://api.together.xyz/v1. Works with the official together Python SDK or any OpenAI-compatible client.
# Python (official)
pip install together
# Node.js (use OpenAI SDK with custom base URL)
npm install openai
# .env
TOGETHER_API_KEY=your-api-key-here
from together import Together
client = Together(api_key=os.environ["TOGETHER_API_KEY"])
response = client.chat.completions.create(
model="meta-llama/Llama-3.3-70B-Instruct-Turbo",
messages=[{"role": "user", "content": "Say hello"}],
max_tokens=10,
)
print(f"Connected! Response: {response.choices[0].message.content}")
import OpenAI from 'openai';
const client = new OpenAI({
apiKey: process.env.TOGETHER_API_KEY,
baseURL: 'https://api.together.xyz/v1',
});
const response = await client.chat.completions.create({
model: 'meta-llama/Llama-3.3-70B-Instruct-Turbo',
messages: [{ role: 'user', content: 'Say hello' }],
max_tokens: 10,
});
console.log(`Connected! ${response.choices[0].message.content}`);
models = client.models.list()
for m in models.data[:5]:
print(f"{m.id} ({m.type})")
| Error | Cause | Solution |
|---|---|---|
401 Unauthorized |
Invalid API key | Check key at api.together.xyz |
Model not found |
Wrong model ID | Use client.models.list() to verify |
ModuleNotFoundError |
SDK not installed | pip install together |
429 Too Many Requests |
Rate limit | Back off and retry |
Proceed to together-hello-world for inference examples.