Authentication
The API uses API keys for authentication. Contact [email protected] to get API Keys.
Always keep your API key confidential! Never display it in publicly accessible areas like client-side scripts or mobile apps. For live operations, ensure your API key is accessed securely, preferably from a backend server, using environmental variables or a key management system.
All API requests should include your API key in an Authorization HTTP header as follows:
Authorization: Bearer API_KEY
Making requests
You can make an API call by specifying the model owner and the model in the model parameters. Please keep in mind to replace $API_KEY with your API key.
OpenAI gpt-3.5-turbo
curl https://api.platform.a15t.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $API_KEY" \
-d '{
"model": "openai/gpt-3.5-turbo",
"messages": [{"role": "user", "content": "Say this is a test!"}],
"temperature": 0.7
}'
Anthropic claude-2
curl https://api.platform.a15t.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $API_KEY" \
-d '{
"model": "anthropic/claude-2",
"messages": [{"role": "user", "content": "Say this is a test!"}],
"temperature": 0.7
}'
Starting using OpenAI Python Library
pip install openai>=1.0.0
Completions
from openai import OpenAI
client = OpenAI(
api_key="sk-...",
base_url="https://api.platform.a15t.com/v1",
)
completion = client.completions.create(model="openai/gpt-3.5-turbo-instruct", prompt="Hello world")
print(completion.choices[0].text)
Chat completions
from openai import OpenAI
client = OpenAI(
api_key="sk-...",
base_url="https://api.platform.a15t.com/v1",
)
completion = client.chat.completions.create(model="anthropic/claude-2", messages=[{"role": "user", "content": "Hello world"}])
print(completion.choices[0].message.content)
Embeddings
from openai import OpenAI
client = OpenAI(
api_key="sk-...",
base_url="https://api.platform.a15t.com/v1",
)
embeddings = client.embeddings.create(model="openai/text-embedding-3-small", input="Hello world", dimensions=100)
print(embeddings.data[0].embedding)