Your First API Call

The Arcee Platform API is OpenAI compatible. It can be accessed through your command line, or, with minor configuration changes, through the OpenAI SDK.

Parameter

Value

base_url

https://api.arcee.ai/api/v1/chat/completions

api_key

Generate API key

1. Generate an API Key

Create an API key from your Arcee Platform dashboard. This key authenticates all API requests.

2. Choose a Model

Specify the model you want to run inference with. Arcee currently provides the following production models:

trinity-mini-thinking
trinity-nano-thinking

3. Run the Code Snippet

Use your API key and model name in the sample code below to make your first request.

curl -X POST "https://api.arcee.ai/api/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <Arcee Platform API Key>" \
  -d '{
        "model": "<Model Name>",
        "messages": [
          {"role": "system", "content": "You are a helpful assistant."},
          {"role": "user", "content": "Greetings!"}
        ],
        "stream": false
      }'

from openai import OpenAI 

client = OpenAI(
    api_key="<Arcee Platform API Key>", 
    base_url="https://api.arcee.ai/api/v1")
response = client.chat.completions.create(
    model = "<Model Name>", # Change to whichever Arcee AI model you want to invoke
    messages = [ 
        {"role":"system", "content":"You are a helpful assistant"},
        {"role":"user", "conent": "Hello"},
    ],
    steam = false 
)

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

import OpenAI from "openai";

const openai = new OpenAI({
        baseURL: 'https://api.arcee.ai/api/v1',
        apiKey: '<Arcee Platform API Key>'
});

async function main() {
  const completion = await openai.chat.completions.create({
    messages: [{ role: "system", content: "You are a helpful assistant." }],
    model: "<Model Name>",
  });

  console.log(completion.choices[0].message.content);
}

main();

PreviousPost Trains NextChat Completion

Last updated 20 days ago