Skip to main content

​
Quickstart

This guide will help you make your first API call in under 5 minutes.

​
Prerequisites

An Assisters account (sign up free)
An API key from your dashboard
Python 3.8+ or Node.js 18+ installed

​
Step 1: Get Your API Key

  1. Log in to your Assisters Dashboard
  2. Navigate to API Keys
  3. Click Create New Key
  4. Copy your key (it starts with ask_)
Keep your API key secure! Never expose it in client-side code or commit it to version control.

​
Step 2: Install the SDK

Since Assisters API is OpenAI-compatible, you can use the official OpenAI SDK: 
pip install openai

​
Step 3: Make Your First Request

from openai import OpenAI

# Initialize the client with Assisters API
client = OpenAI(
    api_key="ask_your_api_key_here",
    base_url="https://api.assisters.dev/v1"
)

# Create a chat completion
response = client.chat.completions.create(
    model="llama-3.1-8b",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the capital of France?"}
    ]
)

print(response.choices[0].message.content)
# Output: The capital of France is Paris.

​
Step 4: Use Streaming (Optional)

For real-time responses, enable streaming: 
from openai import OpenAI

client = OpenAI(
    api_key="ask_your_api_key_here",
    base_url="https://api.assisters.dev/v1"
)

# Stream the response
stream = client.chat.completions.create(
    model="llama-3.1-8b",
    messages=[
        {"role": "user", "content": "Write a haiku about coding"}
    ],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

​
Step 5: Try Other Endpoints

​
Create Embeddings

response = client.embeddings.create(
    model="e5-large-v2",
    input="The quick brown fox jumps over the lazy dog"
)

print(f"Embedding dimensions: {len(response.data[0].embedding)}")
# Output: Embedding dimensions: 1024

​
Content Moderation

response = client.moderations.create(
    model="llama-guard-3",
    input="Hello, how are you today?"
)

print(f"Flagged: {response.results[0].flagged}")
# Output: Flagged: False

​
Understanding the Response

A typical chat completion response looks like this: 
{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1706745600,
  "model": "llama-3.1-8b",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The capital of France is Paris."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 8,
    "total_tokens": 33
  }
}
The usage field shows token consumption, which determines your billing. See token counting for details.

​
Environment Variables

For production, use environment variables instead of hardcoding your API key: 
ASSISTERS_API_KEY=ask_your_api_key_here

​
Next Steps

Authentication

Learn about API keys and security best practices

API Reference

Explore all available endpoints and parameters

Models

Choose the right model for your use case

Rate Limits

Understand rate limits and how to handle them

​
Troubleshooting

  • Check that your API key is correct and starts with ask_
  • Ensure the key hasn’t been revoked in your dashboard
  • Verify you’re using the Authorization: Bearer header format
  • You’ve exceeded your tier’s rate limit (RPM or TPM)
  • Wait a moment and retry, or upgrade your plan
  • Check X-RateLimit-* headers for current limits
  • Check the model name matches exactly (case-sensitive)
  • Some models may require a paid plan
  • See available models for the full list