Skip to main content
Documentation

Build with Assisters

Everything you need to integrate AI models into your applications. From quickstart guides to detailed API references.

TL;DR

  • API Base URL: https://api.assisters.dev/v1
  • OpenAI-compatible - use existing OpenAI SDKs
  • Models: Chat v1/v2, Embed v1, Moderation v1, Rerank v1
  • Pricing: pay per million tokens per model, from a shared wallet — no subscriptions

Get Started in Seconds

Make your first API call in just a few lines of code

cURL
curl https://api.assisters.dev/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "assisters-chat-v1",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'
Python
from assisters import Assisters

client = Assisters(api_key="YOUR_API_KEY")

response = client.chat.completions.create(
  model="assisters-chat-v1",
  messages=[
    {"role": "user", "content": "Hello!"}
  ]
)

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

Frequently Asked Questions

Quick answers to common questions about the Assisters API.

What is the Assisters API base URL?

The Assisters API base URL is https://api.assisters.dev/v1. All API endpoints are relative to this URL. For example, chat completions are at https://api.assisters.dev/v1/chat/completions.

Is Assisters API compatible with OpenAI?

Yes, Assisters API is fully OpenAI-compatible. You can use the OpenAI Python or Node.js SDKs by setting the base URL to https://api.assisters.dev/v1. No code changes required beyond the URL and API key.

What models does Assisters offer?

Assisters offers proprietary AI models: Assisters Chat v1/v2 for conversations (128K context), Assisters Embed v1 for text embeddings (8K context), Assisters Moderation v1 for content safety, and Assisters Rerank v1 for document reranking.

How do I authenticate API requests?

Include your API key in the Authorization header: 'Authorization: Bearer YOUR_API_KEY'. Get your API key from the dashboard at assisters.dev/dashboard/api-keys. Never expose your key in client-side code.

What are the rate limits?

Rate limits are applied at the account level (requests per minute). There are no subscription tiers — rate limits scale with your account, not a monthly plan.

How does pricing work?

Assisters is pure pay-per-token: you pay a separate per-million-token rate for input and output of each model, deducted from a wallet balance shared across assisters.io and assisters.dev. No subscriptions, no monthly plans. See current per-model rates at assisters.dev/pricing.

Need Help?

Can't find what you're looking for? Our support team is here to help.