Skip to main content

​
Introduction to Assisters API

Assisters API provides OpenAI-compatible endpoints for accessing open-source AI models. Whether you’re building chatbots, search systems, or content moderation tools, our API offers a simple, cost-effective solution.

​
What is Assisters API?

Assisters API is a unified interface for accessing multiple open-source AI models through a single API. We handle the infrastructure, scaling, and optimization so you can focus on building great products.

OpenAI Compatible

Use the same code you write for OpenAI - just change the base URL

18+ Models

Access Llama, Mistral, Qwen, and more through one API

Pay Per Token

Only pay for what you use, starting at $0.08 per million tokens

99.9% Uptime

Enterprise-grade reliability with SLA guarantees

​
Key Features

​
Chat Completions

Generate conversational responses with streaming support. Perfect for chatbots, assistants, and interactive applications. 
response = client.chat.completions.create(
    model="llama-3.1-8b",
    messages=[{"role": "user", "content": "Explain quantum computing"}],
    stream=True
)

​
Text Embeddings

Create vector representations for semantic search, clustering, and similarity matching. 
response = client.embeddings.create(
    model="e5-large-v2",
    input="Your text here"
)

​
Content Moderation

Detect harmful, inappropriate, or policy-violating content before it reaches your users. 
response = client.moderations.create(
    model="llama-guard-3",
    input="Content to check"
)

​
Document Reranking

Improve search results by reranking documents based on relevance to a query. 
response = client.rerank.create(
    model="bge-reranker-v2",
    query="search query",
    documents=["doc1", "doc2", "doc3"]
)

​
Available Models

We offer models across four categories:
CategoryModelsStarting Price
ChatLlama 3.1, Mistral, Qwen, Phi-3$0.08/M tokens
EmbeddingsE5, BGE, Jina, Nomic$0.01/M tokens
ModerationLlama Guard, ShieldGemma$0.15/M tokens
RerankingBGE Reranker, Jina Reranker$0.05/M tokens

View All Models

Browse our complete model catalog with detailed specifications

​
Use Cases

Build conversational AI that understands context and provides helpful responses. Our chat models support multi-turn conversations with streaming for real-time interaction.
Automatically detect harmful content, spam, or policy violations before they reach your platform. Protect your users and brand.
Combine embeddings with chat completions to build retrieval-augmented generation systems that answer questions from your knowledge base.

​
Getting Started

Ready to build? Follow these steps:
1

Create an Account

Sign up at assisters.dev to get your free API key with 100K tokens.
2

Install the SDK

Use the official OpenAI SDK - it works with Assisters API out of the box.
3

Make Your First Call

Follow our quickstart guide to send your first request.

​
Support & Resources

API Playground

Test API calls directly in your browser

Community Discord

Get help from our community and team

Status Page

Monitor API uptime and incidents

Contact Support

Reach our support team directly