Skip to main content

​
API Overview

The Assisters API is fully compatible with the OpenAI API specification, making it easy to migrate existing applications or use familiar SDKs.

​
Base URL

All API requests should be made to: 
https://api.assisters.dev/v1

​
Authentication

Authenticate using your API key in the Authorization header: 
Authorization: Bearer ask_your_api_key_here

Get Your API Key

Create an API key in your dashboard

​
Request Format

All requests should:
  • Use HTTPS
  • Include Content-Type: application/json header
  • Send JSON-encoded request bodies
curl https://api.assisters.dev/v1/chat/completions \
  -H "Authorization: Bearer ask_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3.1-8b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

​
Response Format

All responses are JSON-encoded and follow the OpenAI response format: 
{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1706745600,
  "model": "llama-3.1-8b",
  "choices": [...],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 20,
    "total_tokens": 30
  }
}

​
Available Endpoints

EndpointMethodDescription
/v1/chat/completionsPOSTGenerate chat completions
/v1/embeddingsPOSTCreate text embeddings
/v1/moderatePOSTContent moderation
/v1/rerankPOSTDocument reranking
/v1/modelsGETList available models

​
Response Headers

Every response includes useful headers:
HeaderDescription
X-Request-IDUnique request identifier for debugging
X-Processing-Time-MsRequest processing time in milliseconds
X-RateLimit-Limit-RPMYour requests per minute limit
X-RateLimit-Remaining-RPMRemaining requests this minute
X-RateLimit-Limit-TPMYour tokens per minute limit
X-RateLimit-Remaining-TPMRemaining tokens this minute

​
Rate Limits

Rate limits depend on your subscription tier:
TierRPMTPM
Free10100,000
Developer1001,000,000
Startup5005,000,000
EnterpriseCustomCustom
When you hit a rate limit, you’ll receive a 429 Too Many Requests response with a Retry-After header.

​
Streaming

For chat completions, you can enable streaming for real-time responses: 
{
  "model": "llama-3.1-8b",
  "messages": [...],
  "stream": true
}
Streaming responses use Server-Sent Events (SSE): 
data: {"id":"chatcmpl-abc","choices":[{"delta":{"content":"Hello"}}]}

data: {"id":"chatcmpl-abc","choices":[{"delta":{"content":" world"}}]}

data: [DONE]

​
Idempotency

For POST requests, you can include an Idempotency-Key header to safely retry failed requests: 
curl https://api.assisters.dev/v1/chat/completions \
  -H "Authorization: Bearer ask_your_api_key" \
  -H "Idempotency-Key: unique-request-id-123" \
  -H "Content-Type: application/json" \
  -d '{...}'

​
SDKs

Use the official OpenAI SDK with our base URL: 
from openai import OpenAI

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

​
Versioning

The API is currently at version v1. We follow semantic versioning and will communicate any breaking changes well in advance.

View Changelog

See the latest API updates and changes