Chat Completions: OpenAI-Compatible API Endpoint

Overview

Parallel AI’s chat completions endpoint is a drop-in replacement for the OpenAI Chat Completions API. If you already use the OpenAI SDK or any OpenAI-compatible library, you can switch to Parallel AI by changing only two things: the base URL and the API key. Your existing code requires no other modifications. Endpoint: POST https://api.parallellabs.app/api/v0/chat/completions

This endpoint follows the OpenAI Chat Completions specification. Any tool, library, or framework built for the OpenAI API will work seamlessly with Parallel AI.

Request Parameters

Parameter	Type	Description
`model`	string	The model to use (e.g., `gpt-4o-mini`, `gpt-4o`)
`messages`	array	Array of message objects with `role` and `content`
`temperature`	number	Sampling temperature between `0` and `2` (default: `1.0`)
`max_tokens`	integer	Maximum number of tokens to generate
`stream`	boolean	Stream the response as SSE chunks (default: `false`)
`top_p`	number	Nucleus sampling probability mass
`frequency_penalty`	number	Penalize repeated tokens by frequency
`presence_penalty`	number	Penalize tokens that have already appeared
`tools`	array	List of tools (functions) the model may call
`tool_choice`	string / object	Controls how the model selects tools
`response_format`	object	Force output format (e.g., `{"type": "json_object"}`)
`stop`	string / array	Up to 4 sequences where generation stops

Each message in messages must have:

role: one of system, user, assistant, or tool
content: the message text (or an array of content parts for multimodal inputs)

Quickstart Examples

Using the OpenAI Python SDK

Point the OpenAI client at Parallel AI’s base URL — no other changes needed.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.parallellabs.app/api/v0"
)

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "What is machine learning?"}]
)
print(response.choices[0].message.content)

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.parallellabs.app/api/v0"
)

stream = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Explain neural networks step by step."}],
    stream=True
)

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

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.parallellabs.app/api/v0"
)

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "system", "content": "You are a concise technical assistant."},
        {"role": "user", "content": "What is a transformer model?"}
    ],
    temperature=0.7,
    max_tokens=256
)
print(response.choices[0].message.content)

Using cURL

curl -X POST "https://api.parallellabs.app/api/v0/chat/completions" \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {"role": "user", "content": "What is machine learning?"}
    ],
    "temperature": 0.7
  }'

curl -X POST "https://api.parallellabs.app/api/v0/chat/completions" \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {"role": "user", "content": "Explain neural networks step by step."}
    ],
    "stream": true
  }'

Streaming

When stream is set to true, the API returns a stream of Server-Sent Events (SSE). Each event contains a JSON delta with the incremental content. The stream ends with a final data: [DONE] message. Streaming is useful for:

Displaying responses word-by-word in a UI for a faster perceived response time
Long-form generation where you want to process output incrementally
Reducing time-to-first-token in latency-sensitive applications

The OpenAI SDK handles SSE parsing automatically when you pass stream=True. For raw HTTP clients, parse each data: line as JSON and concatenate choices[0].delta.content.

Response Format

A standard (non-streaming) response looks like this:

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1710000000,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Machine learning is a subset of artificial intelligence..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 14,
    "completion_tokens": 87,
    "total_tokens": 101
  }
}

Token Usage

The usage object in every response reports:

Field	Description
`prompt_tokens`	Tokens consumed by your input messages
`completion_tokens`	Tokens generated in the model’s response
`total_tokens`	Sum of prompt and completion tokens

Monitor total_tokens to track and optimize your API usage costs.

Using the OpenAI Node.js SDK

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_API_KEY",
  baseURL: "https://api.parallellabs.app/api/v0",
});

const response = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [{ role: "user", content: "What is machine learning?" }],
});

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

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_API_KEY",
  baseURL: "https://api.parallellabs.app/api/v0",
});

const stream = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [{ role: "user", content: "Explain neural networks step by step." }],
  stream: true,
});

for await (const chunk of stream) {
  const content = chunk.choices[0]?.delta?.content ?? "";
  process.stdout.write(content);
}

Next Steps

Chat Completions API Reference

View the full request schema, response types, and error codes.

OpenAI Compatibility Guide

Learn exactly which OpenAI features are supported and how to migrate existing projects.

Get Started

Core Features

Integrations

Platform

Chat Completions: OpenAI-Compatible API Endpoint

Overview

Request Parameters

Quickstart Examples

Using the OpenAI Python SDK

Using cURL

Streaming

Response Format

Token Usage

Using the OpenAI Node.js SDK

Next Steps

Chat Completions API Reference

OpenAI Compatibility Guide

​Overview

​Request Parameters

​Quickstart Examples

​Using the OpenAI Python SDK

​Using cURL

​Streaming

​Response Format

​Token Usage

​Using the OpenAI Node.js SDK

​Next Steps

Chat Completions API Reference

OpenAI Compatibility Guide

Overview

Request Parameters

Quickstart Examples

Using the OpenAI Python SDK

Using cURL

Streaming

Response Format

Token Usage

Using the OpenAI Node.js SDK

Next Steps