OpenAI Chat Completions

See the full /answer endpoint reference here.

Get Started

Get your Exa API key

An example of your existing openai chat completions code

python
from openai import OpenAI

client = OpenAI(api_key="YOUR_OPENAI_API_KEY")

completion = client.chat.completions.create(
  model="gpt-4o-mini",
  messages= [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What are the latest developments in quantum computing?"}
  ]
)

print(completion.choices[0].message.content)  # print the response content

Replace the base URL with api.exa.ai

Exa will parse through your messages and send only the last message to the /answer endpoint.

python
from openai import OpenAI

client = OpenAI(
  base_url="https://api.exa.ai", # use exa as the base url
  api_key="YOUR_EXA_API_KEY", # update your api key
)

completion = client.chat.completions.create(
  model="exa", # or exa-pro or exa-research
  messages = [
  {"role": "system", "content": "You are a helpful assistant."},
  {"role": "user", "content": "What are the latest developments in quantum computing?"}
],

# use extra_body to pass extra parameters to the /answer endpoint
  extra_body={
    "text": True # include full text from sources
  }
)

print(completion.choices[0].message.content)  # print the response content
print(completion.choices[0].message.citations)  # print the citations

An example of your existing openai chat completions code

python
from openai import OpenAI

client = OpenAI(api_key="YOUR_OPENAI_API_KEY")

completion = client.chat.completions.create(
  model="gpt-4o-mini",
  messages= [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What are the latest developments in quantum computing?"}
  ]
)

print(completion.choices[0].message.content)  # print the response content

Replace the base URL with api.exa.ai

Exa will parse through your messages and send only the last message to the /answer endpoint.

python
from openai import OpenAI

client = OpenAI(
  base_url="https://api.exa.ai", # use exa as the base url
  api_key="YOUR_EXA_API_KEY", # update your api key
)

completion = client.chat.completions.create(
  model="exa", # or exa-pro or exa-research
  messages = [
  {"role": "system", "content": "You are a helpful assistant."},
  {"role": "user", "content": "What are the latest developments in quantum computing?"}
],

# use extra_body to pass extra parameters to the /answer endpoint
  extra_body={
    "text": True # include full text from sources
  }
)

print(completion.choices[0].message.content)  # print the response content
print(completion.choices[0].message.citations)  # print the citations

An example of your existing openai chat completions code

javascript
import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: "YOUR_OPENAI_API_KEY",
  });

async function main() {
  const completion = await openai.chat.completions.create({
    model: "gpt-4o-mini",
    messages: [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What are the latest developments in quantum computing?"}
    ],
    store: true,
    stream: true,
  });

  for await (const chunk of completion) {
    console.log(chunk.choices[0].delta.content);
  }
}

main();

Replace the base URL with api.exa.ai

Exa will parse through your messages and send only the last message to the /answer endpoint.

javascript
import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "https://api.exa.ai", // use exa as the base url
  apiKey: "YOUR_EXA_API_KEY", // update your api key
});

async function main() {
  const completion = await openai.chat.completions.create({
    model: "exa", // or exa-pro
    messages: [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What are the latest developments in quantum computing?"}
    ],
    store: true,
    stream: true,
    extra_body: {
      "text": true // include full text from sources
    }
  });

  for await (const chunk of completion) {
    console.log(chunk.choices[0].delta.content);
  }
}

main();

An example of your existing openai chat completions code

bash
curl https://api.openai.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "What are the latest developments in quantum computing?"
      }
    ],
    "stream": true
  }'

Replace the base URL with api.exa.ai

Exa will parse through your messages and send only the last message to the /answer endpoint.

bash
curl https://api.exa.ai/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YOUR_EXA_API_KEY" \
  -d '{
    "model": "exa", 
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "What are the latest developments in quantum computing?"
      }
    ],
    "extra_body": {
      "text": true
    }
  }'

Getting Started

API Reference

RAG Quick Start Guide

Concepts

Admin

OpenAI Chat Completions

Get Started

Get your Exa API key

Getting Started

API Reference

RAG Quick Start Guide

Concepts

Admin

​Get Started

Get your Exa API key

Get Started