Code beginner · 3 min read

How to translate text with OpenAI API in Python

Direct answer

Use the OpenAI Python SDK with client.chat.completions.create and a prompt instructing the model to translate text, specifying source and target languages.

Setup

Install

bash

pip install openai

Env vars

OPENAI_API_KEY

Imports

python

import os
from openai import OpenAI

Examples

inTranslate 'Hello, how are you?' from English to Spanish.

outHola, ¿cómo estás?

inTranslate 'Good morning, have a nice day!' from English to French.

outBonjour, passez une bonne journée !

inTranslate 'Thank you very much' from English to Japanese.

outどうもありがとうございます

Integration steps

Import OpenAI and os modules.
Initialize the OpenAI client with the API key from os.environ.
Construct a chat message with a prompt instructing the model to translate the given text specifying source and target languages.
Call client.chat.completions.create with the chosen model and messages.
Extract the translated text from response.choices[0].message.content.

Full code

python

import os
from openai import OpenAI

def translate_text(text: str, source_lang: str, target_lang: str) -> str:
    client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
    prompt = (
        f"Translate the following text from {source_lang} to {target_lang}:\n" + text
    )
    response = client.chat.completions.create(
        model="gpt-4o",
        messages=[{"role": "user", "content": prompt}]
    )
    return response.choices[0].message.content.strip()

if __name__ == "__main__":
    source = "English"
    target = "Spanish"
    text_to_translate = "Hello, how are you?"
    translation = translate_text(text_to_translate, source, target)
    print(f"Original ({source}): {text_to_translate}")
    print(f"Translated ({target}): {translation}")

output

Original (English): Hello, how are you?
Translated (Spanish): Hola, ¿cómo estás?

API trace

Request

json

{"model": "gpt-4o", "messages": [{"role": "user", "content": "Translate the following text from English to Spanish:\nHello, how are you?"}]}

Response

json

{"choices": [{"message": {"content": "Hola, ¿cómo estás?"}}], "usage": {"prompt_tokens": 20, "completion_tokens": 7, "total_tokens": 27}}

Extractresponse.choices[0].message.content

Variants

Streaming translation ›

Use streaming to display translation output token-by-token for better user experience with longer texts.

python

import os
from openai import OpenAI

def translate_text_stream(text: str, source_lang: str, target_lang: str) -> None:
    client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
    prompt = f"Translate the following text from {source_lang} to {target_lang}:\n" + text
    stream = client.chat.completions.create(
        model="gpt-4o",
        messages=[{"role": "user", "content": prompt}],
        stream=True
    )
    print(f"Translation ({target_lang}):", end=" ")
    for chunk in stream:
        delta = chunk.choices[0].delta.content or ""
        print(delta, end="", flush=True)
    print()  # newline

if __name__ == "__main__":
    translate_text_stream("Good morning, have a nice day!", "English", "French")

Async translation ›

Use async calls when integrating translation in an async application or to handle multiple concurrent translations.

python

import os
import asyncio
from openai import OpenAI

async def translate_text_async(text: str, source_lang: str, target_lang: str) -> str:
    client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
    prompt = f"Translate the following text from {source_lang} to {target_lang}:\n" + text
    response = await client.chat.completions.acreate(
        model="gpt-4o",
        messages=[{"role": "user", "content": prompt}]
    )
    return response.choices[0].message.content.strip()

async def main():
    translation = await translate_text_async("Thank you very much", "English", "Japanese")
    print(f"Translated (Japanese): {translation}")

if __name__ == "__main__":
    asyncio.run(main())

Use smaller model for cost efficiency ›

Use gpt-4o-mini for lower cost and faster responses when translation quality requirements are moderate.

python

import os
from openai import OpenAI

def translate_text_cost_efficient(text: str, source_lang: str, target_lang: str) -> str:
    client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
    prompt = f"Translate the following text from {source_lang} to {target_lang}:\n" + text
    response = client.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": prompt}]
    )
    return response.choices[0].message.content.strip()

if __name__ == "__main__":
    translation = translate_text_cost_efficient("Hello, how are you?", "English", "Spanish")
    print(f"Translated (Spanish): {translation}")

Performance

Latency~800ms for gpt-4o non-streaming translation

Cost~$0.002 per 500 tokens for gpt-4o

Rate limitsTier 1: 500 requests per minute / 30,000 tokens per minute

Keep prompts concise to reduce token usage.
Use smaller models like gpt-4o-mini for cost savings.
Cache frequent translations to avoid repeated calls.

Approach	Latency	Cost/call	Best for
Standard call with gpt-4o	~800ms	~$0.002 per 500 tokens	High-quality translations
Streaming with gpt-4o	~800ms initial + streaming	~$0.002 per 500 tokens	Better UX for long texts
Async call with gpt-4o	~800ms	~$0.002 per 500 tokens	Concurrent translation tasks
Cost-efficient with gpt-4o-mini	~400ms	~$0.0005 per 500 tokens	Budget-conscious or lower quality needs

✓

Quick tip

Explicitly instruct the model with source and target languages in the prompt for accurate translations.

⚠

Common mistake

Not specifying source and target languages clearly in the prompt, leading to incorrect or incomplete translations.

Verified 2026-04 · gpt-4o, gpt-4o-mini

Verify ↗

Community Notes

No notes yetBe the first to share a version-specific fix or tip.