OpenAI Launches ChatGPT and Whisper APIs: Features, Pricing, and Sample Code

OpenAI announced that developers can now integrate the ChatGPT conversational model and the Whisper speech‑to‑text model into their own applications via public APIs, offering a much cheaper alternative to using the standard language models.

Since its debut in November 2022, ChatGPT has become a major AI phenomenon, reaching over 100 million monthly active users within two months and sparking widespread interest in AI‑driven chat interfaces.

The new ChatGPT API uses the gpt‑3.5‑turbo model, priced at $0.002 per 1,000 tokens—a 90 % cost reduction compared to previous GPT‑3.5 offerings—and is suitable for many non‑chat use cases, with support for the Chat Markup Language (ChatML) message format.

OpenAI also released a Whisper API for the large‑v2 model, priced at $0.006 per minute of audio, supporting various audio formats (m4a, mp3, mp4, wav, etc.) and offering both transcription and translation endpoints.

Sample Python code for the ChatGPT API:

<code>import openai
completion = openai.ChatCompletion.create(
    model="gpt-3.5-turbo",
    messages=[{"role": "user", "content": "Tell the world about the ChatGPT API in the style of a pirate."}]
)
print(completion)</code>

Sample Python code for the Whisper API:

<code>import openai
audio_file = open("/path/to/file/openai.mp3", "rb")
transcription = openai.Audio.transcribe("whisper-1", audio_file)
print(transcription)</code>

OpenAI plans continuous improvements to the ChatGPT model, with version updates such as gpt‑3.5‑turbo‑0301 guaranteed support until at least June 1, and a stable version update scheduled for April.

These APIs enable third‑party developers to build next‑generation applications powered by advanced conversational and speech‑to‑text capabilities.