Use Inference APIs with OpenAI Python SDK

pip install openai

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.inferenceapis.com/v1", api_key=os.environ["INFERENCE_API_KEY"])

resp = client.chat.completions.create(
    model="openai/gpt-oss-120b",
    messages=[{"role": "user", "content": "Hello"}],
    max_tokens=400,
)
print(resp.choices[0].message.content)

with client.chat.completions.stream(model="deepseek-ai/DeepSeek-V4-Flash", messages=[{"role": "user", "content": "Write a haiku"}]) as s:
    for event in s:
        if event.type == "content.delta":
            print(event.delta, end="", flush=True)

audio = client.audio.speech.create(model="hexgrad/Kokoro-82M", voice="af_heart", input="Hello there")
audio.write_to_file("hello.mp3")

with open("hello.mp3", "rb") as f:
    text = client.audio.transcriptions.create(model="openai/whisper-large-v3", file=f).text
print(text)

export OPENAI_BASE_URL="https://api.inferenceapis.com/v1"
export OPENAI_API_KEY="$INFERENCE_API_KEY"   # then OpenAI() with no arguments

python -c "from openai import OpenAI; import os; print([m.id for m in OpenAI(base_url='https://api.inferenceapis.com/v1', api_key=os.environ['INFERENCE_API_KEY']).models.list().data][:5])"