SDK integration

Installation

Python

pip install openai

Node.js

npm install openai

Python call

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.yomiapi.com/v1"
)

response = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Explain the purpose of an API gateway in one sentence"}]
)
print(response.choices[0].message.content)

Node.js call

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_API_KEY",
  baseURL: "https://api.yomiapi.com/v1"
});

const completion = await client.chat.completions.create({
  model: "deepseek-v4-flash",
  messages: [{ role: "user", content: "Explain the purpose of an API gateway in one sentence" }]
});
console.log(completion.choices[0].message.content);

Streaming output

Set stream=True to receive content incrementally, suitable for chat interfaces and other uses requiring immediate feedback:

stream = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Write a 100-character product introduction"}],
    stream=True
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Supported capabilities

• Function Calling: Define tools with the standard tools parameter; the model returns structured tool-call requests.
• Multimodal input: Provide images through image_url content blocks with multimodal models such as claude-sonnet-5.
• Embeddings: client.embeddings.create generates vectors using an available embedding model from the Model Catalog.
• Audio: Transcription, translation and synthesis endpoints in the /v1/audio family are all accessible through the SDK.
• Responses API: client.responses is directly available; see OpenAI Responses API.