Streaming

import os

from openai import OpenAI

openai = OpenAI(
    api_key=os.environ["DEEPINFRA_API_KEY"],
    base_url="https://api.deepinfra.com/v1/openai",
)

stream = openai.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4-Flash-0731",
    messages=[{"role": "user", "content": "Hello"}],
    stream=True,
)

for event in stream:
    if event.choices[0].finish_reason:
        print(event.choices[0].finish_reason,
              event.usage['prompt_tokens'],
              event.usage['completion_tokens'])
    else:
        print(event.choices[0].delta.content, end="", flush=True)

import OpenAI from "openai";

const openai = new OpenAI({
  apiKey: process.env.DEEPINFRA_API_KEY,
  baseURL: "https://api.deepinfra.com/v1/openai",
});

const completion = await openai.chat.completions.create({
  messages: [{ role: "user", content: "Hello" }],
  model: "deepseek-ai/DeepSeek-V4-Flash-0731",
  stream: true,
});

for await (const chunk of completion) {
  if (chunk.choices[0].finish_reason) {
    console.log(chunk.choices[0].finish_reason,
                chunk.usage.prompt_tokens,
                chunk.usage.completion_tokens);
  } else {
    process.stdout.write(chunk.choices[0].delta.content);
  }
}

curl "https://api.deepinfra.com/v1/openai/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $DEEPINFRA_API_KEY" \
  -d '{
      "model": "deepseek-ai/DeepSeek-V4-Flash-0731",
      "stream": true,
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ]
    }'