Streaming

curl --fail-with-body -N https://api.pre.dev/v1/chat/completions \
  -H "Authorization: Bearer $PREDEV_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3.8-flash",
    "stream": true,
    "messages": [{ "role": "user", "content": "Count from one to ten." }]
  }'

import OpenAI from 'openai';

const client = new OpenAI({ baseURL: 'https://api.pre.dev/v1', apiKey: process.env.PREDEV_API_KEY! });

const stream = await client.chat.completions.create({
  model: 'google/gemini-3.8-flash',
  stream: true,
  messages: [{ role: 'user', content: 'Count from one to ten.' }],
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? '');
  if (chunk.usage) console.log('\ncost usd:', (chunk.usage as any).cost);
}

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.pre.dev/v1", api_key=os.environ["PREDEV_API_KEY"])

stream = client.chat.completions.create(
    model="google/gemini-3.8-flash",
    stream=True,
    messages=[{"role": "user", "content": "Count from one to ten."}],
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
    if chunk.usage:
        print("\ncost usd:", chunk.usage.model_dump().get("cost"))

import { createOpenAI } from '@ai-sdk/openai';
import { streamText } from 'ai';

const predev = createOpenAI({ baseURL: 'https://api.pre.dev/v1', apiKey: process.env.PREDEV_API_KEY! });

const result = streamText({
  model: predev('google/gemini-3.8-flash'),
  prompt: 'Count from one to ten.',
});
for await (const part of result.textStream) process.stdout.write(part);