Стриминг

POST /v1/chat/completions stream: true

Потоковая передача ответов через Server-Sent Events (SSE). Ответы приходят частями, что улучшает UX и сокращает время ожидания.

from openai import OpenAI

client = OpenAI(
    api_key="rp_ваш_api_ключ",
    base_url="https://api.modelgate.ru/v1"
)

stream = client.chat.completions.create(
    model="deepseek-v3.2",
    messages=[{"role": "user", "content": "Расскажи анекдот"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
import OpenAI from 'openai';

const client = new OpenAI({
    apiKey: 'rp_ваш_api_ключ',
    baseURL: 'https://api.modelgate.ru/v1',
});

const stream = await client.chat.completions.create({
    model: 'deepseek-v3.2',
    messages: [{ role: 'user', content: 'Расскажи анекдот' }],
    stream: true,
});

for await (const chunk of stream) {
    if (chunk.choices[0].delta.content) {
        process.stdout.write(chunk.choices[0].delta.content);
    }
}
curl -X POST https://api.modelgate.ru/v1/chat/completions \
  -H "Authorization: Bearer rp_ваш_api_ключ" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v3.2",
    "messages": [{"role": "user", "content": "Расскажи анекдот"}],
    "stream": true
  }'

Формат события

data: {"id":"chatcmpl-xxx","object":"chat.chunk","choices":[{"index":0,"delta":{"content":"При"},"finish_reason":null}]}
data: {"id":"chatcmpl-xxx","object":"chat.chunk","choices":[{"index":0,"delta":{"content":"вет"},"finish_reason":null}]}
data: {"id":"chatcmpl-xxx","object":"chat.chunk","choices":[{"index":0,"delta":{"content":"!"},"finish_reason":"stop"}],"usage":{"prompt_tokens":10,"completion_tokens":2,"total_tokens":12}}
data: [DONE]