#1
DeepInfra
models.global_route 🟢 280ms 🎁 Official Free Tier · Daily Auto Refresh (32k Context · 每日自动重置)
Google DeepMind's premier open weights model built on Gemini tech, delivering state-of-the-art reasoning and task versatility at lightweight scale.
Ranked by live health & lowest latency. Copy provider model ID or claim free keys directly.
Fully compatible with OpenAI SDK. Replace the API Key and execute directly in Python or cURL.
from openai import OpenAI
# 1. 替换为对应厂商领取的 API Key 与 Base URL (参见下方厂商雷达表)
client = OpenAI(
api_key="your_api_key_here",
base_url="https://api.siliconflow.cn/v1" # 示例: 硅基流动直连端点
)
response = client.chat.completions.create(
model="google/gemma-3-27b-it",
messages=[
{"role": "system", "content": "You are a helpful AI assistant."},
{"role": "user", "content": "Hello! Please introduce yourself briefly."}
],
temperature=0.6,
stream=True
)
for chunk in response:
if chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="", flush=True)
curl https://api.siliconflow.cn/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer your_api_key_here" \
-d '{
"model": "google/gemma-3-27b-it",
"messages": [
{"role": "user", "content": "Hello!"}
],
"temperature": 0.7
}'