Google (Gemini)

Google's Gemini models — native multimodal understanding, long context, thinking, image/video generation, TTS/STT, and embeddings.

Overview

Google AI provides the Gemini family of natively multimodal models, with long context, built-in reasoning, and a broad range of generation and understanding capabilities.

Official Website: https://ai.google.dev API Documentation: https://ai.google.dev/gemini-api/docs

Key features

Native multimodal — built-in vision, video, and audio understanding
Long context — very large context windows
Thinking — extended reasoning for complex problems
Image & video generation — text-to-image and text-to-video models
Audio — text-to-speech and speech-to-text
Embeddings — text embeddings for semantic search
Context caching — cache reused content to cut cost and latency
Realtime — low-latency bidirectional streaming (Gemini Live)

Address Gemini models by prefixing the model id with the google slug — google/<model> (for example google/gemini-...). You always call the same Yunxin base URL, https://api.yuhuanstudio.com/v1, with your sk- API key; Yunxin routes the request to Google's Gemini API.

Usage example

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["YUNXIN_API_KEY"],
    base_url="https://api.yuhuanstudio.com/v1",
)

response = client.chat.completions.create(
    model="google/gemini-model-id",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"},
    ],
)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.YUNXIN_API_KEY,
  baseURL: "https://api.yuhuanstudio.com/v1",
});

const response = await client.chat.completions.create({
  model: "google/gemini-model-id",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Hello!" },
  ],
});

console.log(response.choices[0].message.content);

curl https://api.yuhuanstudio.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YUNXIN_API_KEY" \
  -d '{
    "model": "google/gemini-model-id",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello!"}
    ]
  }'

Available models

List the models currently available for this provider:

curl "https://api.yuhuanstudio.com/v1/models?provider=google" \
  -H "Authorization: Bearer $YUNXIN_API_KEY"

Capabilities and pricing are per-model. Use the Models API to discover which Gemini models are available and what each one supports.

Native multimodal — built-in vision, video, and audio understanding
Long context — very large context windows
Thinking — extended reasoning for complex problems
Image & video generation — text-to-image and text-to-video models
Audio — text-to-speech and speech-to-text
Embeddings — text embeddings for semantic search
Context caching — cache reused content to cut cost and latency
Realtime — low-latency bidirectional streaming (Gemini Live)

Using Google with Yunxin

Usage example

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["YUNXIN_API_KEY"],
    base_url="https://api.yuhuanstudio.com/v1",
)

response = client.chat.completions.create(
    model="google/gemini-model-id",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"},
    ],
)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.YUNXIN_API_KEY,
  baseURL: "https://api.yuhuanstudio.com/v1",
});

const response = await client.chat.completions.create({
  model: "google/gemini-model-id",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Hello!" },
  ],
});

console.log(response.choices[0].message.content);

curl https://api.yuhuanstudio.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YUNXIN_API_KEY" \
  -d '{
    "model": "google/gemini-model-id",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello!"}
    ]
  }'

Available models

List the models currently available for this provider:

curl "https://api.yuhuanstudio.com/v1/models?provider=google" \
  -H "Authorization: Bearer $YUNXIN_API_KEY"

Capabilities and pricing are per-model. Use the Models API to discover which Gemini models are available and what each one supports.

Overview

Key features

Using Google with Yunxin

Usage example

Available models

Official resources

On this page

Google (Gemini)

Overview

Key features

Using Google with Yunxin

Usage example

Available models

Official resources

On this page