Google Compatible
Google Gemini API proxy - Access Gemini Pro, Gemini 1.5 Pro, Gemini Flash through UniterRouter. Native Google AI SDK support with multimodal, grounding and code execution.
Google Compatible API
UniterRouter provides a native proxy for Google's Gemini API, allowing you to use the Google AI SDK directly while benefiting from unified billing and API key management.
Full API Support: All Google Gemini API endpoints are proxied directly with complete parameter compatibility. All official features including Thinking, Function Calling, Code Execution, and Grounding are supported.
Features
Text Generation
Generate text, code, and creative content
Image Generation (Nano Banana)
Create and edit images with AI - up to 4K resolution
Structured Output
JSON mode with schema validation
Extended Thinking
Deep reasoning for complex problems
Vision
Image and video understanding
Function Calling
Tool use and external integrations
Code Execution
Run Python code in sandbox
Grounding
Real-time Google Search integration
Embeddings
Text embeddings for semantic search
Supported Endpoints
All /v1beta/models/{model}:* endpoints are supported:
| Endpoint | Method | Description |
|---|---|---|
:generateContent | POST | Generate content |
:streamGenerateContent | POST | Stream generate content |
:embedContent | POST | Generate embeddings |
:countTokens | POST | Count tokens |
:batchEmbedContents | POST | Batch embeddings |
Quick Start
import google.generativeai as genai
genai.configure(
api_key="your_uniterouter_api_key",
transport="rest",
client_options={"api_endpoint": "api.uniterouter.ai"}
)
model = genai.GenerativeModel("gemini-2.0-flash")
response = model.generate_content("Hello!")
print(response.text)SDK Installation
Python
pip install google-generativeaiTypeScript/Node.js
npm install @google/generative-aiSupported Models
Gemini 2.x (Latest)
| Model | Description | Context | Features |
|---|---|---|---|
gemini-2.5-pro | Most capable Gemini | 1M | Thinking, Vision, Tools |
gemini-2.5-flash | Fast and capable | 1M | Thinking, Vision, Tools |
gemini-2.0-flash | Latest flash model | 1M | Vision, Tools, Code |
gemini-2.0-flash-thinking-exp | Extended thinking | 1M | Deep reasoning |
Gemini 1.5
| Model | Description | Context | Features |
|---|---|---|---|
gemini-1.5-pro | Best for complex tasks | 2M | Vision, Tools |
gemini-1.5-flash | Balanced performance | 1M | Vision, Tools |
gemini-1.5-flash-8b | Lightweight | 1M | Fast inference |
Specialized Models
| Model | Description | Use Case |
|---|---|---|
gemini-embedding-001 | Text embeddings | Semantic search |
text-embedding-004 | Latest embeddings | RAG, similarity |
imagen-3.0-generate-001 | Image generation | Creative |
veo-001 | Video generation | Creative |
How is this guide?
Messages POST
Claude API Messages endpoint - Create Claude 3.5 Sonnet, Claude 3 Opus conversations through UniterRouter. Anthropic-compatible API with streaming and tool use support.
Generate Content POST
Google Gemini API - Generate content with Gemini Pro, Gemini 1.5 models through UniterRouter. Native Google AI API format with multimodal and streaming support.