Gemini 3 Flash
Gemini 3 Flash API on UniRoute enables Pro-level reasoning, multimodal understanding, and agentic workflows with low latency and efficient inference.
Pricing
| Billing unit | UniRoute | Market |
|---|---|---|
| Input | $0.15 | $0.50 |
| Output | $0.90 | $3.00 |
per 1M tokens
About this model
Gemini 3 Flash API on UniRoute enables Pro-level reasoning, multimodal understanding, and agentic workflows with low latency and efficient inference.
Call it with one request
Works with the OpenAI SDK — just change the base URL.
curl https://api.uniroute.dev/v1/chat/completions \
-H "Authorization: Bearer $UNIROUTE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3-flash",
"messages": [{ "role": "user", "content": "Hello!" }],
"stream": true
}'Related models
NewGemini 3.6 Flash is Google’s efficient AI model built for coding, knowledge work, agentic applications, and multimodal understanding, delivering stronger performance with improved token efficiency.
Build with Google Gemini 3.5 Flash API on UniRoute for agentic coding, multimodal reasoning, long-context analysis, structured outputs, and real AI product workflows.
Gemini 3.1 Pro API is the latest general-purpose LLM developed by Google DeepMind, designed to bridge the gap between high-speed execution and deep logic. It empowers developers to build sophisticated agents with state-of-the-art accuracy in coding, creative writing, and cross-modal analysis.