$5 free credits when you sign up
Back to Models
Vertex AI

Gemini 2.5 Flash

Fast, cost-efficient general-purpose model with 1M context, vision, and function calling — ideal for high-volume workloads.

Released

Context Window

1.0M

tokens
Max Output

65.5K

tokens
Input / 1M

$0.15

per 1M tokens
Output / 1M

$0.60

per 1M tokens

Capabilities

Vision
Function Calling
Streaming
JSON Mode
System Prompt
Tool Use

Pricing Comparison

Quick Start

curl
curl -X POST https://api.nemorouter.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-api-key" \
  -d '{
    "model": "gemini-2.5-flash",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello!"}
    ],
    "max_tokens": 256
  }'

Replace sk-your-api-key with your NemoRouter API key. Use gemini-2.5-flash as the model identifier.