Gemini 2.5 Pro API pricing

What does Gemini 2.5 Pro cost per request?

A typical request of 5,000 input tokens and 1,500 output tokens costs about $0.021 at list price. A thousand of those requests costs about $21.25.

Model usage is drawn from your balance at the upstream list price of each model. Figures above are indicative and exclude any plan fee; the console is the source of truth for live pricing.

Where Gemini 2.5 Pro fits

Gemini 2.5 Pro pairs a 1M token context window with the same input price as GPT-5, which makes it the practical option for inputs that are simply too large for other models.

Pick it when

• A single request has to hold an entire codebase, a long transcript or a large document set.
• You want to avoid building a chunking and retrieval pipeline for a one-off analysis.
• You are comparing vendor output on the same long input and want to hold everything else constant.

What to watch

• Filling a 1M token context costs $1.25 on input alone before any output is generated, so measure the call rather than assuming it is cheap.
• Long contexts raise latency, which matters for interactive tools even when the price is acceptable.

Best for: Whole-repository analysis, long-document reasoning and one-shot jobs where chunking would lose the point.

How to call Gemini 2.5 Pro through the gateway

Point your client at https://api.quickrouter.homes/v1 with a QuickRouter key and pass gemini-2.5-pro as the model name. Nothing else in an OpenAI-style client changes.

curl https://api.quickrouter.homes/v1/chat/completions \
  -H "Authorization: Bearer sk-qr-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-pro",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

The console lists the model ids your key can reach - use the id exactly as it appears there.