Gemini 2.5 Flash API pricing

What does Gemini 2.5 Flash cost per request?

A typical request of 5,000 input tokens and 1,500 output tokens costs about $0.005 at list price. A thousand of those requests costs about $5.25.

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 Flash fits

Gemini 2.5 Flash offers the 1M token context window of the Pro model at $0.30 per 1M input tokens, which makes long-input workloads affordable at volume.

Pick it when

• You are extracting fields from long documents at scale rather than reasoning over them.
• You want a large context window on a budget for classification, tagging or summarisation.
• You are prototyping a pipeline and want to see cost per thousand calls before switching to a stronger model.

What to watch

• Reasoning depth is lower than the Pro tier, so keep an escalation path for the cases it gets wrong.
• A 1M window at $0.30 per 1M tokens still costs real money at volume - measure before you assume the price is negligible.

Best for: Large-scale extraction, document summarisation and the first pass of any long-input pipeline.

How to call Gemini 2.5 Flash through the gateway

Point your client at https://api.quickrouter.homes/v1 with a QuickRouter key and pass gemini-2.5-flash 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-flash",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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