GPT-5 mini API pricing

What does GPT-5 mini cost per request?

A typical request of 5,000 input tokens and 1,500 output tokens costs about $0.004 at list price. A thousand of those requests costs about $4.25.

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 GPT-5 mini fits

GPT-5 mini keeps the 400K context window of the flagship at roughly a fifth of the input price, which makes it the default for high-volume and high-concurrency work.

Pick it when

• You are classifying, extracting or summarising at scale, where the cost per call matters more than the last increment of quality.
• You need a long context window but you are reading far more tokens than you generate.
• You are building a sub-agent or an editor helper that runs on every keystroke or save.

What to watch

• Harder multi-step reasoning degrades earlier than on the flagship, so escalate the hard cases rather than retrying them.
• Output still costs eight times input, so cap generated length when you are producing long documents.

Best for: Bulk extraction, retrieval summaries and the cheap half of a two-model agent setup.

How to call GPT-5 mini through the gateway

Point your client at https://api.quickrouter.homes/v1 with a QuickRouter key and pass gpt-5-mini 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": "gpt-5-mini",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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