GPT-5 API pricing

What does GPT-5 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 GPT-5 fits

GPT-5 is the flagship model in the OpenAI family on this gateway, with a 400K context window and the highest output price of the GPT-5 tier.

Pick it when

• The task needs multi-step reasoning that a smaller model gets wrong, such as planning a refactor across several files.
• A single request has to carry a large amount of context - a long repository summary or a lengthy specification.
• You are running an agent loop where a wrong tool call costs more than the tokens do.

What to watch

• Output costs eight times as much as input, so long generated answers drive the bill more than long prompts.
• GPT-5 mini shares the same 400K context window at a fifth of the input price, which makes mini the better default for high-volume work.

Best for: Agentic coding, multi-step analysis and the reasoning steps you would rather not retry.

How to call GPT-5 through the gateway

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

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