GPT-5 Nano

openai/gpt-5-nano

text, image, document in · text out · 400,000 context · 128,000 max output

toolsschemavisionreasoningcacheno-train
Effective cost per 1k requests

cost = p_in·(input − cached) + p_cache_read·cached + p_out·output + p_req; cached tokens are the prefix a sticky endpoint already holds (part2b §9.3), which is why the cheapest list price is not always the cheapest request.

ProviderRegion · quantContext / max outInput / MOutput / MCache read / writeMarkupPer 1k reqUptime 30 dTTFT p50 / p95ThroughputLast 24 hFidelityDataCapabilitiesStatus
OpenRouterglobal · unknown400,000 / 128,000$0.053$0.420$0.005 / —+5.0%$0.268———no traffic— no-train 30 dmodel defaultactive

Quick start

curl https://api.ai.ml/v1/chat/completions \
  -H "Authorization: Bearer $AIML_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-5-nano","messages":[{"role":"user","content":"Say hello"}]}'
Get a key in the console

Changelog

  • new_model model openai/gpt-5-nano added (active); endpoint ep_openrouter_gpt-5-nano_global (openai/gpt-5-nano) added as active; price input 0.053 output 0.420 USD/M 10/5/2026