OpenAI
GPT-5 nano
openai/gpt-5.4-nano
GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...
Only tracked on Vercel AI Gateway.
GPT-5 nano usage over time
Vercel AI Gateway share of tokens, by day.
GPT-5 nano holds 3.27% today, up from 0.30% at the start of the visible window.
Rank history
Adoption curve vs the pantheon
GPT-5 nano's share plotted against days since first tracked, overlaid on other current leaders on the same axis. The question every new-model page asks: is this one going to make it?
Citable stat
As of 2026-09-02, GPT-5 nano holds 0.0% of Vercel AI Gateway token share, down 7.57pp over 30 days. Source: Tidelines (Vercel AI Gateway).
Cost per session
Median dollars spent on one GPT-5 nano session, by coding agent and session length.
Token rate sets the price; session length and reasoning set the bill.
| Agent | 1 turn | 2–9 turns | 10–49 turns |
|---|---|---|---|
| Hermes Agent | $0.0013 | $0.0070 | $0.039 |
Where to run it
GPT-5 nano pricing by provider
Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.
GPT-5 nano is served by 4 tracked endpoints on OpenRouter. The cheapest output price is $0.63 per million tokens from OpenAI · 400k, and the most expensive is $1.38 from Azure · 400k. The largest context window offered is 400k tokens. Prices are list rates and refresh daily.
| Provider | Input $/M | Output $/M | Context | Uptime |
|---|---|---|---|---|
| OpenAI · 400k | $0.10 | $0.63 | 400k | — |
| Azure · 400k | $0.20 | $1.25 | 400k | 99.97% |
| OpenAI · 400k | $0.20 | $1.25 | 400k | 89.76% |
| Azure · 400k | $0.22 | $1.38 | 400k | 99.94% |