OpenAI
OpenAI: GPT-4o-mini
openai/gpt-4o-mini
GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...
OpenAI: GPT-4o-mini usage over time
OpenRouter share of tokens, by day.
OpenAI: GPT-4o-mini holds 0.22% today, down from 2.22% at the start of the visible window.
Rank history
Adoption curve vs the pantheon
OpenAI: GPT-4o-mini'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 2026-09-01, OpenAI: GPT-4o-mini holds 0.2% of OpenRouter token share, down 0.12pp over 30 days. Source: Tidelines (OpenRouter).
Cost per session
Median dollars spent on one OpenAI: GPT-4o-mini 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 | 50+ turns |
|---|---|---|---|---|
| Hermes Agent | $0.0018 | $0.0052 | $0.037 | $0.203 |
Where to run it
OpenAI: GPT-4o-mini pricing by provider
Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.
OpenAI: GPT-4o-mini is served by 3 tracked endpoints on OpenRouter. The cheapest output price is $0.60 per million tokens from Azure · 128k, and the most expensive is $0.66 from Azure · 128k. The largest context window offered is 128k tokens. Prices are list rates and refresh daily.
| Provider | Input $/M | Output $/M | Context | Uptime |
|---|---|---|---|---|
| Azure · 128k | $0.15 | $0.60 | 128k | 99.86% |
| OpenAI | $0.15 | $0.60 | 128k | 99.99% |
| Azure · 128k | $0.17 | $0.66 | 128k | — |