Opublikowano 2026-08-16 · 赵予安
Bezpośrednia odpowiedź
OpenAI GPT-4o-mini is listed at 0.022 / 0.087 per million tokens, with a 128,000 token context window. CacheSafety for this exact id is unpublished. Ten przewodnik jest przeznaczony dla zespołów produktowych i platformowych, które porównują jakość modeli, koszt, politykę routingu i ryzyko wdrożenia.
What shipped
OpenAI has GPT-4o-mini live in the NextModel catalog, priced at $0.022 in and $0.087 out per 1M tokens. The public model id is openai--gpt-4o-mini. The API model id is openai/gpt-4o-mini. It has a 128000 token context window and a 1000-3000ms latency band. The model has streaming, tool, json, vision, and long capabilities.
Pricing and context
Input price is $0.022 per 1M tokens. Output price is $0.087 per 1M tokens. The context window is 128000 tokens. Related catalog entries include OpenAI: GPT-4.1 Nano at $0.014 in and $0.058 out, OpenAI: GPT-5.4 Nano at $0.029 in and $0.181 out, and OpenAI: GPT-5.6 Luna at $0.029 in and $0.174 out.
Who this is for
The catalog lists vision, long-context, and agent as use cases. Developers can select the model for those workload types through the NextModel gateway.
What remains unverified
Release date is unpublished in this catalog snapshot. Independent third-party quality scores are not in these notes. The NextModel bench table has no first-party CacheSafety row for this exact model, so Safe Hit, Bad Hit, and trap rates are unpublished.