Veröffentlicht am 2026-08-16 · 赵予安
Direkte Antwort
OpenAI GPT-4o is listed at 0.362 / 1.447 per million tokens, with a 128,000 token context window. CacheSafety for this exact id is unpublished. Dieser Leitfaden richtet sich an Produkt- und Plattformteams, die Modellqualität, Kosten, Routing-Politik und Rolloutrisiko vergleichen.
What shipped
OpenAI's GPT-4o is now listed in the NextModel catalog as openai/gpt-4o, with public slug openai--gpt-4o. It costs $0.362 per million input tokens and $1.447 per million output tokens. The catalog display name is OpenAI: GPT-4o. The provider is OpenAI.
Pricing and context
Input price is $0.362 per 1M tokens. Output price is $1.447 per 1M tokens. Context window is 128000 tokens. Latency band is 1000 to 3000ms. Related catalog entries include OpenAI: GPT-5.4 at $0.362 per 1M input tokens and $2.170 per 1M output tokens, OpenAI: GPT-4.1 at $0.289 per 1M input tokens and $1.157 per 1M output tokens, and OpenAI: GPT-5.6 Terra at $0.289 per 1M input tokens and $1.736 per 1M output tokens.
Who this is for
This catalog listing is for developers building vision, long-context, and agent use cases. The model has capabilities for streaming, tool use, JSON output, vision, and long-context input. The context window is 128000 tokens, and the latency band is 1000 to 3000ms.
What is still unverified
Release date is unpublished in this catalog snapshot. Independent third-party quality scores are not in these notes. No first-party CacheSafety row exists for this exact model in the NextModel bench table. Safe Hit, Bad Hit, and trap rates are not listed.