Đăng ngày 2026-08-16 · 赵予安
Trả lời trực tiếp
OpenAI GPT-4o is listed at 2.50 / 10 per million tokens, with a 128,000 token context window. CacheSafety for this exact id is unpublished. Hướng dẫn này dành cho các đội sản phẩm và nền tảng đang so sánh chất lượng model, chi phí, chính sách định tuyến, và rủi ro ra mắt.
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 $2.50 per million input tokens and $10 per million output tokens. The catalog display name is OpenAI: GPT-4o. The provider is OpenAI.
Pricing and context
Input price is $2.50 per 1M tokens. Output price is $10 per 1M tokens. Context window is 128000 tokens. Latency band is 1000 to 3000ms. Related catalog entries include OpenAI: GPT-5.4 at $2.50 per 1M input tokens and $15 per 1M output tokens, OpenAI: GPT-4.1 at $2 per 1M input tokens and $8 per 1M output tokens, and OpenAI: GPT-5.6 Terra at $2 per 1M input tokens and $12 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Release date is unpublished in this catalog snapshot.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.